Model builder (#29)

Co-authored-by: Ayush Chaurasia <ayush.chuararsia@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

ultralytics/tests/assets/dummy_model.yaml

@@ -0,0 +1,49 @@
+# Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]
+

ultralytics/tests/functional/test_loaders.py

@@ -0,0 +1,34 @@
+import torch
+
+from ultralytics.yolo.utils.checks import check_yaml
+from ultralytics.yolo.utils.modeling.tasks import DetectionModel
+
+
+def test_model_parser():
+    cfg = check_yaml("../assets/dummy_model.yaml")  # check YAML
+
+    # Create model
+    model = DetectionModel(cfg)
+    print(model)
+    '''
+    # Options
+    if opt.line_profile:  # profile layer by layer
+        model(im, profile=True)
+
+    elif opt.profile:  # profile forward-backward
+        results = profile(input=im, ops=[model], n=3)
+
+    elif opt.test:  # test all models
+        for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
+            try:
+                _ = Model(cfg)
+            except Exception as e:
+                print(f'Error in {cfg}: {e}')
+
+    else:  # report fused model summary
+        model.fuse()
+    '''
+
+
+if __name__ == "__main__":
+    test_model_parser()

ultralytics/yolo/data/__init__.py

@@ -1,3 +1,4 @@
+from .base import BaseDataset
 from .build import build_classification_dataloader, build_dataloader
 from .dataset import ClassificationDataset, SemanticDataset, YOLODataset
 from .dataset_wrappers import MixAndRectDataset

ultralytics/yolo/data/augment.py

@@ -8,9 +8,12 @@ import numpy as np
 import torch
 import torchvision.transforms as T
 
-from ..utils.general import LOGGER, check_version, colorstr, segment2box
+from ..utils import LOGGER
+from ..utils.checks import check_version
 from ..utils.instance import Instances
+from ..utils.loggers import colorstr
 from ..utils.metrics import bbox_ioa
+from ..utils.ops import segment2box
 from .utils import IMAGENET_MEAN, IMAGENET_STD, polygons2masks, polygons2masks_overlap
 
 
@@ -457,8 +460,8 @@ class LetterBox:
         self.scaleup = scaleup
         self.stride = stride
 
-    def __call__(self, labels):
-        img = labels["img"]
+    def __call__(self, labels={}, image=None):
+        img = image or labels["img"]
         shape = img.shape[:2]  # current shape [height, width]
         new_shape = labels.get("rect_shape", self.new_shape)
         if isinstance(new_shape, int):

ultralytics/yolo/data/base.py

@@ -9,7 +9,7 @@ import numpy as np
 from torch.utils.data import Dataset
 from tqdm import tqdm
 
-from ..utils.general import NUM_THREADS
+from ..utils import NUM_THREADS
 from .utils import BAR_FORMAT, HELP_URL, IMG_FORMATS, LOCAL_RANK
 
 

ultralytics/yolo/data/build.py

@@ -5,7 +5,7 @@ import numpy as np
 import torch
 from torch.utils.data import DataLoader, dataloader, distributed
 
-from ..utils.general import LOGGER
+from ..utils import LOGGER
 from ..utils.torch_utils import torch_distributed_zero_first
 from .dataset import ClassificationDataset, YOLODataset
 from .utils import PIN_MEMORY, RANK

ultralytics/yolo/data/dataset.py

@@ -5,7 +5,7 @@ from pathlib import Path
 import torchvision
 from tqdm import tqdm
 
-from ..utils.general import NUM_THREADS
+from ..utils import NUM_THREADS
 from .augment import *
 from .base import BaseDataset
 from .utils import BAR_FORMAT, HELP_URL, LOCAL_RANK, get_hash, img2label_paths, verify_image_label

ultralytics/yolo/data/utils.py

@@ -6,7 +6,7 @@ import cv2
 import numpy as np
 from PIL import ExifTags, Image, ImageOps
 
-from ..utils.general import segments2boxes
+from ..utils.ops import segments2boxes
 
 HELP_URL = "See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data"
 IMG_FORMATS = "bmp", "dng", "jpeg", "jpg", "mpo", "png", "tif", "tiff", "webp", "pfm"  # include image suffixes

ultralytics/yolo/engine/trainer.py

@@ -20,7 +20,8 @@ from tqdm import tqdm
 
 import ultralytics.yolo.utils as utils
 import ultralytics.yolo.utils.loggers as loggers
-from ultralytics.yolo.utils.general import LOGGER, ROOT
+from ultralytics.yolo.utils import LOGGER, ROOT
+from ultralytics.yolo.utils.files import increment_path, save_yaml
 
 CONFIG_PATH_ABS = ROOT / "yolo/utils/configs"
 DEFAULT_CONFIG = "defaults.yaml"
@@ -35,16 +36,16 @@ class BaseTrainer:
         self.callbacks = defaultdict(list)
         self.console.info(f"Training config: \n train: \n {self.train} \n hyps: \n {self.hyps}")  # to debug
         # Directories
-        self.save_dir = utils.increment_path(Path(self.train.project) / self.train.name, exist_ok=self.train.exist_ok)
+        self.save_dir = increment_path(Path(self.train.project) / self.train.name, exist_ok=self.train.exist_ok)
         self.wdir = self.save_dir / 'weights'
         self.wdir.mkdir(parents=True, exist_ok=True)  # make dir
         self.last, self.best = self.wdir / 'last.pt', self.wdir / 'best.pt'
 
         # Save run settings
-        utils.save_yaml(self.save_dir / 'train.yaml', OmegaConf.to_container(self.train, resolve=True))
+        save_yaml(self.save_dir / 'train.yaml', OmegaConf.to_container(self.train, resolve=True))
 
         # device
-        self.device = utils.select_device(self.train.device, self.train.batch_size)
+        self.device = utils.torch_utils.select_device(self.train.device, self.train.batch_size)
         self.console.info(f"running on device {self.device}")
         self.scaler = amp.GradScaler(enabled=self.device.type != 'cpu')
 

ultralytics/yolo/engine/validator.py

@@ -3,7 +3,8 @@ import logging
 import torch
 from tqdm import tqdm
 
-from ultralytics.yolo.utils import Profile, select_device
+from ultralytics.yolo.utils.ops import Profile
+from ultralytics.yolo.utils.torch_utils import select_device
 
 
 class BaseValidator:

ultralytics/yolo/utils/__init__.py

@@ -1,18 +1,40 @@
-from .general import Profile, WorkingDirectory, check_version, download, increment_path, save_yaml
-from .torch_utils import LOCAL_RANK, RANK, WORLD_SIZE, DDP_model, select_device, torch_distributed_zero_first
-
-__all__ = [
-    # general
-    "increment_path",
-    "save_yaml",
-    "WorkingDirectory",
-    "download",
-    "check_version",
-    "Profile",
-    # torch
-    "torch_distributed_zero_first",
-    "LOCAL_RANK",
-    "RANK",
-    "WORLD_SIZE",
-    "DDP_model",
-    "select_device"]
+import contextlib
+import logging
+import os
+import platform
+from pathlib import Path
+
+from .files import user_config_dir
+from .loggers import emojis, set_logging
+
+# Constants
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[2]  # YOLOv5 root directory
+RANK = int(os.getenv('RANK', -1))
+DATASETS_DIR = ROOT.parent / 'datasets'  # YOLOv5 datasets directory
+NUM_THREADS = min(8, max(1, os.cpu_count() - 1))  # number of YOLOv5 multiprocessing threads
+AUTOINSTALL = str(os.getenv('YOLOv5_AUTOINSTALL', True)).lower() == 'true'  # global auto-install mode
+FONT = 'Arial.ttf'  # https://ultralytics.com/assets/Arial.ttf
+
+CONFIG_DIR = user_config_dir()  # Ultralytics settings dir
+
+set_logging()  # run before defining LOGGER
+LOGGER = logging.getLogger("yolov5")  # define globally
+if platform.system() == "Windows":
+    for fn in LOGGER.info, LOGGER.warning:
+        setattr(LOGGER, fn.__name__, lambda x: fn(emojis(x)))  # emoji safe logging
+
+
+class TryExcept(contextlib.ContextDecorator):
+    # YOLOv5 TryExcept class. Usage: @TryExcept() decorator or 'with TryExcept():' context manager
+    def __init__(self, msg=''):
+        self.msg = msg
+
+    def __enter__(self):
+        pass
+
+    def __exit__(self, exc_type, value, traceback):
+        if value:
+            print(emojis(f'{self.msg}{value}'))
+        return True

ultralytics/yolo/utils/anchors.py

@@ -0,0 +1,171 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+AutoAnchor utils
+"""
+
+import random
+
+import numpy as np
+import torch
+import yaml
+from tqdm import tqdm
+
+from ultralytics.yolo.data import BaseDataset
+from ultralytics.yolo.utils import LOGGER, TryExcept
+
+from .loggers import colorstr
+
+PREFIX = colorstr('AutoAnchor: ')
+
+
+def check_anchor_order(m):
+    # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary
+    a = m.anchors.prod(-1).mean(-1).view(-1)  # mean anchor area per output layer
+    da = a[-1] - a[0]  # delta a
+    ds = m.stride[-1] - m.stride[0]  # delta s
+    if da and (da.sign() != ds.sign()):  # same order
+        LOGGER.info(f'{PREFIX}Reversing anchor order')
+        m.anchors[:] = m.anchors.flip(0)
+
+
+@TryExcept(f'{PREFIX}ERROR: ')
+def check_anchors(dataset, model, thr=4.0, imgsz=640):
+    # Check anchor fit to data, recompute if necessary
+    m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1]  # Detect()
+    shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1))  # augment scale
+    wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float()  # wh
+
+    def metric(k):  # compute metric
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1 / r).min(2)[0]  # ratio metric
+        best = x.max(1)[0]  # best_x
+        aat = (x > 1 / thr).float().sum(1).mean()  # anchors above threshold
+        bpr = (best > 1 / thr).float().mean()  # best possible recall
+        return bpr, aat
+
+    stride = m.stride.to(m.anchors.device).view(-1, 1, 1)  # model strides
+    anchors = m.anchors.clone() * stride  # current anchors
+    bpr, aat = metric(anchors.cpu().view(-1, 2))
+    s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). '
+    if bpr > 0.98:  # threshold to recompute
+        LOGGER.info(f'{s}Current anchors are a good fit to dataset ✅')
+    else:
+        LOGGER.info(f'{s}Anchors are a poor fit to dataset ⚠️, attempting to improve...')
+        na = m.anchors.numel() // 2  # number of anchors
+        anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
+        new_bpr = metric(anchors)[0]
+        if new_bpr > bpr:  # replace anchors
+            anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
+            m.anchors[:] = anchors.clone().view_as(m.anchors)
+            check_anchor_order(m)  # must be in pixel-space (not grid-space)
+            m.anchors /= stride
+            s = f'{PREFIX}Done ✅ (optional: update model *.yaml to use these anchors in the future)'
+        else:
+            s = f'{PREFIX}Done ⚠️ (original anchors better than new anchors, proceeding with original anchors)'
+        LOGGER.info(s)
+
+
+def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
+    """ Creates kmeans-evolved anchors from training dataset
+
+        Arguments:
+            dataset: path to data.yaml, or a loaded dataset
+            n: number of anchors
+            img_size: image size used for training
+            thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
+            gen: generations to evolve anchors using genetic algorithm
+            verbose: print all results
+
+        Return:
+            k: kmeans evolved anchors
+
+        Usage:
+            from utils.autoanchor import *; _ = kmean_anchors()
+    """
+    from scipy.cluster.vq import kmeans
+
+    npr = np.random
+    thr = 1 / thr
+
+    def metric(k, wh):  # compute metrics
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1 / r).min(2)[0]  # ratio metric
+        # x = wh_iou(wh, torch.tensor(k))  # iou metric
+        return x, x.max(1)[0]  # x, best_x
+
+    def anchor_fitness(k):  # mutation fitness
+        _, best = metric(torch.tensor(k, dtype=torch.float32), wh)
+        return (best * (best > thr).float()).mean()  # fitness
+
+    def print_results(k, verbose=True):
+        k = k[np.argsort(k.prod(1))]  # sort small to large
+        x, best = metric(k, wh0)
+        bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n  # best possible recall, anch > thr
+        s = f'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n' \
+            f'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' \
+            f'past_thr={x[x > thr].mean():.3f}-mean: '
+        for x in k:
+            s += '%i,%i, ' % (round(x[0]), round(x[1]))
+        if verbose:
+            LOGGER.info(s[:-2])
+        return k
+
+    if isinstance(dataset, str):  # *.yaml file
+        with open(dataset, errors='ignore') as f:
+            data_dict = yaml.safe_load(f)  # model dict
+
+        dataset = BaseDataset(data_dict['train'], augment=True, rect=True)
+
+    # Get label wh
+    shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)])  # wh
+
+    # Filter
+    i = (wh0 < 3.0).any(1).sum()
+    if i:
+        LOGGER.info(f'{PREFIX}WARNING ⚠️ Extremely small objects found: {i} of {len(wh0)} labels are <3 pixels in size')
+    wh = wh0[(wh0 >= 2.0).any(1)].astype(np.float32)  # filter > 2 pixels
+    # wh = wh * (npr.rand(wh.shape[0], 1) * 0.9 + 0.1)  # multiply by random scale 0-1
+
+    # Kmeans init
+    try:
+        LOGGER.info(f'{PREFIX}Running kmeans for {n} anchors on {len(wh)} points...')
+        assert n <= len(wh)  # apply overdetermined constraint
+        s = wh.std(0)  # sigmas for whitening
+        k = kmeans(wh / s, n, iter=30)[0] * s  # points
+        assert n == len(k)  # kmeans may return fewer points than requested if wh is insufficient or too similar
+    except Exception:
+        LOGGER.warning(f'{PREFIX}WARNING ⚠️ switching strategies from kmeans to random init')
+        k = np.sort(npr.rand(n * 2)).reshape(n, 2) * img_size  # random init
+    wh, wh0 = (torch.tensor(x, dtype=torch.float32) for x in (wh, wh0))
+    k = print_results(k, verbose=False)
+
+    # Plot
+    # k, d = [None] * 20, [None] * 20
+    # for i in tqdm(range(1, 21)):
+    #     k[i-1], d[i-1] = kmeans(wh / s, i)  # points, mean distance
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
+    # ax = ax.ravel()
+    # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7))  # plot wh
+    # ax[0].hist(wh[wh[:, 0]<100, 0],400)
+    # ax[1].hist(wh[wh[:, 1]<100, 1],400)
+    # fig.savefig('wh.png', dpi=200)
+
+    # Evolve
+    f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1  # fitness, generations, mutation prob, sigma
+    pbar = tqdm(range(gen), bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')  # progress bar
+    for _ in pbar:
+        v = np.ones(sh)
+        while (v == 1).all():  # mutate until a change occurs (prevent duplicates)
+            v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
+        kg = (k.copy() * v).clip(min=2.0)
+        fg = anchor_fitness(kg)
+        if fg > f:
+            f, k = fg, kg.copy()
+            pbar.desc = f'{PREFIX}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
+            if verbose:
+                print_results(k, verbose)
+
+    return print_results(k).astype(np.float32)

ultralytics/yolo/utils/checks.py

@@ -0,0 +1,136 @@
+import glob
+import os
+import platform
+import sys
+import urllib
+from pathlib import Path
+from subprocess import check_output
+
+import pkg_resources as pkg
+import torch
+
+from ultralytics.yolo.utils import AUTOINSTALL, CONFIG_DIR, FONT, LOGGER, ROOT, TryExcept
+
+from .loggers import colorstr, emojis
+
+
+def check_version(current="0.0.0", minimum="0.0.0", name="version ", pinned=False, hard=False, verbose=False):
+    # Check version vs. required version
+    current, minimum = (pkg.parse_version(x) for x in (current, minimum))
+    result = (current == minimum) if pinned else (current >= minimum)  # bool
+    s = f"WARNING ⚠️ {name}{minimum} is required by YOLOv5, but {name}{current} is currently installed"  # string
+    if hard:
+        assert result, emojis(s)  # assert min requirements met
+    if verbose and not result:
+        LOGGER.warning(s)
+    return result
+
+
+def check_font(font=FONT, progress=False):
+    # Download font to CONFIG_DIR if necessary
+    font = Path(font)
+    file = CONFIG_DIR / font.name
+    if not font.exists() and not file.exists():
+        url = f'https://ultralytics.com/assets/{font.name}'
+        LOGGER.info(f'Downloading {url} to {file}...')
+        torch.hub.download_url_to_file(url, str(file), progress=progress)
+
+
+def check_online():
+    # Check internet connectivity
+    import socket
+    try:
+        socket.create_connection(("1.1.1.1", 443), 5)  # check host accessibility
+        return True
+    except OSError:
+        return False
+
+
+def check_python(minimum='3.7.0'):
+    # Check current python version vs. required python version
+    check_version(platform.python_version(), minimum, name='Python ', hard=True)
+
+
+@TryExcept()
+def check_requirements(requirements=ROOT / 'requirements.txt', exclude=(), install=True, cmds=''):
+    # Check installed dependencies meet YOLOv5 requirements (pass *.txt file or list of packages or single package str)
+    prefix = colorstr('red', 'bold', 'requirements:')
+    check_python()  # check python version
+    if isinstance(requirements, Path):  # requirements.txt file
+        file = requirements.resolve()
+        assert file.exists(), f"{prefix} {file} not found, check failed."
+        with file.open() as f:
+            requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(f) if x.name not in exclude]
+    elif isinstance(requirements, str):
+        requirements = [requirements]
+
+    s = ''
+    n = 0
+    for r in requirements:
+        try:
+            pkg.require(r)
+        except (pkg.VersionConflict, pkg.DistributionNotFound):  # exception if requirements not met
+            s += f'"{r}" '
+            n += 1
+
+    if s and install and AUTOINSTALL:  # check environment variable
+        LOGGER.info(f"{prefix} YOLOv5 requirement{'s' * (n > 1)} {s}not found, attempting AutoUpdate...")
+        try:
+            assert check_online(), "AutoUpdate skipped (offline)"
+            LOGGER.info(check_output(f'pip install {s} {cmds}', shell=True).decode())
+            source = file if 'file' in locals() else requirements
+            s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \
+                f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n"
+            LOGGER.info(s)
+        except Exception as e:
+            LOGGER.warning(f'{prefix} ❌ {e}')
+
+
+def is_ascii(s=''):
+    # Is string composed of all ASCII (no UTF) characters? (note str().isascii() introduced in python 3.7)
+    s = str(s)  # convert list, tuple, None, etc. to str
+    return len(s.encode().decode('ascii', 'ignore')) == len(s)
+
+
+def check_suffix(file='yolov5s.pt', suffix=('.pt',), msg=''):
+    # Check file(s) for acceptable suffix
+    if file and suffix:
+        if isinstance(suffix, str):
+            suffix = [suffix]
+        for f in file if isinstance(file, (list, tuple)) else [file]:
+            s = Path(f).suffix.lower()  # file suffix
+            if len(s):
+                assert s in suffix, f"{msg}{f} acceptable suffix is {suffix}"
+
+
+def check_file(file, suffix=''):
+    # Search/download file (if necessary) and return path
+    check_suffix(file, suffix)  # optional
+    file = str(file)  # convert to str()
+    if Path(file).is_file() or not file:  # exists
+        return file
+    elif file.startswith(('http:/', 'https:/')):  # download
+        url = file  # warning: Pathlib turns :// -> :/
+        file = Path(urllib.parse.unquote(file).split('?')[0]).name  # '%2F' to '/', split https://url.com/file.txt?auth
+        if Path(file).is_file():
+            LOGGER.info(f'Found {url} locally at {file}')  # file already exists
+        else:
+            LOGGER.info(f'Downloading {url} to {file}...')
+            torch.hub.download_url_to_file(url, file)
+            assert Path(file).exists() and Path(file).stat().st_size > 0, f'File download failed: {url}'  # check
+        return file
+    elif file.startswith('clearml://'):  # ClearML Dataset ID
+        assert 'clearml' in sys.modules, "ClearML is not installed, so cannot use ClearML dataset. Try running 'pip install clearml'."
+        return file
+    else:  # search
+        files = []
+        for d in 'data', 'models', 'utils':  # search directories
+            files.extend(glob.glob(str(ROOT / d / '**' / file), recursive=True))  # find file
+        assert len(files), f'File not found: {file}'  # assert file was found
+        assert len(files) == 1, f"Multiple files match '{file}', specify exact path: {files}"  # assert unique
+        return files[0]  # return file
+
+
+def check_yaml(file, suffix=('.yaml', '.yml')):
+    # Search/download YAML file (if necessary) and return path, checking suffix
+    return check_file(file, suffix)

ultralytics/yolo/utils/downloads.py

@@ -0,0 +1,147 @@
+import logging
+import os
+import subprocess
+import urllib
+from itertools import repeat
+from multiprocessing.pool import ThreadPool
+from pathlib import Path
+from zipfile import ZipFile
+
+import requests
+import torch
+
+from ultralytics.yolo.utils import LOGGER
+
+
+def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''):
+    # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes
+    file = Path(file)
+    assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}"
+    try:  # url1
+        LOGGER.info(f'Downloading {url} to {file}...')
+        torch.hub.download_url_to_file(url, str(file), progress=LOGGER.level <= logging.INFO)
+        assert file.exists() and file.stat().st_size > min_bytes, assert_msg  # check
+    except Exception as e:  # url2
+        if file.exists():
+            file.unlink()  # remove partial downloads
+        LOGGER.info(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...')
+        os.system(f"curl -# -L '{url2 or url}' -o '{file}' --retry 3 -C -")  # curl download, retry and resume on fail
+    finally:
+        if not file.exists() or file.stat().st_size < min_bytes:  # check
+            if file.exists():
+                file.unlink()  # remove partial downloads
+            LOGGER.info(f"ERROR: {assert_msg}\n{error_msg}")
+        LOGGER.info('')
+
+
+def is_url(url, check=True):
+    # Check if string is URL and check if URL exists
+    try:
+        url = str(url)
+        result = urllib.parse.urlparse(url)
+        assert all([result.scheme, result.netloc])  # check if is url
+        return (urllib.request.urlopen(url).getcode() == 200) if check else True  # check if exists online
+    except (AssertionError, urllib.request.HTTPError):
+        return False
+
+
+def attempt_download(file, repo='ultralytics/yolov5', release='v6.2'):
+    # Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.2', etc.
+
+    def github_assets(repository, version='latest'):
+        # Return GitHub repo tag and assets (i.e. ['yolov5s.pt', 'yolov5m.pt', ...])
+        if version != 'latest':
+            version = f'tags/{version}'  # i.e. tags/v6.2
+        response = requests.get(f'https://api.github.com/repos/{repository}/releases/{version}').json()  # github api
+        return response['tag_name'], [x['name'] for x in response['assets']]  # tag, assets
+
+    file = Path(str(file).strip().replace("'", ''))
+    if not file.exists():
+        # URL specified
+        name = Path(urllib.parse.unquote(str(file))).name  # decode '%2F' to '/' etc.
+        if str(file).startswith(('http:/', 'https:/')):  # download
+            url = str(file).replace(':/', '://')  # Pathlib turns :// -> :/
+            file = name.split('?')[0]  # parse authentication https://url.com/file.txt?auth...
+            if Path(file).is_file():
+                LOGGER.info(f'Found {url} locally at {file}')  # file already exists
+            else:
+                safe_download(file=file, url=url, min_bytes=1E5)
+            return file
+
+        # GitHub assets
+        assets = [f'yolov5{size}{suffix}.pt' for size in 'nsmlx' for suffix in ('', '6', '-cls', '-seg')]  # default
+        try:
+            tag, assets = github_assets(repo, release)
+        except Exception:
+            try:
+                tag, assets = github_assets(repo)  # latest release
+            except Exception:
+                try:
+                    tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
+                except Exception:
+                    tag = release
+
+        file.parent.mkdir(parents=True, exist_ok=True)  # make parent dir (if required)
+        if name in assets:
+            url3 = 'https://drive.google.com/drive/folders/1EFQTEUeXWSFww0luse2jB9M1QNZQGwNl'  # backup gdrive mirror
+            safe_download(
+                file,
+                url=f'https://github.com/{repo}/releases/download/{tag}/{name}',
+                min_bytes=1E5,
+                error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/{tag} or {url3}')
+
+    return str(file)
+
+
+def download(url, dir=Path.cwd(), unzip=True, delete=True, curl=False, threads=1, retry=3):
+    # Multithreaded file download and unzip function, used in data.yaml for autodownload
+    def download_one(url, dir):
+        # Download 1 file
+        success = True
+        if Path(url).is_file():
+            f = Path(url)  # filename
+        else:  # does not exist
+            f = dir / Path(url).name
+            LOGGER.info(f'Downloading {url} to {f}...')
+            for i in range(retry + 1):
+                if curl:
+                    s = 'sS' if threads > 1 else ''  # silent
+                    r = os.system(
+                        f'curl -# -{s}L "{url}" -o "{f}" --retry 9 -C -')  # curl download with retry, continue
+                    success = r == 0
+                else:
+                    torch.hub.download_url_to_file(url, f, progress=threads == 1)  # torch download
+                    success = f.is_file()
+                if success:
+                    break
+                elif i < retry:
+                    LOGGER.warning(f'⚠️ Download failure, retrying {i + 1}/{retry} {url}...')
+                else:
+                    LOGGER.warning(f'❌ Failed to download {url}...')
+
+        if unzip and success and f.suffix in ('.zip', '.tar', '.gz'):
+            LOGGER.info(f'Unzipping {f}...')
+            if f.suffix == '.zip':
+                ZipFile(f).extractall(path=dir)  # unzip
+            elif f.suffix == '.tar':
+                os.system(f'tar xf {f} --directory {f.parent}')  # unzip
+            elif f.suffix == '.gz':
+                os.system(f'tar xfz {f} --directory {f.parent}')  # unzip
+            if delete:
+                f.unlink()  # remove zip
+
+    dir = Path(dir)
+    dir.mkdir(parents=True, exist_ok=True)  # make directory
+    if threads > 1:
+        pool = ThreadPool(threads)
+        pool.imap(lambda x: download_one(*x), zip(url, repeat(dir)))  # multithreaded
+        pool.close()
+        pool.join()
+    else:
+        for u in [url] if isinstance(url, (str, Path)) else url:
+            download_one(u, dir)
+
+
+def get_model(model: str):
+    # check for local weights
+    pass

ultralytics/yolo/utils/files.py

@@ -0,0 +1,74 @@
+import contextlib
+import os
+import platform
+from pathlib import Path
+
+import yaml
+
+
+class WorkingDirectory(contextlib.ContextDecorator):
+    # Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager
+    def __init__(self, new_dir):
+        self.dir = new_dir  # new dir
+        self.cwd = Path.cwd().resolve()  # current dir
+
+    def __enter__(self):
+        os.chdir(self.dir)
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        os.chdir(self.cwd)
+
+
+def is_writeable(dir, test=False):
+    # Return True if directory has write permissions, test opening a file with write permissions if test=True
+    if not test:
+        return os.access(dir, os.W_OK)  # possible issues on Windows
+    file = Path(dir) / 'tmp.txt'
+    try:
+        with open(file, 'w'):  # open file with write permissions
+            pass
+        file.unlink()  # remove file
+        return True
+    except OSError:
+        return False
+
+
+def user_config_dir(dir='Ultralytics', env_var='YOLOV5_CONFIG_DIR'):
+    # Return path of user configuration directory. Prefer environment variable if exists. Make dir if required.
+    env = os.getenv(env_var)
+    if env:
+        path = Path(env)  # use environment variable
+    else:
+        cfg = {'Windows': 'AppData/Roaming', 'Linux': '.config', 'Darwin': 'Library/Application Support'}  # 3 OS dirs
+        path = Path.home() / cfg.get(platform.system(), '')  # OS-specific config dir
+        path = (path if is_writeable(path) else Path('/tmp')) / dir  # GCP and AWS lambda fix, only /tmp is writeable
+    path.mkdir(exist_ok=True)  # make if required
+    return path
+
+
+def increment_path(path, exist_ok=False, sep='', mkdir=False):
+    """
+    Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc.
+    # TODO: docs
+    """
+    path = Path(path)  # os-agnostic
+    if path.exists() and not exist_ok:
+        path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '')
+
+        # Method 1
+        for n in range(2, 9999):
+            p = f'{path}{sep}{n}{suffix}'  # increment path
+            if not os.path.exists(p):  #
+                break
+        path = Path(p)
+
+    if mkdir:
+        path.mkdir(parents=True, exist_ok=True)  # make directory
+
+    return path
+
+
+def save_yaml(file='data.yaml', data=None):
+    # Single-line safe yaml saving
+    with open(file, 'w') as f:
+        yaml.safe_dump({k: str(v) if isinstance(v, Path) else v for k, v in data.items()}, f, sort_keys=False)

ultralytics/yolo/utils/general.py

@@ -1,372 +0,0 @@
-# TODO: Follow google docs format for all functions. Easier for automatic doc parser
-
-import contextlib
-import logging
-import os
-import platform
-import subprocess
-import time
-import urllib
-from itertools import repeat
-from multiprocessing.pool import ThreadPool
-from pathlib import Path
-from zipfile import ZipFile
-
-import numpy as np
-import pkg_resources as pkg
-import requests
-import torch
-import yaml
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[2]  # YOLOv5 root directory
-RANK = int(os.getenv('RANK', -1))
-
-# Settings
-DATASETS_DIR = ROOT.parent / 'datasets'  # YOLOv5 datasets directory
-NUM_THREADS = min(8, max(1, os.cpu_count() - 1))  # number of YOLOv5 multiprocessing threads
-AUTOINSTALL = str(os.getenv('YOLOv5_AUTOINSTALL', True)).lower() == 'true'  # global auto-install mode
-VERBOSE = str(os.getenv('YOLOv5_VERBOSE', True)).lower() == 'true'  # global verbose mode
-FONT = 'Arial.ttf'  # https://ultralytics.com/assets/Arial.ttf
-
-
-def is_colab():
-    # Is environment a Google Colab instance?
-    return "COLAB_GPU" in os.environ
-
-
-def is_kaggle():
-    # Is environment a Kaggle Notebook?
-    return os.environ.get("PWD") == "/kaggle/working" and os.environ.get("KAGGLE_URL_BASE") == "https://www.kaggle.com"
-
-
-def emojis(str=""):
-    # Return platform-dependent emoji-safe version of string
-    return str.encode().decode("ascii", "ignore") if platform.system() == "Windows" else str
-
-
-def set_logging(name=None, verbose=VERBOSE):
-    # Sets level and returns logger
-    if is_kaggle() or is_colab():
-        for h in logging.root.handlers:
-            logging.root.removeHandler(h)  # remove all handlers associated with the root logger object
-    rank = int(os.getenv("RANK", -1))  # rank in world for Multi-GPU trainings
-    level = logging.INFO if verbose and rank in {-1, 0} else logging.ERROR
-    log = logging.getLogger(name)
-    log.setLevel(level)
-    handler = logging.StreamHandler()
-    handler.setFormatter(logging.Formatter("%(message)s"))
-    handler.setLevel(level)
-    log.addHandler(handler)
-
-
-set_logging()  # run before defining LOGGER
-LOGGER = logging.getLogger("yolov5")  # define globally (used in train.py, val.py, detect.py, etc.)
-if platform.system() == "Windows":
-    for fn in LOGGER.info, LOGGER.warning:
-        setattr(LOGGER, fn.__name__, lambda x: fn(emojis(x)))  # emoji safe logging
-
-
-def segment2box(segment, width=640, height=640):
-    # Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
-    x, y = segment.T  # segment xy
-    inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
-    x, y, = (
-        x[inside],
-        y[inside],
-    )
-    return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros(4)  # xyxy
-
-
-def check_version(current="0.0.0", minimum="0.0.0", name="version ", pinned=False, hard=False, verbose=False):
-    # Check version vs. required version
-    current, minimum = (pkg.parse_version(x) for x in (current, minimum))
-    result = (current == minimum) if pinned else (current >= minimum)  # bool
-    s = f"WARNING ⚠️ {name}{minimum} is required by YOLOv5, but {name}{current} is currently installed"  # string
-    if hard:
-        assert result, emojis(s)  # assert min requirements met
-    if verbose and not result:
-        LOGGER.warning(s)
-    return result
-
-
-def colorstr(*input):
-    # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e.  colorstr('blue', 'hello world')
-    *args, string = input if len(input) > 1 else ("blue", "bold", input[0])  # color arguments, string
-    colors = {
-        "black": "\033[30m",  # basic colors
-        "red": "\033[31m",
-        "green": "\033[32m",
-        "yellow": "\033[33m",
-        "blue": "\033[34m",
-        "magenta": "\033[35m",
-        "cyan": "\033[36m",
-        "white": "\033[37m",
-        "bright_black": "\033[90m",  # bright colors
-        "bright_red": "\033[91m",
-        "bright_green": "\033[92m",
-        "bright_yellow": "\033[93m",
-        "bright_blue": "\033[94m",
-        "bright_magenta": "\033[95m",
-        "bright_cyan": "\033[96m",
-        "bright_white": "\033[97m",
-        "end": "\033[0m",  # misc
-        "bold": "\033[1m",
-        "underline": "\033[4m",}
-    return "".join(colors[x] for x in args) + f"{string}" + colors["end"]
-
-
-def xyxy2xywh(x):
-    # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
-    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
-    y[:, 0] = (x[:, 0] + x[:, 2]) / 2  # x center
-    y[:, 1] = (x[:, 1] + x[:, 3]) / 2  # y center
-    y[:, 2] = x[:, 2] - x[:, 0]  # width
-    y[:, 3] = x[:, 3] - x[:, 1]  # height
-    return y
-
-
-def xywh2xyxy(x):
-    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
-    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
-    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
-    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
-    y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
-    y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
-    return y
-
-
-def xywh2ltwh(x):
-    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, w, h] where xy1=top-left
-    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
-    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
-    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
-    return y
-
-
-def xyxy2ltwh(x):
-    # Convert nx4 boxes from [x1, y1, x2, y2] to [x1, y1, w, h] where xy1=top-left, xy2=bottom-right
-    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
-    y[:, 2] = x[:, 2] - x[:, 0]  # width
-    y[:, 3] = x[:, 3] - x[:, 1]  # height
-    return y
-
-
-def ltwh2xywh(x):
-    # Convert nx4 boxes from [x1, y1, w, h] to [x, y, w, h] where xy1=top-left, xy=center
-    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
-    y[:, 0] = x[:, 0] + x[:, 2] / 2  # center x
-    y[:, 1] = x[:, 1] + x[:, 3] / 2  # center y
-    return y
-
-
-def ltwh2xyxy(x):
-    # Convert nx4 boxes from [x1, y1, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
-    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
-    y[:, 2] = x[:, 2] + x[:, 0]  # width
-    y[:, 3] = x[:, 3] + x[:, 1]  # height
-    return y
-
-
-def segments2boxes(segments):
-    # Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
-    boxes = []
-    for s in segments:
-        x, y = s.T  # segment xy
-        boxes.append([x.min(), y.min(), x.max(), y.max()])  # cls, xyxy
-    return xyxy2xywh(np.array(boxes))  # cls, xywh
-
-
-def resample_segments(segments, n=1000):
-    # Up-sample an (n,2) segment
-    for i, s in enumerate(segments):
-        s = np.concatenate((s, s[0:1, :]), axis=0)
-        x = np.linspace(0, len(s) - 1, n)
-        xp = np.arange(len(s))
-        segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T  # segment xy
-    return segments
-
-
-def increment_path(path, exist_ok=False, sep='', mkdir=False):
-    """
-    Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc.
-    # TODO: docs
-    """
-    path = Path(path)  # os-agnostic
-    if path.exists() and not exist_ok:
-        path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '')
-
-        # Method 1
-        for n in range(2, 9999):
-            p = f'{path}{sep}{n}{suffix}'  # increment path
-            if not os.path.exists(p):  #
-                break
-        path = Path(p)
-
-    if mkdir:
-        path.mkdir(parents=True, exist_ok=True)  # make directory
-
-    return path
-
-
-def save_yaml(file='data.yaml', data=None):
-    # Single-line safe yaml saving
-    with open(file, 'w') as f:
-        yaml.safe_dump({k: str(v) if isinstance(v, Path) else v for k, v in data.items()}, f, sort_keys=False)
-
-
-def download(url, dir=Path.cwd(), unzip=True, delete=True, curl=False, threads=1, retry=3):
-    # Multithreaded file download and unzip function, used in data.yaml for autodownload
-    def download_one(url, dir):
-        # Download 1 file
-        success = True
-        if Path(url).is_file():
-            f = Path(url)  # filename
-        else:  # does not exist
-            f = dir / Path(url).name
-            LOGGER.info(f'Downloading {url} to {f}...')
-            for i in range(retry + 1):
-                if curl:
-                    s = 'sS' if threads > 1 else ''  # silent
-                    r = os.system(
-                        f'curl -# -{s}L "{url}" -o "{f}" --retry 9 -C -')  # curl download with retry, continue
-                    success = r == 0
-                else:
-                    torch.hub.download_url_to_file(url, f, progress=threads == 1)  # torch download
-                    success = f.is_file()
-                if success:
-                    break
-                elif i < retry:
-                    LOGGER.warning(f'⚠️ Download failure, retrying {i + 1}/{retry} {url}...')
-                else:
-                    LOGGER.warning(f'❌ Failed to download {url}...')
-
-        if unzip and success and f.suffix in ('.zip', '.tar', '.gz'):
-            LOGGER.info(f'Unzipping {f}...')
-            if f.suffix == '.zip':
-                ZipFile(f).extractall(path=dir)  # unzip
-            elif f.suffix == '.tar':
-                os.system(f'tar xf {f} --directory {f.parent}')  # unzip
-            elif f.suffix == '.gz':
-                os.system(f'tar xfz {f} --directory {f.parent}')  # unzip
-            if delete:
-                f.unlink()  # remove zip
-
-    dir = Path(dir)
-    dir.mkdir(parents=True, exist_ok=True)  # make directory
-    if threads > 1:
-        pool = ThreadPool(threads)
-        pool.imap(lambda x: download_one(*x), zip(url, repeat(dir)))  # multithreaded
-        pool.close()
-        pool.join()
-    else:
-        for u in [url] if isinstance(url, (str, Path)) else url:
-            download_one(u, dir)
-
-
-class WorkingDirectory(contextlib.ContextDecorator):
-    # Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager
-    def __init__(self, new_dir):
-        self.dir = new_dir  # new dir
-        self.cwd = Path.cwd().resolve()  # current dir
-
-    def __enter__(self):
-        os.chdir(self.dir)
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        os.chdir(self.cwd)
-
-
-def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''):
-    # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes
-
-    file = Path(file)
-    assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}"
-    try:  # url1
-        LOGGER.info(f'Downloading {url} to {file}...')
-        torch.hub.download_url_to_file(url, str(file), progress=LOGGER.level <= logging.INFO)
-        assert file.exists() and file.stat().st_size > min_bytes, assert_msg  # check
-    except Exception as e:  # url2
-        if file.exists():
-            file.unlink()  # remove partial downloads
-        LOGGER.info(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...')
-        os.system(f"curl -# -L '{url2 or url}' -o '{file}' --retry 3 -C -")  # curl download, retry and resume on fail
-    finally:
-        if not file.exists() or file.stat().st_size < min_bytes:  # check
-            if file.exists():
-                file.unlink()  # remove partial downloads
-            LOGGER.info(f"ERROR: {assert_msg}\n{error_msg}")
-        LOGGER.info('')
-
-
-def attempt_download(file, repo='ultralytics/yolov5', release='v6.2'):
-    # Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.2', etc.
-
-    def github_assets(repository, version='latest'):
-        # Return GitHub repo tag and assets (i.e. ['yolov5s.pt', 'yolov5m.pt', ...])
-        if version != 'latest':
-            version = f'tags/{version}'  # i.e. tags/v6.2
-        response = requests.get(f'https://api.github.com/repos/{repository}/releases/{version}').json()  # github api
-        return response['tag_name'], [x['name'] for x in response['assets']]  # tag, assets
-
-    file = Path(str(file).strip().replace("'", ''))
-    if not file.exists():
-        # URL specified
-        name = Path(urllib.parse.unquote(str(file))).name  # decode '%2F' to '/' etc.
-        if str(file).startswith(('http:/', 'https:/')):  # download
-            url = str(file).replace(':/', '://')  # Pathlib turns :// -> :/
-            file = name.split('?')[0]  # parse authentication https://url.com/file.txt?auth...
-            if Path(file).is_file():
-                LOGGER.info(f'Found {url} locally at {file}')  # file already exists
-            else:
-                safe_download(file=file, url=url, min_bytes=1E5)
-            return file
-
-        # GitHub assets
-        assets = [f'yolov5{size}{suffix}.pt' for size in 'nsmlx' for suffix in ('', '6', '-cls', '-seg')]  # default
-        try:
-            tag, assets = github_assets(repo, release)
-        except Exception:
-            try:
-                tag, assets = github_assets(repo)  # latest release
-            except Exception:
-                try:
-                    tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
-                except Exception:
-                    tag = release
-
-        file.parent.mkdir(parents=True, exist_ok=True)  # make parent dir (if required)
-        if name in assets:
-            url3 = 'https://drive.google.com/drive/folders/1EFQTEUeXWSFww0luse2jB9M1QNZQGwNl'  # backup gdrive mirror
-            safe_download(
-                file,
-                url=f'https://github.com/{repo}/releases/download/{tag}/{name}',
-                min_bytes=1E5,
-                error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/{tag} or {url3}')
-
-    return str(file)
-
-
-def get_model(model: str):
-    # check for local weights
-    pass
-
-
-class Profile(contextlib.ContextDecorator):
-    # YOLOv5 Profile class. Usage: @Profile() decorator or 'with Profile():' context manager
-    def __init__(self, t=0.0):
-        self.t = t
-        self.cuda = torch.cuda.is_available()
-
-    def __enter__(self):
-        self.start = self.time()
-        return self
-
-    def __exit__(self, type, value, traceback):
-        self.dt = self.time() - self.start  # delta-time
-        self.t += self.dt  # accumulate dt
-
-    def time(self):
-        if self.cuda:
-            torch.cuda.synchronize()
-        return time.time()

ultralytics/yolo/utils/instance.py

@@ -5,7 +5,7 @@ from typing import List
 
 import numpy as np
 
-from .general import ltwh2xywh, ltwh2xyxy, resample_segments, xywh2ltwh, xywh2xyxy, xyxy2ltwh, xyxy2xywh
+from .ops import ltwh2xywh, ltwh2xyxy, resample_segments, xywh2ltwh, xywh2xyxy, xyxy2ltwh, xyxy2xywh
 
 
 # From PyTorch internals

ultralytics/yolo/utils/loggers/__init__.py

@@ -1,3 +1,57 @@
+import logging
+import os
+import platform
+
 from .base import default_callbacks
 
-__all__ = ["default_callbacks"]
+VERBOSE = str(os.getenv('YOLOv5_VERBOSE', True)).lower() == 'true'  # global verbose mode
+
+
+# console logging utils
+def emojis(str=''):
+    # Return platform-dependent emoji-safe version of string
+    return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str
+
+
+def colorstr(*input):
+    # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e.  colorstr('blue', 'hello world')
+    *args, string = input if len(input) > 1 else ("blue", "bold", input[0])  # color arguments, string
+    colors = {
+        "black": "\033[30m",  # basic colors
+        "red": "\033[31m",
+        "green": "\033[32m",
+        "yellow": "\033[33m",
+        "blue": "\033[34m",
+        "magenta": "\033[35m",
+        "cyan": "\033[36m",
+        "white": "\033[37m",
+        "bright_black": "\033[90m",  # bright colors
+        "bright_red": "\033[91m",
+        "bright_green": "\033[92m",
+        "bright_yellow": "\033[93m",
+        "bright_blue": "\033[94m",
+        "bright_magenta": "\033[95m",
+        "bright_cyan": "\033[96m",
+        "bright_white": "\033[97m",
+        "end": "\033[0m",  # misc
+        "bold": "\033[1m",
+        "underline": "\033[4m",}
+    return "".join(colors[x] for x in args) + f"{string}" + colors["end"]
+
+
+def set_logging(name=None, verbose=VERBOSE):
+    # Sets level and returns logger
+    is_kaggle = os.environ.get("PWD") == "/kaggle/working" and os.environ.get(
+        "KAGGLE_URL_BASE") == "https://www.kaggle.com"
+    is_colab = "COLAB_GPU" in os.environ
+    if is_colab or is_kaggle:
+        for h in logging.root.handlers:
+            logging.root.removeHandler(h)  # remove all handlers associated with the root logger object
+    rank = int(os.getenv("RANK", -1))  # rank in world for Multi-GPU trainings
+    level = logging.INFO if verbose and rank in {-1, 0} else logging.ERROR
+    log = logging.getLogger(name)
+    log.setLevel(level)
+    handler = logging.StreamHandler()
+    handler.setFormatter(logging.Formatter("%(message)s"))
+    handler.setLevel(level)
+    log.addHandler(handler)

ultralytics/yolo/utils/metrics.py

@@ -4,6 +4,12 @@ Model validation metrics
 """
 
 import numpy as np
+import torch
+
+
+def box_area(box):
+    # box = xyxy(4,n)
+    return (box[2] - box[0]) * (box[3] - box[1])
 
 
 def bbox_ioa(box1, box2, eps=1e-7):
@@ -26,3 +32,24 @@ def bbox_ioa(box1, box2, eps=1e-7):
 
     # Intersection over box2 area
     return inter_area / box2_area
+
+
+def box_iou(box1, box2, eps=1e-7):
+    # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
+    """
+    Return intersection-over-union (Jaccard index) of boxes.
+    Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+    Arguments:
+        box1 (Tensor[N, 4])
+        box2 (Tensor[M, 4])
+    Returns:
+        iou (Tensor[N, M]): the NxM matrix containing the pairwise
+            IoU values for every element in boxes1 and boxes2
+    """
+
+    # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
+    (a1, a2), (b1, b2) = box1[:, None].chunk(2, 2), box2.chunk(2, 1)
+    inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp(0).prod(2)
+
+    # IoU = inter / (area1 + area2 - inter)
+    return inter / (box_area(box1.T)[:, None] + box_area(box2.T) - inter + eps)

ultralytics/yolo/utils/modeling/__init__.py

@@ -0,0 +1,113 @@
+import contextlib
+
+import yaml
+
+from ultralytics.yolo.utils.downloads import attempt_download
+
+from .modules import *
+
+
+def attempt_load_weights(weights, device=None, inplace=True, fuse=True):
+    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+
+    model = Ensemble()
+    for w in weights if isinstance(weights, list) else [weights]:
+        ckpt = torch.load(attempt_download(w), map_location='cpu')  # load
+        ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float()  # FP32 model
+
+        # Model compatibility updates
+        if not hasattr(ckpt, 'stride'):
+            ckpt.stride = torch.tensor([32.])
+        if hasattr(ckpt, 'names') and isinstance(ckpt.names, (list, tuple)):
+            ckpt.names = dict(enumerate(ckpt.names))  # convert to dict
+
+        model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval())  # model in eval mode
+
+    # Module compatibility updates
+    for m in model.modules():
+        t = type(m)
+        if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model):
+            m.inplace = inplace  # torch 1.7.0 compatibility
+            if t is Detect and not isinstance(m.anchor_grid, list):
+                delattr(m, 'anchor_grid')
+                setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
+        elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'):
+            m.recompute_scale_factor = None  # torch 1.11.0 compatibility
+
+    # Return model
+    if len(model) == 1:
+        return model[-1]
+
+    # Return detection ensemble
+    print(f'Ensemble created with {weights}\n')
+    for k in 'names', 'nc', 'yaml':
+        setattr(model, k, getattr(model[0], k))
+    model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride  # max stride
+    assert all(model[0].nc == m.nc for m in model), f'Models have different class counts: {[m.nc for m in model]}'
+    return model
+
+
+def parse_model(d, ch):  # model_dict, input_channels(3)
+    # Parse a YOLOv5 model.yaml dictionary
+    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
+    anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
+    if act:
+        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
+        LOGGER.info(f"{colorstr('activation:')} {act}")  # print
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            with contextlib.suppress(NameError):
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+
+        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in {
+                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus, CrossConv, BottleneckCSP, C3,
+                C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
+            c1, c2 = ch[f], args[0]
+            if c2 != no:  # if not output
+                c2 = make_divisible(c2 * gw, 8)
+
+            args = [c1, c2, *args[1:]]
+            if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x}:
+                args.insert(2, n)  # number of repeats
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum(ch[x] for x in f)
+        # TODO: channel, gw, gd
+        elif m in {Detect, Segment}:
+            args.append([ch[x] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+            if m is Segment:
+                args[3] = make_divisible(args[3] * gw, 8)
+        elif m is Contract:
+            c2 = ch[f] * args[0] ** 2
+        elif m is Expand:
+            c2 = ch[f] // args[0] ** 2
+        else:
+            c2 = ch[f]
+
+        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum(x.numel() for x in m_.parameters())  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}')  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        if i == 0:
+            ch = []
+        ch.append(c2)
+    return nn.Sequential(*layers), sorted(save)
+
+
+def yaml_load(file='data.yaml'):
+    # Single-line safe yaml loading
+    with open(file, errors='ignore') as f:
+        return yaml.safe_load(f)

ultralytics/yolo/utils/modeling/autobackend.py

@@ -0,0 +1,324 @@
+import json
+import platform
+from collections import OrderedDict, namedtuple
+from pathlib import Path
+from urllib.parse import urlparse
+
+import cv2
+import numpy as np
+import torch
+import torch.nn as nn
+from PIL import Image
+
+from ultralytics.yolo.utils import LOGGER, ROOT
+from ultralytics.yolo.utils.checks import check_requirements, check_suffix, check_version
+from ultralytics.yolo.utils.downloads import attempt_download, is_url
+from ultralytics.yolo.utils.ops import xywh2xyxy
+
+
+class AutoBackend(nn.Module):
+    # YOLOv5 MultiBackend class for python inference on various backends
+    def __init__(self, weights='yolov5s.pt', device=torch.device('cpu'), dnn=False, data=None, fp16=False, fuse=True):
+        # Usage:
+        #   PyTorch:              weights = *.pt
+        #   TorchScript:                    *.torchscript
+        #   ONNX Runtime:                   *.onnx
+        #   ONNX OpenCV DNN:                *.onnx --dnn
+        #   OpenVINO:                       *.xml
+        #   CoreML:                         *.mlmodel
+        #   TensorRT:                       *.engine
+        #   TensorFlow SavedModel:          *_saved_model
+        #   TensorFlow GraphDef:            *.pb
+        #   TensorFlow Lite:                *.tflite
+        #   TensorFlow Edge TPU:            *_edgetpu.tflite
+        #   PaddlePaddle:                   *_paddle_model
+        from ultralytics.yolo.utils.modeling import attempt_load_weights, yaml_load
+
+        super().__init__()
+        w = str(weights[0] if isinstance(weights, list) else weights)
+        pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, triton = self._model_type(w)
+        fp16 &= pt or jit or onnx or engine  # FP16
+        nhwc = coreml or saved_model or pb or tflite or edgetpu  # BHWC formats (vs torch BCWH)
+        stride = 32  # default stride
+        cuda = torch.cuda.is_available() and device.type != 'cpu'  # use CUDA
+        if not (pt or triton):
+            w = attempt_download(w)  # download if not local
+
+        if pt:  # PyTorch
+            model = attempt_load_weights(weights if isinstance(weights, list) else w,
+                                         device=device,
+                                         inplace=True,
+                                         fuse=fuse)
+            stride = max(int(model.stride.max()), 32)  # model stride
+            names = model.module.names if hasattr(model, 'module') else model.names  # get class names
+            model.half() if fp16 else model.float()
+            self.model = model  # explicitly assign for to(), cpu(), cuda(), half()
+        elif jit:  # TorchScript
+            LOGGER.info(f'Loading {w} for TorchScript inference...')
+            extra_files = {'config.txt': ''}  # model metadata
+            model = torch.jit.load(w, _extra_files=extra_files, map_location=device)
+            model.half() if fp16 else model.float()
+            if extra_files['config.txt']:  # load metadata dict
+                d = json.loads(extra_files['config.txt'],
+                               object_hook=lambda d: {int(k) if k.isdigit() else k: v
+                                                      for k, v in d.items()})
+                stride, names = int(d['stride']), d['names']
+        elif dnn:  # ONNX OpenCV DNN
+            LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
+            check_requirements('opencv-python>=4.5.4')
+            net = cv2.dnn.readNetFromONNX(w)
+        elif onnx:  # ONNX Runtime
+            LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
+            check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
+            import onnxruntime
+            providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
+            session = onnxruntime.InferenceSession(w, providers=providers)
+            output_names = [x.name for x in session.get_outputs()]
+            meta = session.get_modelmeta().custom_metadata_map  # metadata
+            if 'stride' in meta:
+                stride, names = int(meta['stride']), eval(meta['names'])
+        elif xml:  # OpenVINO
+            LOGGER.info(f'Loading {w} for OpenVINO inference...')
+            check_requirements('openvino')  # requires openvino-dev: https://pypi.org/project/openvino-dev/
+            from openvino.runtime import Core, Layout, get_batch
+            ie = Core()
+            if not Path(w).is_file():  # if not *.xml
+                w = next(Path(w).glob('*.xml'))  # get *.xml file from *_openvino_model dir
+            network = ie.read_model(model=w, weights=Path(w).with_suffix('.bin'))
+            if network.get_parameters()[0].get_layout().empty:
+                network.get_parameters()[0].set_layout(Layout("NCHW"))
+            batch_dim = get_batch(network)
+            if batch_dim.is_static:
+                batch_size = batch_dim.get_length()
+            executable_network = ie.compile_model(network, device_name="CPU")  # device_name="MYRIAD" for Intel NCS2
+            stride, names = self._load_metadata(Path(w).with_suffix('.yaml'))  # load metadata
+        elif engine:  # TensorRT
+            LOGGER.info(f'Loading {w} for TensorRT inference...')
+            import tensorrt as trt  # https://developer.nvidia.com/nvidia-tensorrt-download
+            check_version(trt.__version__, '7.0.0', hard=True)  # require tensorrt>=7.0.0
+            if device.type == 'cpu':
+                device = torch.device('cuda:0')
+            Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr'))
+            logger = trt.Logger(trt.Logger.INFO)
+            with open(w, 'rb') as f, trt.Runtime(logger) as runtime:
+                model = runtime.deserialize_cuda_engine(f.read())
+            context = model.create_execution_context()
+            bindings = OrderedDict()
+            output_names = []
+            fp16 = False  # default updated below
+            dynamic = False
+            for i in range(model.num_bindings):
+                name = model.get_binding_name(i)
+                dtype = trt.nptype(model.get_binding_dtype(i))
+                if model.binding_is_input(i):
+                    if -1 in tuple(model.get_binding_shape(i)):  # dynamic
+                        dynamic = True
+                        context.set_binding_shape(i, tuple(model.get_profile_shape(0, i)[2]))
+                    if dtype == np.float16:
+                        fp16 = True
+                else:  # output
+                    output_names.append(name)
+                shape = tuple(context.get_binding_shape(i))
+                im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device)
+                bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr()))
+            binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items())
+            batch_size = bindings['images'].shape[0]  # if dynamic, this is instead max batch size
+        elif coreml:  # CoreML
+            LOGGER.info(f'Loading {w} for CoreML inference...')
+            import coremltools as ct
+            model = ct.models.MLModel(w)
+        elif saved_model:  # TF SavedModel
+            LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
+            import tensorflow as tf
+            keras = False  # assume TF1 saved_model
+            model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w)
+        elif pb:  # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
+            LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
+            import tensorflow as tf
+
+            def wrap_frozen_graph(gd, inputs, outputs):
+                x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), [])  # wrapped
+                ge = x.graph.as_graph_element
+                return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs))
+
+            def gd_outputs(gd):
+                name_list, input_list = [], []
+                for node in gd.node:  # tensorflow.core.framework.node_def_pb2.NodeDef
+                    name_list.append(node.name)
+                    input_list.extend(node.input)
+                return sorted(f'{x}:0' for x in list(set(name_list) - set(input_list)) if not x.startswith('NoOp'))
+
+            gd = tf.Graph().as_graph_def()  # TF GraphDef
+            with open(w, 'rb') as f:
+                gd.ParseFromString(f.read())
+            frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs=gd_outputs(gd))
+        elif tflite or edgetpu:  # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
+            try:  # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
+                from tflite_runtime.interpreter import Interpreter, load_delegate
+            except ImportError:
+                import tensorflow as tf
+                Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate,
+            if edgetpu:  # TF Edge TPU https://coral.ai/software/#edgetpu-runtime
+                LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...')
+                delegate = {
+                    'Linux': 'libedgetpu.so.1',
+                    'Darwin': 'libedgetpu.1.dylib',
+                    'Windows': 'edgetpu.dll'}[platform.system()]
+                interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
+            else:  # TFLite
+                LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
+                interpreter = Interpreter(model_path=w)  # load TFLite model
+            interpreter.allocate_tensors()  # allocate
+            input_details = interpreter.get_input_details()  # inputs
+            output_details = interpreter.get_output_details()  # outputs
+        elif tfjs:  # TF.js
+            raise NotImplementedError('ERROR: YOLOv5 TF.js inference is not supported')
+        elif paddle:  # PaddlePaddle
+            LOGGER.info(f'Loading {w} for PaddlePaddle inference...')
+            check_requirements('paddlepaddle-gpu' if cuda else 'paddlepaddle')
+            import paddle.inference as pdi
+            if not Path(w).is_file():  # if not *.pdmodel
+                w = next(Path(w).rglob('*.pdmodel'))  # get *.xml file from *_openvino_model dir
+            weights = Path(w).with_suffix('.pdiparams')
+            config = pdi.Config(str(w), str(weights))
+            if cuda:
+                config.enable_use_gpu(memory_pool_init_size_mb=2048, device_id=0)
+            predictor = pdi.create_predictor(config)
+            input_handle = predictor.get_input_handle(predictor.get_input_names()[0])
+            output_names = predictor.get_output_names()
+        elif triton:  # NVIDIA Triton Inference Server
+            LOGGER.info('Triton Inference Server not supported...')
+            '''
+            TODO:
+            check_requirements('tritonclient[all]')
+            from utils.triton import TritonRemoteModel
+            model = TritonRemoteModel(url=w)
+            nhwc = model.runtime.startswith("tensorflow")
+            '''
+        else:
+            raise NotImplementedError(f'ERROR: {w} is not a supported format')
+
+        # class names
+        if 'names' not in locals():
+            names = yaml_load(data)['names'] if data else {i: f'class{i}' for i in range(999)}
+        if names[0] == 'n01440764' and len(names) == 1000:  # ImageNet
+            names = yaml_load(ROOT / 'data/ImageNet.yaml')['names']  # human-readable names
+
+        self.__dict__.update(locals())  # assign all variables to self
+
+    def forward(self, im, augment=False, visualize=False):
+        # YOLOv5 MultiBackend inference
+        b, ch, h, w = im.shape  # batch, channel, height, width
+        if self.fp16 and im.dtype != torch.float16:
+            im = im.half()  # to FP16
+        if self.nhwc:
+            im = im.permute(0, 2, 3, 1)  # torch BCHW to numpy BHWC shape(1,320,192,3)
+
+        if self.pt:  # PyTorch
+            y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im)
+        elif self.jit:  # TorchScript
+            y = self.model(im)
+        elif self.dnn:  # ONNX OpenCV DNN
+            im = im.cpu().numpy()  # torch to numpy
+            self.net.setInput(im)
+            y = self.net.forward()
+        elif self.onnx:  # ONNX Runtime
+            im = im.cpu().numpy()  # torch to numpy
+            y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im})
+        elif self.xml:  # OpenVINO
+            im = im.cpu().numpy()  # FP32
+            y = list(self.executable_network([im]).values())
+        elif self.engine:  # TensorRT
+            if self.dynamic and im.shape != self.bindings['images'].shape:
+                i = self.model.get_binding_index('images')
+                self.context.set_binding_shape(i, im.shape)  # reshape if dynamic
+                self.bindings['images'] = self.bindings['images']._replace(shape=im.shape)
+                for name in self.output_names:
+                    i = self.model.get_binding_index(name)
+                    self.bindings[name].data.resize_(tuple(self.context.get_binding_shape(i)))
+            s = self.bindings['images'].shape
+            assert im.shape == s, f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}"
+            self.binding_addrs['images'] = int(im.data_ptr())
+            self.context.execute_v2(list(self.binding_addrs.values()))
+            y = [self.bindings[x].data for x in sorted(self.output_names)]
+        elif self.coreml:  # CoreML
+            im = im.cpu().numpy()
+            im = Image.fromarray((im[0] * 255).astype('uint8'))
+            # im = im.resize((192, 320), Image.ANTIALIAS)
+            y = self.model.predict({'image': im})  # coordinates are xywh normalized
+            if 'confidence' in y:
+                box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]])  # xyxy pixels
+                conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float)
+                y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1)
+            else:
+                y = list(reversed(y.values()))  # reversed for segmentation models (pred, proto)
+        elif self.paddle:  # PaddlePaddle
+            im = im.cpu().numpy().astype(np.float32)
+            self.input_handle.copy_from_cpu(im)
+            self.predictor.run()
+            y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names]
+        elif self.triton:  # NVIDIA Triton Inference Server
+            y = self.model(im)
+        else:  # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
+            im = im.cpu().numpy()
+            if self.saved_model:  # SavedModel
+                y = self.model(im, training=False) if self.keras else self.model(im)
+            elif self.pb:  # GraphDef
+                y = self.frozen_func(x=self.tf.constant(im))
+            else:  # Lite or Edge TPU
+                input = self.input_details[0]
+                int8 = input['dtype'] == np.uint8  # is TFLite quantized uint8 model
+                if int8:
+                    scale, zero_point = input['quantization']
+                    im = (im / scale + zero_point).astype(np.uint8)  # de-scale
+                self.interpreter.set_tensor(input['index'], im)
+                self.interpreter.invoke()
+                y = []
+                for output in self.output_details:
+                    x = self.interpreter.get_tensor(output['index'])
+                    if int8:
+                        scale, zero_point = output['quantization']
+                        x = (x.astype(np.float32) - zero_point) * scale  # re-scale
+                    y.append(x)
+            y = [x if isinstance(x, np.ndarray) else x.numpy() for x in y]
+            y[0][..., :4] *= [w, h, w, h]  # xywh normalized to pixels
+
+        if isinstance(y, (list, tuple)):
+            return self.from_numpy(y[0]) if len(y) == 1 else [self.from_numpy(x) for x in y]
+        else:
+            return self.from_numpy(y)
+
+    def from_numpy(self, x):
+        return torch.from_numpy(x).to(self.device) if isinstance(x, np.ndarray) else x
+
+    def warmup(self, imgsz=(1, 3, 640, 640)):
+        # Warmup model by running inference once
+        warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb, self.triton
+        if any(warmup_types) and (self.device.type != 'cpu' or self.triton):
+            im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device)  # input
+            for _ in range(2 if self.jit else 1):  #
+                self.forward(im)  # warmup
+
+    @staticmethod
+    def _model_type(p='path/to/model.pt'):
+        # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx
+        # types = [pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle]
+        from export import export_formats
+        sf = list(export_formats().Suffix)  # export suffixes
+        if not is_url(p, check=False):
+            check_suffix(p, sf)  # checks
+        url = urlparse(p)  # if url may be Triton inference server
+        types = [s in Path(p).name for s in sf]
+        types[8] &= not types[9]  # tflite &= not edgetpu
+        triton = not any(types) and all([any(s in url.scheme for s in ["http", "grpc"]), url.netloc])
+        return types + [triton]
+
+    @staticmethod
+    def _load_metadata(f=Path('path/to/meta.yaml')):
+        from ultralytics.yolo.utils.modeling import yaml_load
+
+        # Load metadata from meta.yaml if it exists
+        if f.exists():
+            d = yaml_load(f)
+            return d['stride'], d['names']  # assign stride, names
+        return None, None

ultralytics/yolo/utils/modeling/modules.py

@@ -0,0 +1,635 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Common modules
+"""
+
+import argparse
+import math
+import warnings
+from copy import copy
+from pathlib import Path
+
+import cv2
+import numpy as np
+import pandas as pd
+import requests
+import torch
+import torch.nn as nn
+from PIL import Image, ImageOps
+from torch.cuda import amp
+
+from ultralytics.yolo.data.augment import LetterBox
+from ultralytics.yolo.utils import LOGGER
+from ultralytics.yolo.utils.checks import check_version
+from ultralytics.yolo.utils.files import increment_path
+from ultralytics.yolo.utils.loggers import colorstr
+from ultralytics.yolo.utils.ops import Profile, make_divisible, non_max_suppression, scale_boxes, xyxy2xywh
+from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box
+from ultralytics.yolo.utils.torch_utils import copy_attr, smart_inference_mode
+
+from .autobackend import AutoBackend
+
+# from utils.plots import feature_visualization TODO
+
+
+def autopad(k, p=None, d=1):  # kernel, padding, dilation
+    # Pad to 'same' shape outputs
+    if d > 1:
+        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
+    if p is None:
+        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
+    return p
+
+
+class Conv(nn.Module):
+    # Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)
+    default_act = nn.SiLU()  # default activation
+
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
+        super().__init__()
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
+
+    def forward(self, x):
+        return self.act(self.bn(self.conv(x)))
+
+    def forward_fuse(self, x):
+        return self.act(self.conv(x))
+
+
+class DWConv(Conv):
+    # Depth-wise convolution
+    def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation
+        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)
+
+
+class DWConvTranspose2d(nn.ConvTranspose2d):
+    # Depth-wise transpose convolution
+    def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0):  # ch_in, ch_out, kernel, stride, padding, padding_out
+        super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))
+
+
+class TransformerLayer(nn.Module):
+    # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
+    def __init__(self, c, num_heads):
+        super().__init__()
+        self.q = nn.Linear(c, c, bias=False)
+        self.k = nn.Linear(c, c, bias=False)
+        self.v = nn.Linear(c, c, bias=False)
+        self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
+        self.fc1 = nn.Linear(c, c, bias=False)
+        self.fc2 = nn.Linear(c, c, bias=False)
+
+    def forward(self, x):
+        x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
+        x = self.fc2(self.fc1(x)) + x
+        return x
+
+
+class TransformerBlock(nn.Module):
+    # Vision Transformer https://arxiv.org/abs/2010.11929
+    def __init__(self, c1, c2, num_heads, num_layers):
+        super().__init__()
+        self.conv = None
+        if c1 != c2:
+            self.conv = Conv(c1, c2)
+        self.linear = nn.Linear(c2, c2)  # learnable position embedding
+        self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
+        self.c2 = c2
+
+    def forward(self, x):
+        if self.conv is not None:
+            x = self.conv(x)
+        b, _, w, h = x.shape
+        p = x.flatten(2).permute(2, 0, 1)
+        return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)
+
+
+class Bottleneck(nn.Module):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c2, 3, 1, g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class BottleneckCSP(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
+        self.act = nn.SiLU()
+        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1))))
+
+
+class CrossConv(nn.Module):
+    # Cross Convolution Downsample
+    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, (1, k), (1, s))
+        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class C3(nn.Module):
+    # CSP Bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
+        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+
+    def forward(self, x):
+        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
+
+
+class C3x(C3):
+    # C3 module with cross-convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = nn.Sequential(*(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)))
+
+
+class C3TR(C3):
+    # C3 module with TransformerBlock()
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = TransformerBlock(c_, c_, 4, n)
+
+
+class C3SPP(C3):
+    # C3 module with SPP()
+    def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = SPP(c_, c_, k)
+
+
+class C3Ghost(C3):
+    # C3 module with GhostBottleneck()
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
+
+
+class SPP(nn.Module):
+    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
+    def __init__(self, c1, c2, k=(5, 9, 13)):
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+    def forward(self, x):
+        x = self.cv1(x)
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
+            return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
+
+
+class SPPF(nn.Module):
+    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
+    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * 4, c2, 1, 1)
+        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
+
+    def forward(self, x):
+        x = self.cv1(x)
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
+            y1 = self.m(x)
+            y2 = self.m(y1)
+            return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))
+
+
+class Focus(nn.Module):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act)
+        # self.contract = Contract(gain=2)
+
+    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+        return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1))
+        # return self.conv(self.contract(x))
+
+
+class GhostConv(nn.Module):
+    # Ghost Convolution https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
+        super().__init__()
+        c_ = c2 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, k, s, None, g, act=act)
+        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act)
+
+    def forward(self, x):
+        y = self.cv1(x)
+        return torch.cat((y, self.cv2(y)), 1)
+
+
+class GhostBottleneck(nn.Module):
+    # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stride
+        super().__init__()
+        c_ = c2 // 2
+        self.conv = nn.Sequential(
+            GhostConv(c1, c_, 1, 1),  # pw
+            DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
+            GhostConv(c_, c2, 1, 1, act=False))  # pw-linear
+        self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False), Conv(c1, c2, 1, 1,
+                                                                            act=False)) if s == 2 else nn.Identity()
+
+    def forward(self, x):
+        return self.conv(x) + self.shortcut(x)
+
+
+class Contract(nn.Module):
+    # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        b, c, h, w = x.size()  # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
+        s = self.gain
+        x = x.view(b, c, h // s, s, w // s, s)  # x(1,64,40,2,40,2)
+        x = x.permute(0, 3, 5, 1, 2, 4).contiguous()  # x(1,2,2,64,40,40)
+        return x.view(b, c * s * s, h // s, w // s)  # x(1,256,40,40)
+
+
+class Expand(nn.Module):
+    # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        b, c, h, w = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
+        s = self.gain
+        x = x.view(b, s, s, c // s ** 2, h, w)  # x(1,2,2,16,80,80)
+        x = x.permute(0, 3, 4, 1, 5, 2).contiguous()  # x(1,16,80,2,80,2)
+        return x.view(b, c // s ** 2, h * s, w * s)  # x(1,16,160,160)
+
+
+class Concat(nn.Module):
+    # Concatenate a list of tensors along dimension
+    def __init__(self, dimension=1):
+        super().__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        return torch.cat(x, self.d)
+
+
+class AutoShape(nn.Module):
+    # YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
+    conf = 0.25  # NMS confidence threshold
+    iou = 0.45  # NMS IoU threshold
+    agnostic = False  # NMS class-agnostic
+    multi_label = False  # NMS multiple labels per box
+    classes = None  # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
+    max_det = 1000  # maximum number of detections per image
+    amp = False  # Automatic Mixed Precision (AMP) inference
+
+    def __init__(self, model, verbose=True):
+        super().__init__()
+        if verbose:
+            LOGGER.info('Adding AutoShape... ')
+        copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=())  # copy attributes
+        self.dmb = isinstance(model, AutoBackend)  # DetectMultiBackend() instance
+        self.pt = not self.dmb or model.pt  # PyTorch model
+        self.model = model.eval()
+        if self.pt:
+            m = self.model.model.model[-1] if self.dmb else self.model.model[-1]  # Detect()
+            m.inplace = False  # Detect.inplace=False for safe multithread inference
+            m.export = True  # do not output loss values
+
+    def _apply(self, fn):
+        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+        self = super()._apply(fn)
+        if self.pt:
+            m = self.model.model.model[-1] if self.dmb else self.model.model[-1]  # Detect()
+            m.stride = fn(m.stride)
+            m.grid = list(map(fn, m.grid))
+            if isinstance(m.anchor_grid, list):
+                m.anchor_grid = list(map(fn, m.anchor_grid))
+        return self
+
+    @smart_inference_mode()
+    def forward(self, ims, size=640, augment=False, profile=False):
+        # Inference from various sources. For size(height=640, width=1280), RGB images example inputs are:
+        #   file:        ims = 'data/images/zidane.jpg'  # str or PosixPath
+        #   URI:             = 'https://ultralytics.com/images/zidane.jpg'
+        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
+        #   PIL:             = Image.open('image.jpg') or ImageGrab.grab()  # HWC x(640,1280,3)
+        #   numpy:           = np.zeros((640,1280,3))  # HWC
+        #   torch:           = torch.zeros(16,3,320,640)  # BCHW (scaled to size=640, 0-1 values)
+        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images
+
+        dt = (Profile(), Profile(), Profile())
+        with dt[0]:
+            if isinstance(size, int):  # expand
+                size = (size, size)
+            p = next(self.model.parameters()) if self.pt else torch.empty(1, device=self.model.device)  # param
+            autocast = self.amp and (p.device.type != 'cpu')  # Automatic Mixed Precision (AMP) inference
+            if isinstance(ims, torch.Tensor):  # torch
+                with amp.autocast(autocast):
+                    return self.model(ims.to(p.device).type_as(p), augment=augment)  # inference
+
+            # Pre-process
+            n, ims = (len(ims), list(ims)) if isinstance(ims, (list, tuple)) else (1, [ims])  # number, list of images
+            shape0, shape1, files = [], [], []  # image and inference shapes, filenames
+            for i, im in enumerate(ims):
+                f = f'image{i}'  # filename
+                if isinstance(im, (str, Path)):  # filename or uri
+                    im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
+                    im = np.asarray(ImageOps.exif_transpose(im))
+                elif isinstance(im, Image.Image):  # PIL Image
+                    im, f = np.asarray(ImageOps.exif_transpose(im)), getattr(im, 'filename', f) or f
+                files.append(Path(f).with_suffix('.jpg').name)
+                if im.shape[0] < 5:  # image in CHW
+                    im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
+                im = im[..., :3] if im.ndim == 3 else cv2.cvtColor(im, cv2.COLOR_GRAY2BGR)  # enforce 3ch input
+                s = im.shape[:2]  # HWC
+                shape0.append(s)  # image shape
+                g = max(size) / max(s)  # gain
+                shape1.append([y * g for y in s])
+                ims[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
+            shape1 = [make_divisible(x, self.stride) for x in np.array(shape1).max(0)] if self.pt else size  # inf shape
+            x = [LetterBox(shape1, auto=False)(image=im)["img"] for im in ims]  # pad
+            x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2)))  # stack and BHWC to BCHW
+            x = torch.from_numpy(x).to(p.device).type_as(p) / 255  # uint8 to fp16/32
+
+        with amp.autocast(autocast):
+            # Inference
+            with dt[1]:
+                y = self.model(x, augment=augment)  # forward
+
+            # Post-process
+            with dt[2]:
+                y = non_max_suppression(y if self.dmb else y[0],
+                                        self.conf,
+                                        self.iou,
+                                        self.classes,
+                                        self.agnostic,
+                                        self.multi_label,
+                                        max_det=self.max_det)  # NMS
+                for i in range(n):
+                    scale_boxes(shape1, y[i][:, :4], shape0[i])
+
+            return Detections(ims, y, files, dt, self.names, x.shape)
+
+
+class Detections:
+    # YOLOv5 detections class for inference results
+    def __init__(self, ims, pred, files, times=(0, 0, 0), names=None, shape=None):
+        super().__init__()
+        d = pred[0].device  # device
+        gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in ims]  # normalizations
+        self.ims = ims  # list of images as numpy arrays
+        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
+        self.names = names  # class names
+        self.files = files  # image filenames
+        self.times = times  # profiling times
+        self.xyxy = pred  # xyxy pixels
+        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
+        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
+        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
+        self.n = len(self.pred)  # number of images (batch size)
+        self.t = tuple(x.t / self.n * 1E3 for x in times)  # timestamps (ms)
+        self.s = tuple(shape)  # inference BCHW shape
+
+    def _run(self, pprint=False, show=False, save=False, crop=False, render=False, labels=True, save_dir=Path('')):
+        s, crops = '', []
+        for i, (im, pred) in enumerate(zip(self.ims, self.pred)):
+            s += f'\nimage {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '  # string
+            if pred.shape[0]:
+                for c in pred[:, -1].unique():
+                    n = (pred[:, -1] == c).sum()  # detections per class
+                    s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
+                s = s.rstrip(', ')
+                if show or save or render or crop:
+                    annotator = Annotator(im, example=str(self.names))
+                    for *box, conf, cls in reversed(pred):  # xyxy, confidence, class
+                        label = f'{self.names[int(cls)]} {conf:.2f}'
+                        if crop:
+                            file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
+                            crops.append({
+                                'box': box,
+                                'conf': conf,
+                                'cls': cls,
+                                'label': label,
+                                'im': save_one_box(box, im, file=file, save=save)})
+                        else:  # all others
+                            annotator.box_label(box, label if labels else '', color=colors(cls))
+                    im = annotator.im
+            else:
+                s += '(no detections)'
+
+            im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im  # from np
+            if show:
+                im.show(self.files[i])  # show
+            if save:
+                f = self.files[i]
+                im.save(save_dir / f)  # save
+                if i == self.n - 1:
+                    LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
+            if render:
+                self.ims[i] = np.asarray(im)
+        if pprint:
+            s = s.lstrip('\n')
+            return f'{s}\nSpeed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {self.s}' % self.t
+        if crop:
+            if save:
+                LOGGER.info(f'Saved results to {save_dir}\n')
+            return crops
+
+    def show(self, labels=True):
+        self._run(show=True, labels=labels)  # show results
+
+    def save(self, labels=True, save_dir='runs/detect/exp', exist_ok=False):
+        save_dir = increment_path(save_dir, exist_ok, mkdir=True)  # increment save_dir
+        self._run(save=True, labels=labels, save_dir=save_dir)  # save results
+
+    def crop(self, save=True, save_dir='runs/detect/exp', exist_ok=False):
+        save_dir = increment_path(save_dir, exist_ok, mkdir=True) if save else None
+        return self._run(crop=True, save=save, save_dir=save_dir)  # crop results
+
+    def render(self, labels=True):
+        self._run(render=True, labels=labels)  # render results
+        return self.ims
+
+    def pandas(self):
+        # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
+        new = copy(self)  # return copy
+        ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name'  # xyxy columns
+        cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name'  # xywh columns
+        for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
+            a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)]  # update
+            setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
+        return new
+
+    def tolist(self):
+        # return a list of Detections objects, i.e. 'for result in results.tolist():'
+        r = range(self.n)  # iterable
+        x = [Detections([self.ims[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
+        # for d in x:
+        #    for k in ['ims', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
+        #        setattr(d, k, getattr(d, k)[0])  # pop out of list
+        return x
+
+    def print(self):
+        LOGGER.info(self.__str__())
+
+    def __len__(self):  # override len(results)
+        return self.n
+
+    def __str__(self):  # override print(results)
+        return self._run(pprint=True)  # print results
+
+    def __repr__(self):
+        return f'YOLOv5 {self.__class__} instance\n' + self.__str__()
+
+
+class Proto(nn.Module):
+    # YOLOv5 mask Proto module for segmentation models
+    def __init__(self, c1, c_=256, c2=32):  # ch_in, number of protos, number of masks
+        super().__init__()
+        self.cv1 = Conv(c1, c_, k=3)
+        self.upsample = nn.Upsample(scale_factor=2, mode='nearest')
+        self.cv2 = Conv(c_, c_, k=3)
+        self.cv3 = Conv(c_, c2)
+
+    def forward(self, x):
+        return self.cv3(self.cv2(self.upsample(self.cv1(x))))
+
+
+class Ensemble(nn.ModuleList):
+    # Ensemble of models
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x, augment=False, profile=False, visualize=False):
+        y = [module(x, augment, profile, visualize)[0] for module in self]
+        # y = torch.stack(y).max(0)[0]  # max ensemble
+        # y = torch.stack(y).mean(0)  # mean ensemble
+        y = torch.cat(y, 1)  # nms ensemble
+        return y, None  # inference, train output
+
+
+# heads
+class Detect(nn.Module):
+    # YOLOv5 Detect head for detection models
+    stride = None  # strides computed during build
+    dynamic = False  # force grid reconstruction
+    export = False  # export mode
+
+    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
+        super().__init__()
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.empty(0) for _ in range(self.nl)]  # init grid
+        self.anchor_grid = [torch.empty(0) for _ in range(self.nl)]  # init anchor grid
+        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+        self.inplace = inplace  # use inplace ops (e.g. slice assignment)
+
+    def forward(self, x):
+        z = []  # inference output
+        for i in range(self.nl):
+            x[i] = self.m[i](x[i])  # conv
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
+
+                if isinstance(self, Segment):  # (boxes + masks)
+                    xy, wh, conf, mask = x[i].split((2, 2, self.nc + 1, self.no - self.nc - 5), 4)
+                    xy = (xy.sigmoid() * 2 + self.grid[i]) * self.stride[i]  # xy
+                    wh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i]  # wh
+                    y = torch.cat((xy, wh, conf.sigmoid(), mask), 4)
+                else:  # Detect (boxes only)
+                    xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4)
+                    xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
+                    wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
+                    y = torch.cat((xy, wh, conf), 4)
+                z.append(y.view(bs, self.na * nx * ny, self.no))
+
+        return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)
+
+    def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):
+        d = self.anchors[i].device
+        t = self.anchors[i].dtype
+        shape = 1, self.na, ny, nx, 2  # grid shape
+        y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
+        yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x)  # torch>=0.7 compatibility
+        grid = torch.stack((xv, yv), 2).expand(shape) - 0.5  # add grid offset, i.e. y = 2.0 * x - 0.5
+        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
+        return grid, anchor_grid
+
+
+class Segment(Detect):
+    # YOLOv5 Segment head for segmentation models
+    def __init__(self, nc=80, anchors=(), nm=32, npr=256, ch=(), inplace=True):
+        super().__init__(nc, anchors, ch, inplace)
+        self.nm = nm  # number of masks
+        self.npr = npr  # number of protos
+        self.no = 5 + nc + self.nm  # number of outputs per anchor
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+        self.proto = Proto(ch[0], self.npr, self.nm)  # protos
+        self.detect = Detect.forward
+
+    def forward(self, x):
+        p = self.proto(x[0])
+        x = self.detect(self, x)
+        return (x, p) if self.training else (x[0], p) if self.export else (x[0], p, x[1])
+
+
+class Classify(nn.Module):
+    # YOLOv5 classification head, i.e. x(b,c1,20,20) to x(b,c2)
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        c_ = 1280  # efficientnet_b0 size
+        self.conv = Conv(c1, c_, k, s, autopad(k, p), g)
+        self.pool = nn.AdaptiveAvgPool2d(1)  # to x(b,c_,1,1)
+        self.drop = nn.Dropout(p=0.0, inplace=True)
+        self.linear = nn.Linear(c_, c2)  # to x(b,c2)
+
+    def forward(self, x):
+        if isinstance(x, list):
+            x = torch.cat(x, 1)
+        return self.linear(self.drop(self.pool(self.conv(x)).flatten(1)))

ultralytics/yolo/utils/modeling/tasks.py

@@ -0,0 +1,199 @@
+import time
+from copy import deepcopy
+
+import thop
+import torch.nn as nn
+
+from ultralytics.yolo.utils import LOGGER
+from ultralytics.yolo.utils.anchors import check_anchor_order
+from ultralytics.yolo.utils.modeling import parse_model
+from ultralytics.yolo.utils.modeling.modules import *
+from ultralytics.yolo.utils.torch_utils import fuse_conv_and_bn, initialize_weights, model_info, scale_img, time_sync
+
+
+class BaseModel(nn.Module):
+    # YOLOv5 base model
+    def forward(self, x, profile=False, visualize=False):
+        return self._forward_once(x, profile, visualize)  # single-scale inference, train
+
+    def _forward_once(self, x, profile=False, visualize=False):
+        y, dt = [], []  # outputs
+        for m in self.model:
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+            if profile:
+                self._profile_one_layer(m, x, dt)
+            x = m(x)  # run
+            y.append(x if m.i in self.save else None)  # save output
+            if visualize:
+                pass
+                # TODO: feature_visualization(x, m.type, m.i, save_dir=visualize)
+        return x
+
+    def _profile_one_layer(self, m, x, dt):
+        c = m == self.model[-1]  # is final layer, copy input as inplace fix
+        o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
+        t = time_sync()
+        for _ in range(10):
+            m(x.copy() if c else x)
+        dt.append((time_sync() - t) * 100)
+        if m == self.model[0]:
+            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  module")
+        LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
+        if c:
+            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")
+
+    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
+        LOGGER.info('Fusing layers... ')
+        for m in self.model.modules():
+            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
+                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
+                delattr(m, 'bn')  # remove batchnorm
+                m.forward = m.forward_fuse  # update forward
+        self.info()
+        return self
+
+    def info(self, verbose=False, img_size=640):  # print model information
+        model_info(self, verbose, img_size)
+
+    def _apply(self, fn):
+        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+        self = super()._apply(fn)
+        m = self.model[-1]  # Detect()
+        if isinstance(m, (Detect, Segment)):
+            m.stride = fn(m.stride)
+            m.grid = list(map(fn, m.grid))
+            if isinstance(m.anchor_grid, list):
+                m.anchor_grid = list(map(fn, m.anchor_grid))
+        return self
+
+
+class DetectionModel(BaseModel):
+    # YOLO detection model
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
+        super().__init__()
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg, encoding='ascii', errors='ignore') as f:
+                self.yaml = yaml.safe_load(f)  # model dict
+
+        # Define model
+        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
+        if nc and nc != self.yaml['nc']:
+            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
+            self.yaml['nc'] = nc  # override yaml value
+        if anchors:
+            LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
+            self.yaml['anchors'] = round(anchors)  # override yaml value
+        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
+        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
+        self.inplace = self.yaml.get('inplace', True)
+
+        # Build strides, anchors
+        m = self.model[-1]  # Detect()
+        if isinstance(m, (Detect, Segment)):
+            s = 256  # 2x min stride
+            m.inplace = self.inplace
+            forward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x)
+            m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
+            check_anchor_order(m)
+            m.anchors /= m.stride.view(-1, 1, 1)
+            self.stride = m.stride
+            self._initialize_biases()  # only run once
+
+        # Init weights, biases
+        initialize_weights(self)
+        self.info()
+        LOGGER.info('')
+
+    def forward(self, x, augment=False, profile=False, visualize=False):
+        if augment:
+            return self._forward_augment(x)  # augmented inference, None
+        return self._forward_once(x, profile, visualize)  # single-scale inference, train
+
+    def _forward_augment(self, x):
+        img_size = x.shape[-2:]  # height, width
+        s = [1, 0.83, 0.67]  # scales
+        f = [None, 3, None]  # flips (2-ud, 3-lr)
+        y = []  # outputs
+        for si, fi in zip(s, f):
+            xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
+            yi = self._forward_once(xi)[0]  # forward
+            # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
+            yi = self._descale_pred(yi, fi, si, img_size)
+            y.append(yi)
+        y = self._clip_augmented(y)  # clip augmented tails
+        return torch.cat(y, 1), None  # augmented inference, train
+
+    def _descale_pred(self, p, flips, scale, img_size):
+        # de-scale predictions following augmented inference (inverse operation)
+        if self.inplace:
+            p[..., :4] /= scale  # de-scale
+            if flips == 2:
+                p[..., 1] = img_size[0] - p[..., 1]  # de-flip ud
+            elif flips == 3:
+                p[..., 0] = img_size[1] - p[..., 0]  # de-flip lr
+        else:
+            x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scale
+            if flips == 2:
+                y = img_size[0] - y  # de-flip ud
+            elif flips == 3:
+                x = img_size[1] - x  # de-flip lr
+            p = torch.cat((x, y, wh, p[..., 4:]), -1)
+        return p
+
+    def _clip_augmented(self, y):
+        # Clip YOLOv5 augmented inference tails
+        nl = self.model[-1].nl  # number of detection layers (P3-P5)
+        g = sum(4 ** x for x in range(nl))  # grid points
+        e = 1  # exclude layer count
+        i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
+        y[0] = y[0][:, :-i]  # large
+        i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
+        y[-1] = y[-1][:, i:]  # small
+        return y
+
+    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Detect() module
+        for mi, s in zip(m.m, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b.data[:, 5:5 + m.nc] += math.log(0.6 / (m.nc - 0.99999)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+
+class SegmentationModel(DetectionModel):
+    # YOLOv5 segmentation model
+    def __init__(self, cfg='yolov5s-seg.yaml', ch=3, nc=None, anchors=None):
+        super().__init__(cfg, ch, nc, anchors)
+
+
+class ClassificationModel(BaseModel):
+    # YOLOv5 classification model
+    def __init__(self, cfg=None, model=None, nc=1000, cutoff=10):  # yaml, model, number of classes, cutoff index
+        super().__init__()
+        self._from_detection_model(model, nc, cutoff) if model is not None else self._from_yaml(cfg)
+
+    def _from_detection_model(self, model, nc=1000, cutoff=10):
+        # Create a YOLOv5 classification model from a YOLOv5 detection model
+        if isinstance(model, AutoBackend):
+            model = model.model  # unwrap DetectMultiBackend
+        model.model = model.model[:cutoff]  # backbone
+        m = model.model[-1]  # last layer
+        ch = m.conv.in_channels if hasattr(m, 'conv') else m.cv1.conv.in_channels  # ch into module
+        c = Classify(ch, nc)  # Classify()
+        c.i, c.f, c.type = m.i, m.f, 'models.common.Classify'  # index, from, type
+        model.model[-1] = c  # replace
+        self.model = model.model
+        self.stride = model.stride
+        self.save = []
+        self.nc = nc
+
+    def _from_yaml(self, cfg):
+        # Create a YOLOv5 classification model from a *.yaml file
+        self.model = None

ultralytics/yolo/utils/ops.py

@@ -0,0 +1,306 @@
+import contextlib
+import math
+import time
+
+import cv2
+import numpy as np
+import torch
+import torchvision
+
+from ultralytics.yolo.utils import LOGGER
+
+from .metrics import box_iou
+
+
+class Profile(contextlib.ContextDecorator):
+    # YOLOv5 Profile class. Usage: @Profile() decorator or 'with Profile():' context manager
+    def __init__(self, t=0.0):
+        self.t = t
+        self.cuda = torch.cuda.is_available()
+
+    def __enter__(self):
+        self.start = self.time()
+        return self
+
+    def __exit__(self, type, value, traceback):
+        self.dt = self.time() - self.start  # delta-time
+        self.t += self.dt  # accumulate dt
+
+    def time(self):
+        if self.cuda:
+            torch.cuda.synchronize()
+        return time.time()
+
+
+def segment2box(segment, width=640, height=640):
+    # Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
+    x, y = segment.T  # segment xy
+    inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
+    x, y, = (
+        x[inside],
+        y[inside],
+    )
+    return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros(4)  # xyxy
+
+
+def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None):
+    # Rescale boxes (xyxy) from img1_shape to img0_shape
+    if ratio_pad is None:  # calculate from img0_shape
+        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
+        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
+    else:
+        gain = ratio_pad[0][0]
+        pad = ratio_pad[1]
+
+    boxes[:, [0, 2]] -= pad[0]  # x padding
+    boxes[:, [1, 3]] -= pad[1]  # y padding
+    boxes[:, :4] /= gain
+    clip_boxes(boxes, img0_shape)
+    return boxes
+
+
+def clip_boxes(boxes, shape):
+    # Clip boxes (xyxy) to image shape (height, width)
+    if isinstance(boxes, torch.Tensor):  # faster individually
+        boxes[:, 0].clamp_(0, shape[1])  # x1
+        boxes[:, 1].clamp_(0, shape[0])  # y1
+        boxes[:, 2].clamp_(0, shape[1])  # x2
+        boxes[:, 3].clamp_(0, shape[0])  # y2
+    else:  # np.array (faster grouped)
+        boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1])  # x1, x2
+        boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0])  # y1, y2
+
+
+def make_divisible(x, divisor):
+    # Returns nearest x divisible by divisor
+    if isinstance(divisor, torch.Tensor):
+        divisor = int(divisor.max())  # to int
+    return math.ceil(x / divisor) * divisor
+
+
+def non_max_suppression(
+        prediction,
+        conf_thres=0.25,
+        iou_thres=0.45,
+        classes=None,
+        agnostic=False,
+        multi_label=False,
+        labels=(),
+        max_det=300,
+        nm=0,  # number of masks
+):
+    """Non-Maximum Suppression (NMS) on inference results to reject overlapping detections
+    Returns:
+         list of detections, on (n,6) tensor per image [xyxy, conf, cls]
+    """
+
+    if isinstance(prediction, (list, tuple)):  # YOLOv5 model in validation model, output = (inference_out, loss_out)
+        prediction = prediction[0]  # select only inference output
+
+    device = prediction.device
+    mps = 'mps' in device.type  # Apple MPS
+    if mps:  # MPS not fully supported yet, convert tensors to CPU before NMS
+        prediction = prediction.cpu()
+    bs = prediction.shape[0]  # batch size
+    nc = prediction.shape[2] - nm - 5  # number of classes
+    xc = prediction[..., 4] > conf_thres  # candidates
+
+    # Checks
+    assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
+    assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
+
+    # Settings
+    # min_wh = 2  # (pixels) minimum box width and height
+    max_wh = 7680  # (pixels) maximum box width and height
+    max_nms = 30000  # maximum number of boxes into torchvision.ops.nms()
+    time_limit = 0.5 + 0.05 * bs  # seconds to quit after
+    redundant = True  # require redundant detections
+    multi_label &= nc > 1  # multiple labels per box (adds 0.5ms/img)
+    merge = False  # use merge-NMS
+
+    t = time.time()
+    mi = 5 + nc  # mask start index
+    output = [torch.zeros((0, 6 + nm), device=prediction.device)] * bs
+    for xi, x in enumerate(prediction):  # image index, image inference
+        # Apply constraints
+        # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0  # width-height
+        x = x[xc[xi]]  # confidence
+
+        # Cat apriori labels if autolabelling
+        if labels and len(labels[xi]):
+            lb = labels[xi]
+            v = torch.zeros((len(lb), nc + nm + 5), device=x.device)
+            v[:, :4] = lb[:, 1:5]  # box
+            v[:, 4] = 1.0  # conf
+            v[range(len(lb)), lb[:, 0].long() + 5] = 1.0  # cls
+            x = torch.cat((x, v), 0)
+
+        # If none remain process next image
+        if not x.shape[0]:
+            continue
+
+        # Compute conf
+        x[:, 5:] *= x[:, 4:5]  # conf = obj_conf * cls_conf
+
+        # Box/Mask
+        box = xywh2xyxy(x[:, :4])  # center_x, center_y, width, height) to (x1, y1, x2, y2)
+        mask = x[:, mi:]  # zero columns if no masks
+
+        # Detections matrix nx6 (xyxy, conf, cls)
+        if multi_label:
+            i, j = (x[:, 5:mi] > conf_thres).nonzero(as_tuple=False).T
+            x = torch.cat((box[i], x[i, 5 + j, None], j[:, None].float(), mask[i]), 1)
+        else:  # best class only
+            conf, j = x[:, 5:mi].max(1, keepdim=True)
+            x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres]
+
+        # Filter by class
+        if classes is not None:
+            x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
+
+        # Apply finite constraint
+        # if not torch.isfinite(x).all():
+        #     x = x[torch.isfinite(x).all(1)]
+
+        # Check shape
+        n = x.shape[0]  # number of boxes
+        if not n:  # no boxes
+            continue
+        elif n > max_nms:  # excess boxes
+            x = x[x[:, 4].argsort(descending=True)[:max_nms]]  # sort by confidence
+        else:
+            x = x[x[:, 4].argsort(descending=True)]  # sort by confidence
+
+        # Batched NMS
+        c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
+        boxes, scores = x[:, :4] + c, x[:, 4]  # boxes (offset by class), scores
+        i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
+        if i.shape[0] > max_det:  # limit detections
+            i = i[:max_det]
+        if merge and (1 < n < 3E3):  # Merge NMS (boxes merged using weighted mean)
+            # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
+            iou = box_iou(boxes[i], boxes) > iou_thres  # iou matrix
+            weights = iou * scores[None]  # box weights
+            x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True)  # merged boxes
+            if redundant:
+                i = i[iou.sum(1) > 1]  # require redundancy
+
+        output[xi] = x[i]
+        if mps:
+            output[xi] = output[xi].to(device)
+        if (time.time() - t) > time_limit:
+            LOGGER.warning(f'WARNING ⚠️ NMS time limit {time_limit:.3f}s exceeded')
+            break  # time limit exceeded
+
+    return output
+
+
+def clip_coords(boxes, shape):
+    # Clip bounding xyxy bounding boxes to image shape (height, width)
+    if isinstance(boxes, torch.Tensor):  # faster individually
+        boxes[:, 0].clamp_(0, shape[1])  # x1
+        boxes[:, 1].clamp_(0, shape[0])  # y1
+        boxes[:, 2].clamp_(0, shape[1])  # x2
+        boxes[:, 3].clamp_(0, shape[0])  # y2
+    else:  # np.array (faster grouped)
+        boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1])  # x1, x2
+        boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0])  # y1, y2
+
+
+def scale_image(im1_shape, masks, im0_shape, ratio_pad=None):
+    """
+    img1_shape: model input shape, [h, w]
+    img0_shape: origin pic shape, [h, w, 3]
+    masks: [h, w, num]
+    """
+    # Rescale coordinates (xyxy) from im1_shape to im0_shape
+    if ratio_pad is None:  # calculate from im0_shape
+        gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1])  # gain  = old / new
+        pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2  # wh padding
+    else:
+        pad = ratio_pad[1]
+    top, left = int(pad[1]), int(pad[0])  # y, x
+    bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0])
+
+    if len(masks.shape) < 2:
+        raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}')
+    masks = masks[top:bottom, left:right]
+    # masks = masks.permute(2, 0, 1).contiguous()
+    # masks = F.interpolate(masks[None], im0_shape[:2], mode='bilinear', align_corners=False)[0]
+    # masks = masks.permute(1, 2, 0).contiguous()
+    masks = cv2.resize(masks, (im0_shape[1], im0_shape[0]))
+
+    if len(masks.shape) == 2:
+        masks = masks[:, :, None]
+    return masks
+
+
+def xyxy2xywh(x):
+    # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = (x[:, 0] + x[:, 2]) / 2  # x center
+    y[:, 1] = (x[:, 1] + x[:, 3]) / 2  # y center
+    y[:, 2] = x[:, 2] - x[:, 0]  # width
+    y[:, 3] = x[:, 3] - x[:, 1]  # height
+    return y
+
+
+def xywh2xyxy(x):
+    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
+    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
+    y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
+    y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
+    return y
+
+
+def xywh2ltwh(x):
+    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, w, h] where xy1=top-left
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
+    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
+    return y
+
+
+def xyxy2ltwh(x):
+    # Convert nx4 boxes from [x1, y1, x2, y2] to [x1, y1, w, h] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 2] = x[:, 2] - x[:, 0]  # width
+    y[:, 3] = x[:, 3] - x[:, 1]  # height
+    return y
+
+
+def ltwh2xywh(x):
+    # Convert nx4 boxes from [x1, y1, w, h] to [x, y, w, h] where xy1=top-left, xy=center
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = x[:, 0] + x[:, 2] / 2  # center x
+    y[:, 1] = x[:, 1] + x[:, 3] / 2  # center y
+    return y
+
+
+def ltwh2xyxy(x):
+    # Convert nx4 boxes from [x1, y1, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 2] = x[:, 2] + x[:, 0]  # width
+    y[:, 3] = x[:, 3] + x[:, 1]  # height
+    return y
+
+
+def segments2boxes(segments):
+    # Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
+    boxes = []
+    for s in segments:
+        x, y = s.T  # segment xy
+        boxes.append([x.min(), y.min(), x.max(), y.max()])  # cls, xyxy
+    return xyxy2xywh(np.array(boxes))  # cls, xywh
+
+
+def resample_segments(segments, n=1000):
+    # Up-sample an (n,2) segment
+    for i, s in enumerate(segments):
+        s = np.concatenate((s, s[0:1, :]), axis=0)
+        x = np.linspace(0, len(s) - 1, n)
+        xp = np.arange(len(s))
+        segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T  # segment xy
+    return segments

ultralytics/yolo/utils/plotting.py

@@ -0,0 +1,181 @@
+from pathlib import Path
+from urllib.error import URLError
+
+import cv2
+import numpy as np
+import torch
+from PIL import Image, ImageDraw, ImageFont
+
+from ultralytics.yolo.utils import CONFIG_DIR, FONT
+
+from .checks import check_font, check_requirements, is_ascii
+from .files import increment_path
+from .ops import clip_coords, scale_image, xywh2xyxy, xyxy2xywh
+
+
+class Colors:
+    # Ultralytics color palette https://ultralytics.com/
+    def __init__(self):
+        # hex = matplotlib.colors.TABLEAU_COLORS.values()
+        hexs = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB',
+                '2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7')
+        self.palette = [self.hex2rgb(f'#{c}') for c in hexs]
+        self.n = len(self.palette)
+
+    def __call__(self, i, bgr=False):
+        c = self.palette[int(i) % self.n]
+        return (c[2], c[1], c[0]) if bgr else c
+
+    @staticmethod
+    def hex2rgb(h):  # rgb order (PIL)
+        return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4))
+
+
+colors = Colors()  # create instance for 'from utils.plots import colors'
+
+
+class Annotator:
+    # YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations
+    def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'):
+        assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.'
+        non_ascii = not is_ascii(example)  # non-latin labels, i.e. asian, arabic, cyrillic
+        self.pil = pil or non_ascii
+        if self.pil:  # use PIL
+            self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
+            self.draw = ImageDraw.Draw(self.im)
+            self.font = check_pil_font(font='Arial.Unicode.ttf' if non_ascii else font,
+                                       size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12))
+        else:  # use cv2
+            self.im = im
+        self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2)  # line width
+
+    def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)):
+        # Add one xyxy box to image with label
+        if self.pil or not is_ascii(label):
+            self.draw.rectangle(box, width=self.lw, outline=color)  # box
+            if label:
+                w, h = self.font.getsize(label)  # text width, height
+                outside = box[1] - h >= 0  # label fits outside box
+                self.draw.rectangle(
+                    (box[0], box[1] - h if outside else box[1], box[0] + w + 1,
+                     box[1] + 1 if outside else box[1] + h + 1),
+                    fill=color,
+                )
+                # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls')  # for PIL>8.0
+                self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font)
+        else:  # cv2
+            p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
+            cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA)
+            if label:
+                tf = max(self.lw - 1, 1)  # font thickness
+                w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0]  # text width, height
+                outside = p1[1] - h >= 3
+                p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3
+                cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA)  # filled
+                cv2.putText(self.im,
+                            label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2),
+                            0,
+                            self.lw / 3,
+                            txt_color,
+                            thickness=tf,
+                            lineType=cv2.LINE_AA)
+
+    def masks(self, masks, colors, im_gpu=None, alpha=0.5):
+        """Plot masks at once.
+        Args:
+            masks (tensor): predicted masks on cuda, shape: [n, h, w]
+            colors (List[List[Int]]): colors for predicted masks, [[r, g, b] * n]
+            im_gpu (tensor): img is in cuda, shape: [3, h, w], range: [0, 1]
+            alpha (float): mask transparency: 0.0 fully transparent, 1.0 opaque
+        """
+        if self.pil:
+            # convert to numpy first
+            self.im = np.asarray(self.im).copy()
+        if im_gpu is None:
+            # Add multiple masks of shape(h,w,n) with colors list([r,g,b], [r,g,b], ...)
+            if len(masks) == 0:
+                return
+            if isinstance(masks, torch.Tensor):
+                masks = torch.as_tensor(masks, dtype=torch.uint8)
+                masks = masks.permute(1, 2, 0).contiguous()
+                masks = masks.cpu().numpy()
+            # masks = np.ascontiguousarray(masks.transpose(1, 2, 0))
+            masks = scale_image(masks.shape[:2], masks, self.im.shape)
+            masks = np.asarray(masks, dtype=np.float32)
+            colors = np.asarray(colors, dtype=np.float32)  # shape(n,3)
+            s = masks.sum(2, keepdims=True).clip(0, 1)  # add all masks together
+            masks = (masks @ colors).clip(0, 255)  # (h,w,n) @ (n,3) = (h,w,3)
+            self.im[:] = masks * alpha + self.im * (1 - s * alpha)
+        else:
+            if len(masks) == 0:
+                self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
+            colors = torch.tensor(colors, device=im_gpu.device, dtype=torch.float32) / 255.0
+            colors = colors[:, None, None]  # shape(n,1,1,3)
+            masks = masks.unsqueeze(3)  # shape(n,h,w,1)
+            masks_color = masks * (colors * alpha)  # shape(n,h,w,3)
+
+            inv_alph_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
+            mcs = (masks_color * inv_alph_masks).sum(0) * 2  # mask color summand shape(n,h,w,3)
+
+            im_gpu = im_gpu.flip(dims=[0])  # flip channel
+            im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
+            im_gpu = im_gpu * inv_alph_masks[-1] + mcs
+            im_mask = (im_gpu * 255).byte().cpu().numpy()
+            self.im[:] = scale_image(im_gpu.shape, im_mask, self.im.shape)
+        if self.pil:
+            # convert im back to PIL and update draw
+            self.fromarray(self.im)
+
+    def rectangle(self, xy, fill=None, outline=None, width=1):
+        # Add rectangle to image (PIL-only)
+        self.draw.rectangle(xy, fill, outline, width)
+
+    def text(self, xy, text, txt_color=(255, 255, 255), anchor='top'):
+        # Add text to image (PIL-only)
+        if anchor == 'bottom':  # start y from font bottom
+            w, h = self.font.getsize(text)  # text width, height
+            xy[1] += 1 - h
+        self.draw.text(xy, text, fill=txt_color, font=self.font)
+
+    def fromarray(self, im):
+        # Update self.im from a numpy array
+        self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
+        self.draw = ImageDraw.Draw(self.im)
+
+    def result(self):
+        # Return annotated image as array
+        return np.asarray(self.im)
+
+
+def check_pil_font(font=FONT, size=10):
+    # Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary
+    font = Path(font)
+    font = font if font.exists() else (CONFIG_DIR / font.name)
+    try:
+        return ImageFont.truetype(str(font) if font.exists() else font.name, size)
+    except Exception:  # download if missing
+        try:
+            check_font(font)
+            return ImageFont.truetype(str(font), size)
+        except TypeError:
+            check_requirements('Pillow>=8.4.0')  # known issue https://github.com/ultralytics/yolov5/issues/5374
+        except URLError:  # not online
+            return ImageFont.load_default()
+
+
+def save_one_box(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=10, square=False, BGR=False, save=True):
+    # Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop
+    xyxy = torch.tensor(xyxy).view(-1, 4)
+    b = xyxy2xywh(xyxy)  # boxes
+    if square:
+        b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1)  # attempt rectangle to square
+    b[:, 2:] = b[:, 2:] * gain + pad  # box wh * gain + pad
+    xyxy = xywh2xyxy(b).long()
+    clip_coords(xyxy, im.shape)
+    crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)]
+    if save:
+        file.parent.mkdir(parents=True, exist_ok=True)  # make directory
+        f = str(increment_path(file).with_suffix('.jpg'))
+        # cv2.imwrite(f, crop)  # save BGR, https://github.com/ultralytics/yolov5/issues/7007 chroma subsampling issue
+        Image.fromarray(crop[..., ::-1]).save(f, quality=95, subsampling=0)  # save RGB
+    return crop

ultralytics/yolo/utils/torch_utils.py

@@ -1,11 +1,20 @@
+import math
 import os
+import time
 from contextlib import contextmanager
+from copy import deepcopy
+from pathlib import Path
 
+import thop
 import torch
 import torch.distributed as dist
+import torch.nn as nn
+import torch.nn.functional as F
 from torch.nn.parallel import DistributedDataParallel as DDP
 
-from ultralytics.yolo.utils import check_version
+from ultralytics.yolo.utils import LOGGER
+
+from .checks import check_version
 
 LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1))  # https://pytorch.org/docs/stable/elastic/run.html
 RANK = int(os.getenv('RANK', -1))
@@ -68,3 +77,100 @@ def select_device(device='', batch_size=0, newline=True):
         s = s.rstrip()
     print(s)
     return torch.device(arg)
+
+
+def time_sync():
+    # PyTorch-accurate time
+    if torch.cuda.is_available():
+        torch.cuda.synchronize()
+    return time.time()
+
+
+def fuse_conv_and_bn(conv, bn):
+    # Fuse Conv2d() and BatchNorm2d() layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/
+    fusedconv = nn.Conv2d(conv.in_channels,
+                          conv.out_channels,
+                          kernel_size=conv.kernel_size,
+                          stride=conv.stride,
+                          padding=conv.padding,
+                          dilation=conv.dilation,
+                          groups=conv.groups,
+                          bias=True).requires_grad_(False).to(conv.weight.device)
+
+    # Prepare filters
+    w_conv = conv.weight.clone().view(conv.out_channels, -1)
+    w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
+    fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape))
+
+    # Prepare spatial bias
+    b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias
+    b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
+    fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn)
+
+    return fusedconv
+
+
+def model_info(model, verbose=False, imgsz=640):
+    # Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320]
+    n_p = sum(x.numel() for x in model.parameters())  # number parameters
+    n_g = sum(x.numel() for x in model.parameters() if x.requires_grad)  # number gradients
+    if verbose:
+        print(f"{'layer':>5} {'name':>40} {'gradient':>9} {'parameters':>12} {'shape':>20} {'mu':>10} {'sigma':>10}")
+        for i, (name, p) in enumerate(model.named_parameters()):
+            name = name.replace('module_list.', '')
+            print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
+                  (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
+
+    try:  # FLOPs
+        p = next(model.parameters())
+        stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32  # max stride
+        im = torch.empty((1, p.shape[1], stride, stride), device=p.device)  # input image in BCHW format
+        flops = thop.profile(deepcopy(model), inputs=(im,), verbose=False)[0] / 1E9 * 2  # stride GFLOPs
+        imgsz = imgsz if isinstance(imgsz, list) else [imgsz, imgsz]  # expand if int/float
+        fs = f', {flops * imgsz[0] / stride * imgsz[1] / stride:.1f} GFLOPs'  # 640x640 GFLOPs
+    except Exception:
+        fs = ''
+
+    name = Path(model.yaml_file).stem.replace('yolov5', 'YOLOv5') if hasattr(model, 'yaml_file') else 'Model'
+    LOGGER.info(f"{name} summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}")
+
+
+def initialize_weights(model):
+    for m in model.modules():
+        t = type(m)
+        if t is nn.Conv2d:
+            pass  # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+        elif t is nn.BatchNorm2d:
+            m.eps = 1e-3
+            m.momentum = 0.03
+        elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
+            m.inplace = True
+
+
+def scale_img(img, ratio=1.0, same_shape=False, gs=32):  # img(16,3,256,416)
+    # Scales img(bs,3,y,x) by ratio constrained to gs-multiple
+    if ratio == 1.0:
+        return img
+    h, w = img.shape[2:]
+    s = (int(h * ratio), int(w * ratio))  # new size
+    img = F.interpolate(img, size=s, mode='bilinear', align_corners=False)  # resize
+    if not same_shape:  # pad/crop img
+        h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w))
+    return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447)  # value = imagenet mean
+
+
+def copy_attr(a, b, include=(), exclude=()):
+    # Copy attributes from b to a, options to only include [...] and to exclude [...]
+    for k, v in b.__dict__.items():
+        if (len(include) and k not in include) or k.startswith('_') or k in exclude:
+            continue
+        else:
+            setattr(a, k, v)
+
+
+def smart_inference_mode(torch_1_9=check_version(torch.__version__, '1.9.0')):
+    # Applies torch.inference_mode() decorator if torch>=1.9.0 else torch.no_grad() decorator
+    def decorate(fn):
+        return (torch.inference_mode if torch_1_9 else torch.no_grad)()(fn)
+
+    return decorate

ultralytics/yolo/v8/classify/train.py

@@ -7,9 +7,12 @@ import torch
 import torchvision
 from val import ClassificationValidator
 
-from ultralytics.yolo import BaseTrainer, utils, v8
+from ultralytics.yolo import BaseTrainer, v8
 from ultralytics.yolo.data import build_classification_dataloader
 from ultralytics.yolo.engine.trainer import CONFIG_PATH_ABS, DEFAULT_CONFIG
+from ultralytics.yolo.utils.downloads import download
+from ultralytics.yolo.utils.files import WorkingDirectory
+from ultralytics.yolo.utils.torch_utils import LOCAL_RANK, torch_distributed_zero_first
 
 
 # BaseTrainer python usage
@@ -18,7 +21,7 @@ class ClassificationTrainer(BaseTrainer):
     def get_dataset(self):
         # temporary solution. Replace with new ultralytics.yolo.ClassificationDataset module
         data = Path("datasets") / self.data
-        with utils.torch_distributed_zero_first(utils.LOCAL_RANK), utils.WorkingDirectory(Path.cwd()):
+        with torch_distributed_zero_first(LOCAL_RANK), WorkingDirectory(Path.cwd()):
             data_dir = data if data.is_dir() else (Path.cwd() / data)
             if not data_dir.is_dir():
                 self.console.info(f'\nDataset not found ⚠️, missing path {data_dir}, attempting download...')
@@ -27,7 +30,7 @@ class ClassificationTrainer(BaseTrainer):
                     subprocess.run(f"bash {v8.ROOT / 'data/scripts/get_imagenet.sh'}", shell=True, check=True)
                 else:
                     url = f'https://github.com/ultralytics/yolov5/releases/download/v1.0/{self.data}.zip'
-                    utils.download(url, dir=data_dir.parent)
+                    download(url, dir=data_dir.parent)
                 # TODO: add colorstr
                 s = f"Dataset download success ✅ ({time.time() - t:.1f}s), saved to {'bold', data_dir}\n"
                 self.console.info(s)