Shorten module paths with new 'nn' dir (#96)
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
GitHub
0
ultralytics/nn/__init__.py
Normal file
0
ultralytics/nn/__init__.py
Normal file
333
ultralytics/nn/autobackend.py
Normal file
333
ultralytics/nn/autobackend.py
Normal file
@ -0,0 +1,333 @@
|
||||
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.files import yaml_load
|
||||
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
|
||||
|
||||
super().__init__()
|
||||
w = str(weights[0] if isinstance(weights, list) else weights)
|
||||
nn_module = isinstance(weights, torch.nn.Module)
|
||||
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 or nn_module # 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 or nn_module):
|
||||
w = attempt_download(w) # download if not local
|
||||
|
||||
# NOTE: special case: in-memory pytorch model
|
||||
if nn_module:
|
||||
model = weights.to(device)
|
||||
model = model.fuse() if fuse else model
|
||||
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 pt: # PyTorch
|
||||
from ultralytics.nn.tasks import attempt_load_weights
|
||||
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 # noqa
|
||||
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 or self.nn_module: # 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, self.nn_module
|
||||
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 ultralytics.yolo.engine.exporter import export_formats
|
||||
sf = list(export_formats().Suffix) # export suffixes
|
||||
if not is_url(p, check=False) and not isinstance(p, str):
|
||||
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.files 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
|
||||
682
ultralytics/nn/modules.py
Normal file
682
ultralytics/nn/modules.py
Normal file
@ -0,0 +1,682 @@
|
||||
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
||||
"""
|
||||
Common modules
|
||||
"""
|
||||
|
||||
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.nn.autobackend import AutoBackend
|
||||
from ultralytics.yolo.data.augment import LetterBox
|
||||
from ultralytics.yolo.utils import LOGGER, colorstr
|
||||
from ultralytics.yolo.utils.files import increment_path
|
||||
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.tal import dist2bbox, make_anchors
|
||||
from ultralytics.yolo.utils.torch_utils import copy_attr, smart_inference_mode
|
||||
|
||||
# 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 ConvTranspose(nn.Module):
|
||||
# Convolution transpose 2d layer
|
||||
default_act = nn.SiLU() # default activation
|
||||
|
||||
def __init__(self, c1, c2, k=2, s=2, p=0, bn=True, act=True):
|
||||
super().__init__()
|
||||
self.conv_transpose = nn.ConvTranspose2d(c1, c2, k, s, p, bias=not bn)
|
||||
self.bn = nn.BatchNorm2d(c2) if bn else nn.Identity()
|
||||
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_transpose(x)))
|
||||
|
||||
|
||||
class DFL(nn.Module):
|
||||
# DFL module
|
||||
def __init__(self, c1=16):
|
||||
super().__init__()
|
||||
self.conv = nn.Conv2d(c1, 1, 1, bias=False).requires_grad_(False)
|
||||
x = torch.arange(c1, dtype=torch.float)
|
||||
self.conv.weight.data[:] = nn.Parameter(x.view(1, c1, 1, 1))
|
||||
self.c1 = c1
|
||||
|
||||
def forward(self, x):
|
||||
b, c, a = x.shape # batch, channels, anchors
|
||||
return self.conv(x.view(b, 4, self.c1, a).transpose(2, 1).softmax(1)).view(b, 4, a)
|
||||
# return self.conv(x.view(b, self.c1, 4, a).softmax(1)).view(b, 4, a)
|
||||
|
||||
|
||||
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, k=(3, 3), e=0.5): # ch_in, ch_out, shortcut, kernels, groups, expand
|
||||
super().__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, k[0], 1)
|
||||
self.cv2 = Conv(c_, c2, k[1], 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 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 C2(nn.Module):
|
||||
# CSP Bottleneck with 2 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__()
|
||||
self.c = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, 2 * self.c, 1, 1)
|
||||
self.cv2 = Conv(2 * self.c, c2, 1) # optional act=FReLU(c2)
|
||||
# self.attention = ChannelAttention(2 * self.c) # or SpatialAttention()
|
||||
self.m = nn.Sequential(*(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n)))
|
||||
|
||||
def forward(self, x):
|
||||
a, b = self.cv1(x).split((self.c, self.c), 1)
|
||||
return self.cv2(torch.cat((self.m(a), b), 1))
|
||||
|
||||
|
||||
class C2f(nn.Module):
|
||||
# CSP Bottleneck with 2 convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
self.c = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, 2 * self.c, 1, 1)
|
||||
self.cv2 = Conv((2 + n) * self.c, c2, 1) # optional act=FReLU(c2)
|
||||
self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))
|
||||
|
||||
def forward(self, x):
|
||||
y = list(self.cv1(x).split((self.c, self.c), 1))
|
||||
y.extend(m(y[-1]) for m in self.m)
|
||||
return self.cv2(torch.cat(y, 1))
|
||||
|
||||
|
||||
class ChannelAttention(nn.Module):
|
||||
# Channel-attention module https://github.com/open-mmlab/mmdetection/tree/v3.0.0rc1/configs/rtmdet
|
||||
def __init__(self, channels: int) -> None:
|
||||
super().__init__()
|
||||
self.pool = nn.AdaptiveAvgPool2d(1)
|
||||
self.fc = nn.Conv2d(channels, channels, 1, 1, 0, bias=True)
|
||||
self.act = nn.Sigmoid()
|
||||
|
||||
def forward(self, x: torch.Tensor) -> torch.Tensor:
|
||||
return x * self.act(self.fc(self.pool(x)))
|
||||
|
||||
|
||||
class SpatialAttention(nn.Module):
|
||||
# Spatial-attention module
|
||||
def __init__(self, kernel_size=7):
|
||||
super().__init__()
|
||||
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
|
||||
padding = 3 if kernel_size == 7 else 1
|
||||
self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
|
||||
self.act = nn.Sigmoid()
|
||||
|
||||
def forward(self, x):
|
||||
return x * self.act(self.cv1(torch.cat([torch.mean(x, 1, keepdim=True), torch.max(x, 1, keepdim=True)[0]], 1)))
|
||||
|
||||
|
||||
class CBAM(nn.Module):
|
||||
# CSP Bottleneck with 3 convolutions
|
||||
def __init__(self, c1, ratio=16, kernel_size=7): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
self.channel_attention = ChannelAttention(c1)
|
||||
self.spatial_attention = SpatialAttention(kernel_size)
|
||||
|
||||
def forward(self, x):
|
||||
return self.spatial_attention(self.channel_attention(x))
|
||||
|
||||
|
||||
class C1(nn.Module):
|
||||
# CSP Bottleneck with 3 convolutions
|
||||
def __init__(self, c1, c2, n=1): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super().__init__()
|
||||
self.cv1 = Conv(c1, c2, 1, 1)
|
||||
self.m = nn.Sequential(*(Conv(c2, c2, 3) for _ in range(n)))
|
||||
|
||||
def forward(self, x):
|
||||
y = self.cv1(x)
|
||||
return self.m(y) + y
|
||||
|
||||
|
||||
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)
|
||||
self.c_ = int(c2 * e)
|
||||
self.m = nn.Sequential(*(Bottleneck(self.c_, self.c_, shortcut, g, k=((1, 3), (3, 1)), e=1) 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 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 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
|
||||
dynamic = False # force grid reconstruction
|
||||
export = False # export mode
|
||||
shape = None
|
||||
anchors = torch.empty(0) # init
|
||||
strides = torch.empty(0) # init
|
||||
|
||||
def __init__(self, nc=80, ch=()): # detection layer
|
||||
super().__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.nl = len(ch) # number of detection layers
|
||||
self.reg_max = 16 # DFL channels (ch[0] // 16 to scale 4/8/12/16/20 for n/s/m/l/x)
|
||||
self.no = nc + self.reg_max * 4 # number of outputs per anchor
|
||||
self.stride = torch.zeros(self.nl) # strides computed during build
|
||||
|
||||
c2, c3 = max((16, ch[0] // 4, self.reg_max * 4)), max(ch[0], self.nc) # channels
|
||||
self.cv2 = nn.ModuleList(
|
||||
nn.Sequential(Conv(x, c2, 3), Conv(c2, c2, 3), nn.Conv2d(c2, 4 * self.reg_max, 1)) for x in ch)
|
||||
self.cv3 = nn.ModuleList(nn.Sequential(Conv(x, c3, 3), Conv(c3, c3, 3), nn.Conv2d(c3, self.nc, 1)) for x in ch)
|
||||
self.dfl = DFL(self.reg_max) if self.reg_max > 1 else nn.Identity()
|
||||
|
||||
def forward(self, x):
|
||||
shape = x[0].shape # BCHW
|
||||
for i in range(self.nl):
|
||||
x[i] = torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)
|
||||
box, cls = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2).split((self.reg_max * 4, self.nc), 1)
|
||||
if self.training:
|
||||
return x, box, cls
|
||||
elif self.dynamic or self.shape != shape:
|
||||
self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))
|
||||
self.shape = shape
|
||||
|
||||
dbox = dist2bbox(self.dfl(box), self.anchors.unsqueeze(0), xywh=True, dim=1) * self.strides
|
||||
y = torch.cat((dbox, cls.sigmoid()), 1)
|
||||
return y if self.export else (y, (x, box, cls))
|
||||
|
||||
def bias_init(self):
|
||||
# Initialize Detect() biases, WARNING: requires stride availability
|
||||
m = self # self.model[-1] # Detect() module
|
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1
|
||||
# ncf = math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # nominal class frequency
|
||||
for a, b, s in zip(m.cv2, m.cv3, m.stride): # from
|
||||
a[-1].bias.data[:] = 1.0 # box
|
||||
b[-1].bias.data[:m.nc] = math.log(5 / m.nc / (640 / s) ** 2) # cls (.01 objects, 80 classes, 640 img)
|
||||
|
||||
|
||||
class Segment(Detect):
|
||||
# YOLOv5 Segment head for segmentation models
|
||||
def __init__(self, nc=80, anchors=(), nm=32, npr=256, ch=()):
|
||||
super().__init__(nc, anchors, ch)
|
||||
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)))
|
||||
326
ultralytics/nn/tasks.py
Normal file
326
ultralytics/nn/tasks.py
Normal file
@ -0,0 +1,326 @@
|
||||
import contextlib
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
import thop
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torchvision
|
||||
import yaml
|
||||
|
||||
from ultralytics.nn.modules import (C1, C2, C3, C3TR, SPP, SPPF, Bottleneck, BottleneckCSP, C2f, C3Ghost, C3x, Classify,
|
||||
Concat, Conv, ConvTranspose, Detect, DWConv, DWConvTranspose2d, Ensemble, Focus,
|
||||
GhostBottleneck, GhostConv, Segment)
|
||||
from ultralytics.yolo.utils import LOGGER, colorstr
|
||||
from ultralytics.yolo.utils.torch_utils import (fuse_conv_and_bn, initialize_weights, intersect_state_dicts,
|
||||
make_divisible, 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, imgsz=640): # print model information
|
||||
model_info(self, verbose, imgsz)
|
||||
|
||||
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.anchors = fn(m.anchors)
|
||||
m.strides = fn(m.strides)
|
||||
return self
|
||||
|
||||
def load(self, weights):
|
||||
# Force all tasks to implement this function
|
||||
raise NotImplementedError("This function needs to be implemented by derived classes!")
|
||||
|
||||
|
||||
class DetectionModel(BaseModel):
|
||||
# YOLOv5 detection model
|
||||
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None): # model, input channels, number of classes
|
||||
super().__init__()
|
||||
if isinstance(cfg, dict):
|
||||
self.yaml = cfg # model dict
|
||||
else: # is *.yaml
|
||||
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
|
||||
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
|
||||
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, Detect)) else self.forward(x)
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
self.stride = m.stride
|
||||
m.bias_init() # 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
|
||||
|
||||
@staticmethod
|
||||
def _descale_pred(p, flips, scale, img_size, dim=1):
|
||||
# de-scale predictions following augmented inference (inverse operation)
|
||||
p[:, :4] /= scale # de-scale
|
||||
x, y, wh, cls = p.split((1, 1, 2, p.shape[dim] - 4), dim)
|
||||
if flips == 2:
|
||||
y = img_size[0] - y # de-flip ud
|
||||
elif flips == 3:
|
||||
x = img_size[1] - x # de-flip lr
|
||||
return torch.cat((x, y, wh, cls), dim)
|
||||
|
||||
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 load(self, weights):
|
||||
csd = weights['model'].float().state_dict() # checkpoint state_dict as FP32
|
||||
csd = intersect_state_dicts(csd, self.state_dict()) # intersect
|
||||
self.load_state_dict(csd, strict=False) # load
|
||||
LOGGER.info(f'Transferred {len(csd)}/{len(self.model.state_dict())} items from pretrained weights')
|
||||
|
||||
|
||||
class SegmentationModel(DetectionModel):
|
||||
# YOLOv5 segmentation model
|
||||
def __init__(self, cfg='yolov5s-seg.yaml', ch=3, nc=None):
|
||||
super().__init__(cfg, ch, nc)
|
||||
|
||||
|
||||
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
|
||||
from ultralytics.nn.autobackend import AutoBackend
|
||||
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):
|
||||
# TODO: Create a YOLOv5 classification model from a *.yaml file
|
||||
self.model = None
|
||||
|
||||
def load(self, weights):
|
||||
model = weights["model"] if isinstance(weights, dict) else weights # torchvision models are not dicts
|
||||
csd = model.float().state_dict()
|
||||
csd = intersect_state_dicts(csd, self.state_dict()) # intersect
|
||||
self.load_state_dict(csd, strict=False) # load
|
||||
|
||||
@staticmethod
|
||||
def reshape_outputs(model, nc):
|
||||
# Update a TorchVision classification model to class count 'n' if required
|
||||
name, m = list((model.model if hasattr(model, 'model') else model).named_children())[-1] # last module
|
||||
if isinstance(m, Classify): # YOLO Classify() head
|
||||
if m.linear.out_features != nc:
|
||||
m.linear = nn.Linear(m.linear.in_features, nc)
|
||||
elif isinstance(m, nn.Linear): # ResNet, EfficientNet
|
||||
if m.out_features != nc:
|
||||
setattr(model, name, nn.Linear(m.in_features, nc))
|
||||
elif isinstance(m, nn.Sequential):
|
||||
types = [type(x) for x in m]
|
||||
if nn.Linear in types:
|
||||
i = types.index(nn.Linear) # nn.Linear index
|
||||
if m[i].out_features != nc:
|
||||
m[i] = nn.Linear(m[i].in_features, nc)
|
||||
elif nn.Conv2d in types:
|
||||
i = types.index(nn.Conv2d) # nn.Conv2d index
|
||||
if m[i].out_channels != nc:
|
||||
m[i] = nn.Conv2d(m[i].in_channels, nc, m[i].kernel_size, m[i].stride, bias=m[i].bias is not None)
|
||||
|
||||
|
||||
# Functions ------------------------------------------------------------------------------------------------------------
|
||||
|
||||
|
||||
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
|
||||
from ultralytics.yolo.utils.downloads import attempt_download
|
||||
|
||||
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, Segment):
|
||||
m.inplace = inplace # torch 1.7.0 compatibility
|
||||
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':>20}{'n':>3}{'params':>10} {'module':<45}{'arguments':<30}")
|
||||
nc, gd, gw, act = 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
|
||||
no = nc + 4 # number of outputs = classes + box
|
||||
|
||||
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, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus, BottleneckCSP,
|
||||
C1, C2, C2f, C3, C3TR, 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, C1, C2, C2f, 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 m is Segment:
|
||||
args[3] = make_divisible(args[3] * gw, 8)
|
||||
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
|
||||
m.np = sum(x.numel() for x in m_.parameters()) # number params
|
||||
m_.i, m_.f, m_.type = i, f, t # attach index, 'from' index, type
|
||||
LOGGER.info(f'{i:>3}{str(f):>20}{n_:>3}{m.np:10.0f} {t:<45}{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 get_model(model='s.pt', pretrained=True):
|
||||
# Load a YOLO model locally, from torchvision, or from Ultralytics assets
|
||||
if model.endswith(".pt"):
|
||||
model = model.split(".")[0]
|
||||
|
||||
if Path(f"{model}.pt").is_file(): # local file
|
||||
return attempt_load_weights(f"{model}.pt", device='cpu')
|
||||
elif model in torchvision.models.__dict__: # TorchVision models i.e. resnet50, efficientnet_b0
|
||||
return torchvision.models.__dict__[model](weights='IMAGENET1K_V1' if pretrained else None)
|
||||
else: # Ultralytics assets
|
||||
return attempt_load_weights(f"{model}.pt", device='cpu')
|
||||
Reference in New Issue
Block a user