xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.47 Docker and reformat updates (#1153)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
2023-02-25 22:49:19 -08:00
committed by GitHub
parent d4be4cb24b
commit a58f766f94
41 changed files with 224 additions and 201 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/ci.yaml vendored
View File

@ -38,7 +38,7 @@ jobs:
if [ "${{ matrix.os }}" == "macos-latest" ]; then
pip install -e . coremltools openvino-dev tensorflow-macos --extra-index-url https://download.pytorch.org/whl/cpu
else
pip install -e . coremltools openvino-dev tensorflow-cpu paddlepaddle x2paddle --extra-index-url https://download.pytorch.org/whl/cpu
pip install -e . coremltools openvino-dev tensorflow-cpu --extra-index-url https://download.pytorch.org/whl/cpu
fi
yolo export format=tflite
- name: Check environment
@ -66,7 +66,7 @@ jobs:
shell: python
run: |
from ultralytics.yolo.utils.benchmarks import benchmark
benchmark(model='${{ matrix.model }}-cls.pt', imgsz=160, half=False, hard_fail=0.70)
benchmark(model='${{ matrix.model }}-cls.pt', imgsz=160, half=False, hard_fail=0.60)
- name: Benchmark Summary
run: cat benchmarks.log

9
README.zh-CN.md
View File

@ -223,10 +223,11 @@ Ultralytics [发布页](https://github.com/ultralytics/ultralytics/releases) 自
## <div align="center">License</div>
- YOLOv8 在两种不同的 License 下可用：
- **GPL-3.0 License**： 查看 [License](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) 文件的详细信息。
- **企业License**：在没有 GPL-3.0 开源要求的情况下为商业产品开发提供更大的灵活性。典型用例是将 Ultralytics 软件和 AI
模型嵌入到商业产品和应用程序中。在以下位置申请企业许可证 [Ultralytics 许可](https://ultralytics.com/license) 。
YOLOv8 在两种不同的 License 下可用：
- **GPL-3.0 License**： 查看 [License](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) 文件的详细信息。
- **企业License**：在没有 GPL-3.0 开源要求的情况下为商业产品开发提供更大的灵活性。典型用例是将 Ultralytics 软件和 AI
模型嵌入到商业产品和应用程序中。在以下位置申请企业许可证 [Ultralytics 许可](https://ultralytics.com/license) 。
## <div align="center">联系我们</div>

3
docker/Dockerfile
View File

@ -29,9 +29,8 @@ WORKDIR /usr/src/ultralytics
RUN git clone https://github.com/ultralytics/ultralytics /usr/src/ultralytics
# Install pip packages
COPY requirements.txt .
RUN python3 -m pip install --upgrade pip wheel
RUN pip install --no-cache ultralytics[export] albumentations comet gsutil notebook
RUN pip install --no-cache '.[export]' albumentations comet gsutil notebook
# Set environment variables
ENV OMP_NUM_THREADS=1

3
docker/Dockerfile-arm64
View File

@ -24,9 +24,8 @@ WORKDIR /usr/src/ultralytics
RUN git clone https://github.com/ultralytics/ultralytics /usr/src/ultralytics
# Install pip packages
COPY requirements.txt .
RUN python3 -m pip install --upgrade pip wheel
RUN pip install --no-cache ultralytics albumentations gsutil notebook
RUN pip install --no-cache . albumentations gsutil notebook
# Cleanup
ENV DEBIAN_FRONTEND teletype

3
docker/Dockerfile-cpu
View File

@ -24,9 +24,8 @@ WORKDIR /usr/src/ultralytics
RUN git clone https://github.com/ultralytics/ultralytics /usr/src/ultralytics
# Install pip packages
COPY requirements.txt .
RUN python3 -m pip install --upgrade pip wheel
RUN pip install --no-cache ultralytics[export] albumentations gsutil notebook \
RUN pip install --no-cache '.[export]' albumentations gsutil notebook \
--extra-index-url https://download.pytorch.org/whl/cpu
# Cleanup

4
docs/predict.md
View File

@ -97,8 +97,8 @@ Class reference documentation for `Results` module and its components can be fou
## Plotting results
You can use `plot()` function of `Result` object to plot results on in image object. It plots all components(boxes, masks,
classification logits, etc) found in the results object
You can use `plot()` function of `Result` object to plot results on in image object. It plots all components(boxes,
masks, classification logits, etc) found in the results object
```python
res = model(img)

17
docs/tasks/tracking.md
View File

@ -42,11 +42,15 @@ Use a trained YOLOv8n/YOLOv8n-seg model to run tracker on video streams.
```
As in the above usage, we support both the detection and segmentation models for tracking and the only thing you need to do is loading the corresponding(detection or segmentation) model.
As in the above usage, we support both the detection and segmentation models for tracking and the only thing you need to
do is loading the corresponding (detection or segmentation) model.
## Configuration
### Tracking
Tracking shares the configuration with predict, i.e `conf`, `iou`, `show`. More configurations please refer to [predict page](https://docs.ultralytics.com/cfg/#prediction).
Tracking shares the configuration with predict, i.e `conf`, `iou`, `show`. More configurations please refer
to [predict page](https://docs.ultralytics.com/cfg/#prediction).
!!! example ""
=== "Python"
@ -65,7 +69,10 @@ Tracking shares the configuration with predict, i.e `conf`, `iou`, `show`. More
```
### Tracker
We also support using a modified tracker config file, just copy a config file i.e `custom_tracker.yaml` from [ultralytics/tracker/cfg](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/tracker/cfg) and modify any configurations(expect the `tracker_type`) you need to.
We also support using a modified tracker config file, just copy a config file i.e `custom_tracker.yaml`
from [ultralytics/tracker/cfg](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/tracker/cfg) and modify
any configurations(expect the `tracker_type`) you need to.
!!! example ""
=== "Python"
@ -82,5 +89,7 @@ We also support using a modified tracker config file, just copy a config file i.
yolo track model=yolov8n.pt source="https://youtu.be/Zgi9g1ksQHc" tracker='custom_tracker.yaml'
```
Please refer to [ultralytics/tracker/cfg](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/tracker/cfg) page.
Please refer to [ultralytics/tracker/cfg](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/tracker/cfg)
page.

1
requirements.txt
View File

@ -37,7 +37,6 @@ seaborn>=0.11.0
# Extras --------------------------------------
psutil # system utilization
thop>=0.1.1 # FLOPs computation
wheel>=0.38.0 # Snyk vulnerability fix
# ipython # interactive notebook
# albumentations>=1.0.3
# pycocotools>=2.0.6 # COCO mAP

12
setup.cfg
View File

@ -25,17 +25,19 @@ verbose = 2
# https://pep8.readthedocs.io/en/latest/intro.html#error-codes
format = pylint
# see: https://www.flake8rules.com/
ignore = E731,F405,E402,F401,W504,E127,E231,E501,F403
ignore = E731,F405,E402,W504,E501
# E731: Do not assign a lambda expression, use a def
# F405: name may be undefined, or defined from star imports: module
# E402: module level import not at top of file
# F401: module imported but unused
# W504: line break after binary operator
# E127: continuation line over-indented for visual indent
# E231: missing whitespace after ‘,’, ‘;’, or ‘:’
# E501: line too long
# removed:
# F401: module imported but unused
# E231: missing whitespace after ‘,’, ‘;’, or ‘:’
# E127: continuation line over-indented for visual indent
# F403: ‘from module import *’ used; unable to detect undefined names
[isort]
# https://pycqa.github.io/isort/docs/configuration/options.html
line_length = 120
@ -48,7 +50,7 @@ spaces_before_comment = 2
COLUMN_LIMIT = 120
COALESCE_BRACKETS = True
SPACES_AROUND_POWER_OPERATOR = True
SPACE_BETWEEN_ENDING_COMMA_AND_CLOSING_BRACKET = False
SPACE_BETWEEN_ENDING_COMMA_AND_CLOSING_BRACKET = True
SPLIT_BEFORE_CLOSING_BRACKET = False
SPLIT_BEFORE_FIRST_ARGUMENT = False
# EACH_DICT_ENTRY_ON_SEPARATE_LINE = False

2
setup.py
View File

@ -59,7 +59,7 @@ setup(
'Topic :: Scientific/Engineering :: Image Recognition',
'Operating System :: POSIX :: Linux',
'Operating System :: MacOS',
'Operating System :: Microsoft :: Windows',],
'Operating System :: Microsoft :: Windows', ],
keywords='machine-learning, deep-learning, vision, ML, DL, AI, YOLO, YOLOv3, YOLOv5, YOLOv8, HUB, Ultralytics',
entry_points={
'console_scripts': ['yolo = ultralytics.yolo.cfg:entrypoint', 'ultralytics = ultralytics.yolo.cfg:entrypoint']})

4
tests/test_cli.py
View File

@ -22,7 +22,7 @@ def test_special_modes():
# Train checks ---------------------------------------------------------------------------------------------------------
def test_train_det():
run(f'yolo train detect model={CFG}.yaml data=coco8.yaml imgsz=32 epochs=1')
run(f'yolo train detect model={CFG}.yaml data=coco8.yaml imgsz=32 epochs=1 v5loader')
def test_train_seg():
@ -48,7 +48,7 @@ def test_val_classify():
# Predict checks -------------------------------------------------------------------------------------------------------
def test_predict_detect():
run(f"yolo predict model={MODEL}.pt source={ROOT / 'assets'} imgsz=32 save")
run(f"yolo predict model={MODEL}.pt source={ROOT / 'assets'} imgsz=32 save save_crop save_txt")
if checks.check_online():
run(f'yolo predict model={MODEL}.pt source=https://ultralytics.com/images/bus.jpg imgsz=32')
run(f'yolo predict model={MODEL}.pt source=https://ultralytics.com/assets/decelera_landscape_min.mov imgsz=32')

5
tests/test_python.py
View File

@ -162,9 +162,8 @@ def test_workflow():
def test_predict_callback_and_setup():
def on_predict_batch_end(predictor):
# results -> List[batch_size]
# test callback addition for prediction
def on_predict_batch_end(predictor): # results -> List[batch_size]
path, _, im0s, _, _ = predictor.batch
# print('on_predict_batch_end', im0s[0].shape)
im0s = im0s if isinstance(im0s, list) else [im0s]

4
ultralytics/__init__.py
View File

@ -1,8 +1,8 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
__version__ = '8.0.46'
__version__ = '8.0.47'
from ultralytics.yolo.engine.model import YOLO
from ultralytics.yolo.utils.checks import check_yolo as checks
__all__ = ['__version__', 'YOLO', 'checks'] # allow simpler import
__all__ = '__version__', 'YOLO', 'checks' # allow simpler import

11
ultralytics/hub/utils.py
View File

@ -154,11 +154,12 @@ class Traces:
'python': platform.python_version(),
'release': __version__,
'environment': ENVIRONMENT}
self.enabled = SETTINGS['sync'] and \
RANK in {-1, 0} and \
check_online() and \
not TESTS_RUNNING and \
(is_pip_package() or get_git_origin_url() == 'https://github.com/ultralytics/ultralytics.git')
self.enabled = \
SETTINGS['sync'] and \
RANK in {-1, 0} and \
check_online() and \
not TESTS_RUNNING and \
(is_pip_package() or get_git_origin_url() == 'https://github.com/ultralytics/ultralytics.git')
def __call__(self, cfg, all_keys=False, traces_sample_rate=1.0):
"""

26
ultralytics/nn/autobackend.py
View File

@ -136,7 +136,7 @@ class AutoBackend(nn.Module):
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
executable_network = ie.compile_model(network, device_name='CPU') # device_name="MYRIAD" for NCS2
elif engine: # TensorRT
LOGGER.info(f'Loading {w} for TensorRT inference...')
import tensorrt as trt # https://developer.nvidia.com/nvidia-tensorrt-download
@ -176,6 +176,8 @@ class AutoBackend(nn.Module):
LOGGER.info(f'Loading {w} for CoreML inference...')
import coremltools as ct
model = ct.models.MLModel(w)
names, stride, task = (model.user_defined_metadata.get(k) for k in ('names', 'stride', 'task'))
names, stride = eval(names), int(stride)
elif saved_model: # TF SavedModel
LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
import tensorflow as tf
@ -185,18 +187,13 @@ class AutoBackend(nn.Module):
LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
import tensorflow as tf
from ultralytics.yolo.engine.exporter import gd_outputs
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())
@ -319,10 +316,17 @@ class AutoBackend(nn.Module):
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[0].cpu().numpy()
if self.task == 'classify':
from ultralytics.yolo.data.utils import IMAGENET_MEAN, IMAGENET_STD
# im_pil = Image.fromarray(((im / 6 + 0.5) * 255).astype('uint8'))
for i in range(3):
im[..., i] *= IMAGENET_STD[i]
im[..., i] += IMAGENET_MEAN[i]
im_pil = Image.fromarray((im * 255).astype('uint8'))
# im = im.resize((192, 320), Image.ANTIALIAS)
y = self.model.predict({'image': im}) # coordinates are xywh normalized
y = self.model.predict({'image': im_pil}) # 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)

41
ultralytics/nn/tasks.py
View File

@ -11,7 +11,7 @@ import torch.nn as nn
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 DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, RANK, colorstr, yaml_load
from ultralytics.yolo.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, RANK, colorstr, emojis, yaml_load
from ultralytics.yolo.utils.checks import check_requirements, check_yaml
from ultralytics.yolo.utils.torch_utils import (fuse_conv_and_bn, fuse_deconv_and_bn, initialize_weights,
intersect_dicts, make_divisible, model_info, scale_img, time_sync)
@ -76,7 +76,7 @@ class BaseModel(nn.Module):
None
"""
c = m == self.model[-1] # is final layer, copy input as inplace fix
o = thop.profile(m, inputs=(x.clone() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
o = thop.profile(m, inputs=[x.clone() if c else x], verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
t = time_sync()
for _ in range(10):
m(x.clone() if c else x)
@ -339,14 +339,20 @@ def torch_safe_load(weight):
file = attempt_download_asset(weight) # search online if missing locally
try:
return torch.load(file, map_location='cpu'), file # load
except ModuleNotFoundError as e:
if e.name == 'omegaconf': # e.name is missing module name
LOGGER.warning(f'WARNING ⚠️ {weight} requires {e.name}, which is not in ultralytics requirements.'
f'\nAutoInstall will run now for {e.name} but this feature will be removed in the future.'
f'\nRecommend fixes are to train a new model using updated ultralytics package or to '
f'download updated models from https://github.com/ultralytics/assets/releases/tag/v0.0.0')
if e.name != 'models':
check_requirements(e.name) # install missing module
except ModuleNotFoundError as e: # e.name is missing module name
if e.name == 'models':
raise TypeError(
emojis(f'ERROR ❌️ {weight} appears to be an Ultralytics YOLOv5 model originally trained '
f'with https://github.com/ultralytics/yolov5.\nThis model is NOT forwards compatible with '
f'YOLOv8 at https://github.com/ultralytics/ultralytics.'
f"\nRecommend fixes are to train a new model using the latest 'ultralytics' package or to "
f"run a command with an official YOLOv8 model, i.e. 'yolo predict model=yolov8n.pt'")) from e
LOGGER.warning(f"WARNING ⚠️ {weight} appears to require '{e.name}', which is not in ultralytics requirements."
f"\nAutoInstall will run now for '{e.name}' but this feature will be removed in the future."
f"\nRecommend fixes are to train a new model using the latest 'ultralytics' package or to "
f"run a command with an official YOLOv8 model, i.e. 'yolo predict model=yolov8n.pt'")
check_requirements(e.name) # install missing module
return torch.load(file, map_location='cpu'), file # load
@ -437,22 +443,21 @@ def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)
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 {
Classify, Conv, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus,
BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
if m in (Classify, 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 != nc: # if c2 not equal to number of classes (i.e. for Classify() output)
c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]
if m in {BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, C3x}:
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)
elif m in {Detect, Segment}:
elif m in (Detect, Segment):
args.append([ch[x] for x in f])
if m is Segment:
args[2] = make_divisible(args[2] * gw, 8)
@ -490,11 +495,11 @@ def guess_model_task(model):
def cfg2task(cfg):
# Guess from YAML dictionary
m = cfg['head'][-1][-2].lower() # output module name
if m in ['classify', 'classifier', 'cls', 'fc']:
if m in ('classify', 'classifier', 'cls', 'fc'):
return 'classify'
if m in ['detect']:
if m == 'detect':
return 'detect'
if m in ['segment']:
if m == 'segment':
return 'segment'
# Guess from model cfg

2
ultralytics/tracker/__init__.py
View File

@ -2,3 +2,5 @@
from .track import register_tracker
from .trackers import BOTSORT, BYTETracker
__all__ = 'register_tracker', 'BOTSORT', 'BYTETracker' # allow simpler import

2
ultralytics/tracker/trackers/__init__.py
View File

@ -2,3 +2,5 @@
from .bot_sort import BOTSORT
from .byte_tracker import BYTETracker
__all__ = 'BOTSORT', 'BYTETracker' # allow simpler import

2
ultralytics/tracker/utils/gmc.py
View File

@ -213,7 +213,7 @@ class GMC:
prev_pt = np.array(self.prevKeyPoints[m.queryIdx].pt, dtype=np.int_)
curr_pt = np.array(keypoints[m.trainIdx].pt, dtype=np.int_)
curr_pt[0] += W
color = np.random.randint(0, 255, (3,))
color = np.random.randint(0, 255, 3)
color = (int(color[0]), int(color[1]), int(color[2]))
matches_img = cv2.line(matches_img, prev_pt, curr_pt, tuple(color), 1, cv2.LINE_AA)

2
ultralytics/yolo/__init__.py
View File

@ -2,4 +2,4 @@
from . import v8
__all__ = ['v8']
__all__ = 'v8', # tuple or list

17
ultralytics/yolo/cfg/__init__.py
View File

@ -269,6 +269,11 @@ def entrypoint(debug=''):
checks.check_yolo()
return
# Task
task = overrides.get('task')
if task and task not in TASKS:
raise ValueError(f"Invalid 'task={task}'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}")
# Model
model = overrides.pop('model', DEFAULT_CFG.model)
if model is None:
@ -276,15 +281,11 @@ def entrypoint(debug=''):
LOGGER.warning(f"WARNING ⚠️ 'model' is missing. Using default 'model={model}'.")
from ultralytics.yolo.engine.model import YOLO
overrides['model'] = model
model = YOLO(model)
model = YOLO(model, task=task)
# Task
task = overrides.get('task', model.task)
if task is not None:
if task not in TASKS:
raise ValueError(f"Invalid 'task={task}'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}")
else:
model.task = task
# Task Update
task = task or model.task
overrides['task'] = task
# Mode
if mode in {'predict', 'track'} and 'source' not in overrides:

11
ultralytics/yolo/data/__init__.py
View File

@ -5,12 +5,5 @@ from .build import build_classification_dataloader, build_dataloader, load_infer
from .dataset import ClassificationDataset, SemanticDataset, YOLODataset
from .dataset_wrappers import MixAndRectDataset
__all__ = [
'BaseDataset',
'ClassificationDataset',
'MixAndRectDataset',
'SemanticDataset',
'YOLODataset',
'build_classification_dataloader',
'build_dataloader',
'load_inference_source',]
__all__ = ('BaseDataset', 'ClassificationDataset', 'MixAndRectDataset', 'SemanticDataset', 'YOLODataset',
'build_classification_dataloader', 'build_dataloader', 'load_inference_source')

10
ultralytics/yolo/data/augment.py
View File

@ -564,7 +564,7 @@ class Albumentations:
A.CLAHE(p=0.01),
A.RandomBrightnessContrast(p=0.0),
A.RandomGamma(p=0.0),
A.ImageCompression(quality_lower=75, p=0.0),] # transforms
A.ImageCompression(quality_lower=75, p=0.0)] # transforms
self.transform = A.Compose(T, bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
LOGGER.info(prefix + ', '.join(f'{x}'.replace('always_apply=False, ', '') for x in T if x.p))
@ -671,14 +671,14 @@ def v8_transforms(dataset, imgsz, hyp):
shear=hyp.shear,
perspective=hyp.perspective,
pre_transform=LetterBox(new_shape=(imgsz, imgsz)),
),])
)])
return Compose([
pre_transform,
MixUp(dataset, pre_transform=pre_transform, p=hyp.mixup),
Albumentations(p=1.0),
RandomHSV(hgain=hyp.hsv_h, sgain=hyp.hsv_s, vgain=hyp.hsv_v),
RandomFlip(direction='vertical', p=hyp.flipud),
RandomFlip(direction='horizontal', p=hyp.fliplr),]) # transforms
RandomFlip(direction='horizontal', p=hyp.fliplr)]) # transforms
# Classification augmentations -----------------------------------------------------------------------------------------
@ -719,8 +719,8 @@ def classify_albumentations(
if vflip > 0:
T += [A.VerticalFlip(p=vflip)]
if jitter > 0:
color_jitter = (float(jitter),) * 3 # repeat value for brightness, contrast, saturation, 0 hue
T += [A.ColorJitter(*color_jitter, 0)]
jitter = float(jitter)
T += [A.ColorJitter(jitter, jitter, jitter, 0)] # brightness, contrast, saturation, 0 hue
else: # Use fixed crop for eval set (reproducibility)
T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)]
T += [A.Normalize(mean=mean, std=std), ToTensorV2()] # Normalize and convert to Tensor

26
ultralytics/yolo/data/base.py
View File

@ -24,20 +24,18 @@ class BaseDataset(Dataset):
label_path (str): label path, this can also be an ann_file or other custom label path.
"""
def __init__(
self,
img_path,
imgsz=640,
cache=False,
augment=True,
hyp=None,
prefix='',
rect=False,
batch_size=None,
stride=32,
pad=0.5,
single_cls=False,
):
def __init__(self,
img_path,
imgsz=640,
cache=False,
augment=True,
hyp=None,
prefix='',
rect=False,
batch_size=None,
stride=32,
pad=0.5,
single_cls=False):
super().__init__()
self.img_path = img_path
self.imgsz = imgsz

4
ultralytics/yolo/data/dataloaders/v5augmentations.py
View File

@ -335,8 +335,8 @@ def classify_albumentations(
if vflip > 0:
T += [A.VerticalFlip(p=vflip)]
if jitter > 0:
color_jitter = (float(jitter),) * 3 # repeat value for brightness, contrast, satuaration, 0 hue
T += [A.ColorJitter(*color_jitter, 0)]
jitter = float(jitter)
T += [A.ColorJitter(jitter, jitter, jitter, 0)] # brightness, contrast, satuaration, 0 hue
else: # Use fixed crop for eval set (reproducibility)
T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)]
T += [A.Normalize(mean=mean, std=std), ToTensorV2()] # Normalize and convert to Tensor

7
ultralytics/yolo/data/dataset.py
View File

@ -4,13 +4,16 @@ from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path
import cv2
import numpy as np
import torch
import torchvision
from tqdm import tqdm
from ..utils import NUM_THREADS, TQDM_BAR_FORMAT, is_dir_writeable
from .augment import *
from .augment import Compose, Format, Instances, LetterBox, classify_albumentations, classify_transforms, v8_transforms
from .base import BaseDataset
from .utils import HELP_URL, LOCAL_RANK, get_hash, img2label_paths, verify_image_label
from .utils import HELP_URL, LOCAL_RANK, LOGGER, get_hash, img2label_paths, verify_image_label
class YOLODataset(BaseDataset):

117
ultralytics/yolo/engine/exporter.py
View File

@ -50,7 +50,6 @@ TensorFlow.js:
import json
import os
import platform
import re
import subprocess
import time
import warnings
@ -90,9 +89,9 @@ def export_formats():
['TensorFlow SavedModel', 'saved_model', '_saved_model', True, True],
['TensorFlow GraphDef', 'pb', '.pb', True, True],
['TensorFlow Lite', 'tflite', '.tflite', True, False],
['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite', False, False],
['TensorFlow.js', 'tfjs', '_web_model', False, False],
['PaddlePaddle', 'paddle', '_paddle_model', True, True],]
['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite', True, False],
['TensorFlow.js', 'tfjs', '_web_model', True, False],
['PaddlePaddle', 'paddle', '_paddle_model', True, True], ]
return pd.DataFrame(x, columns=['Format', 'Argument', 'Suffix', 'CPU', 'GPU'])
@ -100,6 +99,15 @@ EXPORT_FORMATS_LIST = list(export_formats()['Argument'][1:])
EXPORT_FORMATS_TABLE = str(export_formats())
def gd_outputs(gd):
# TensorFlow GraphDef model output node names
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'))
def try_export(inner_func):
# YOLOv8 export decorator, i..e @try_export
inner_args = get_default_args(inner_func)
@ -164,10 +172,10 @@ class Exporter:
# Checks
model.names = check_class_names(model.names)
self.imgsz = check_imgsz(self.args.imgsz, stride=model.stride, min_dim=2) # check image size
if model.task == 'classify':
self.args.nms = self.args.agnostic_nms = False
if self.args.optimize:
assert self.device.type == 'cpu', '--optimize not compatible with cuda devices, i.e. use --device cpu'
if edgetpu and not LINUX:
raise SystemError('Edge TPU export only supported on Linux. See https://coral.ai/docs/edgetpu/compiler/')
# Input
im = torch.zeros(self.args.batch, 3, *self.imgsz).to(self.device)
@ -208,7 +216,7 @@ class Exporter:
self.file = file
self.output_shape = tuple(y.shape) if isinstance(y, torch.Tensor) else tuple(tuple(x.shape) for x in y)
self.pretty_name = self.file.stem.replace('yolo', 'YOLO')
description = f'Ultralytics {self.pretty_name} model' + f'trained on {Path(self.args.data).name}' \
description = f'Ultralytics {self.pretty_name} model ' + f'trained on {Path(self.args.data).name}' \
if self.args.data else '(untrained)'
self.metadata = {
'description': description,
@ -239,8 +247,7 @@ class Exporter:
'Please consider contributing to the effort if you have TF expertise. Thank you!')
nms = False
self.args.int8 |= edgetpu
f[5], s_model = self._export_saved_model(nms=nms or self.args.agnostic_nms or tfjs,
agnostic_nms=self.args.agnostic_nms or tfjs)
f[5], s_model = self._export_saved_model()
if pb or tfjs: # pb prerequisite to tfjs
f[6], _ = self._export_pb(s_model)
if tflite:
@ -386,7 +393,7 @@ class Exporter:
check_requirements('coremltools>=6.0')
import coremltools as ct # noqa
class iOSModel(torch.nn.Module):
class iOSDetectModel(torch.nn.Module):
# Wrap an Ultralytics YOLO model for iOS export
def __init__(self, model, im):
super().__init__()
@ -405,29 +412,36 @@ class Exporter:
LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...')
f = self.file.with_suffix('.mlmodel')
bias = [0.0, 0.0, 0.0]
scale = 1 / 255
classifier_config = None
if self.model.task == 'classify':
bias = [-x for x in IMAGENET_MEAN]
scale = 1 / 255 / (sum(IMAGENET_STD) / 3)
classifier_config = ct.ClassifierConfig(list(self.model.names.values())) if self.args.nms else None
else:
bias = [0.0, 0.0, 0.0]
scale = 1 / 255
classifier_config = None
model = iOSModel(self.model, self.im).eval() if self.args.nms else self.model
ts = torch.jit.trace(model, self.im, strict=False) # TorchScript model
model = self.model
elif self.model.task == 'detect':
model = iOSDetectModel(self.model, self.im) if self.args.nms else self.model
elif self.model.task == 'segment':
# TODO CoreML Segmentation model pipelining
model = self.model
ts = torch.jit.trace(model.eval(), self.im, strict=False) # TorchScript model
ct_model = ct.convert(ts,
inputs=[ct.ImageType('image', shape=self.im.shape, scale=scale, bias=bias)],
classifier_config=classifier_config)
bits, mode = (8, 'kmeans_lut') if self.args.int8 else (16, 'linear') if self.args.half else (32, None)
if bits < 32:
ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
if self.args.nms:
if self.args.nms and self.model.task == 'detect':
ct_model = self._pipeline_coreml(ct_model)
ct_model.short_description = self.metadata['description']
ct_model.author = self.metadata['author']
ct_model.license = self.metadata['license']
ct_model.version = self.metadata['version']
m = self.metadata # metadata dict
ct_model.short_description = m['description']
ct_model.author = m['author']
ct_model.license = m['license']
ct_model.version = m['version']
ct_model.user_defined_metadata.update({k: str(v) for k, v in m.items() if k in ('stride', 'task', 'names')})
ct_model.save(str(f))
return f, ct_model
@ -497,14 +511,7 @@ class Exporter:
return f, None
@try_export
def _export_saved_model(self,
nms=False,
agnostic_nms=False,
topk_per_class=100,
topk_all=100,
iou_thres=0.45,
conf_thres=0.25,
prefix=colorstr('TensorFlow SavedModel:')):
def _export_saved_model(self, prefix=colorstr('TensorFlow SavedModel:')):
# YOLOv8 TensorFlow SavedModel export
try:
@ -562,6 +569,9 @@ class Exporter:
@try_export
def _export_tflite(self, keras_model, nms, agnostic_nms, prefix=colorstr('TensorFlow Lite:')):
# YOLOv8 TensorFlow Lite export
import tensorflow as tf # noqa
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
saved_model = Path(str(self.file).replace(self.file.suffix, '_saved_model'))
if self.args.int8:
f = saved_model / (self.file.stem + 'yolov8n_integer_quant.tflite') # fp32 in/out
@ -572,9 +582,6 @@ class Exporter:
return str(f), None # noqa
# OLD VERSION BELOW ---------------------------------------------------------------
import tensorflow as tf # noqa
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
batch_size, ch, *imgsz = list(self.im.shape) # BCHW
f = str(self.file).replace(self.file.suffix, '-fp16.tflite')
@ -619,7 +626,9 @@ class Exporter:
LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}')
sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0 # sudo installed on system
for c in (
'curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -',
# 'curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -', # errors
'wget --no-check-certificate -q -O - https://packages.cloud.google.com/apt/doc/apt-key.gpg | '
'sudo apt-key add -',
'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | ' # no comma
'sudo tee /etc/apt/sources.list.d/coral-edgetpu.list',
'sudo apt-get update',
@ -639,30 +648,36 @@ class Exporter:
def _export_tfjs(self, prefix=colorstr('TensorFlow.js:')):
# YOLOv8 TensorFlow.js export
check_requirements('tensorflowjs')
import tensorflow as tf
import tensorflowjs as tfjs # noqa
LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...')
f = str(self.file).replace(self.file.suffix, '_web_model') # js dir
f_pb = self.file.with_suffix('.pb') # *.pb path
f_json = Path(f) / 'model.json' # *.json path
cmd = f'tensorflowjs_converter --input_format=tf_frozen_model ' \
f'--output_node_names=Identity,Identity_1,Identity_2,Identity_3 {f_pb} {f}'
gd = tf.Graph().as_graph_def() # TF GraphDef
with open(f_pb, 'rb') as file:
gd.ParseFromString(file.read())
outputs = ','.join(gd_outputs(gd))
LOGGER.info(f'\n{prefix} output node names: {outputs}')
cmd = f'tensorflowjs_converter --input_format=tf_frozen_model --output_node_names={outputs} {f_pb} {f}'
subprocess.run(cmd.split(), check=True)
with open(f_json, 'w') as j: # sort JSON Identity_* in ascending order
subst = re.sub(
r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
r'"Identity.?.?": {"name": "Identity.?.?"}, '
r'"Identity.?.?": {"name": "Identity.?.?"}, '
r'"Identity.?.?": {"name": "Identity.?.?"}}}',
r'{"outputs": {"Identity": {"name": "Identity"}, '
r'"Identity_1": {"name": "Identity_1"}, '
r'"Identity_2": {"name": "Identity_2"}, '
r'"Identity_3": {"name": "Identity_3"}}}',
f_json.read_text(),
)
j.write(subst)
# f_json = Path(f) / 'model.json' # *.json path
# with open(f_json, 'w') as j: # sort JSON Identity_* in ascending order
# subst = re.sub(
# r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
# r'"Identity.?.?": {"name": "Identity.?.?"}, '
# r'"Identity.?.?": {"name": "Identity.?.?"}, '
# r'"Identity.?.?": {"name": "Identity.?.?"}}}',
# r'{"outputs": {"Identity": {"name": "Identity"}, '
# r'"Identity_1": {"name": "Identity_1"}, '
# r'"Identity_2": {"name": "Identity_2"}, '
# r'"Identity_3": {"name": "Identity_3"}}}',
# f_json.read_text(),
# )
# j.write(subst)
yaml_save(Path(f) / 'metadata.yaml', self.metadata) # add metadata.yaml
return f, None
@ -680,7 +695,7 @@ class Exporter:
model_meta.license = self.metadata['license']
# Label file
tmp_file = file.parent / 'temp_meta.txt'
tmp_file = Path(file).parent / 'temp_meta.txt'
with open(tmp_file, 'w') as f:
f.write(str(self.metadata))
@ -718,7 +733,7 @@ class Exporter:
b.Finish(model_meta.Pack(b), _metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
metadata_buf = b.Output()
populator = _metadata.MetadataPopulator.with_model_file(file)
populator = _metadata.MetadataPopulator.with_model_file(str(file))
populator.load_metadata_buffer(metadata_buf)
populator.load_associated_files([str(tmp_file)])
populator.populate()

17
ultralytics/yolo/engine/model.py
View File

@ -2,7 +2,6 @@
import sys
from pathlib import Path
from typing import List
from ultralytics import yolo # noqa
from ultralytics.nn.tasks import (ClassificationModel, DetectionModel, SegmentationModel, attempt_load_one_weight,
@ -68,7 +67,7 @@ class YOLO:
list(ultralytics.yolo.engine.results.Results): The prediction results.
"""
def __init__(self, model='yolov8n.pt') -> None:
def __init__(self, model='yolov8n.pt', task=None) -> None:
"""
Initializes the YOLO model.
@ -91,9 +90,9 @@ class YOLO:
if not suffix and Path(model).stem in GITHUB_ASSET_STEMS:
model, suffix = Path(model).with_suffix('.pt'), '.pt' # add suffix, i.e. yolov8n -> yolov8n.pt
if suffix == '.yaml':
self._new(model)
self._new(model, task)
else:
self._load(model)
self._load(model, task)
def __call__(self, source=None, stream=False, **kwargs):
return self.predict(source, stream, **kwargs)
@ -102,17 +101,18 @@ class YOLO:
name = self.__class__.__name__
raise AttributeError(f"'{name}' object has no attribute '{attr}'. See valid attributes below.\n{self.__doc__}")
def _new(self, cfg: str, verbose=True):
def _new(self, cfg: str, task=None, verbose=True):
"""
Initializes a new model and infers the task type from the model definitions.
Args:
cfg (str): model configuration file
task (str) or (None): model task
verbose (bool): display model info on load
"""
self.cfg = check_yaml(cfg) # check YAML
cfg_dict = yaml_load(self.cfg, append_filename=True) # model dict
self.task = guess_model_task(cfg_dict)
self.task = task or guess_model_task(cfg_dict)
self.model = TASK_MAP[self.task][0](cfg_dict, verbose=verbose and RANK == -1) # build model
self.overrides['model'] = self.cfg
@ -121,12 +121,13 @@ class YOLO:
self.model.args = {k: v for k, v in args.items() if k in DEFAULT_CFG_KEYS} # attach args to model
self.model.task = self.task
def _load(self, weights: str, task=''):
def _load(self, weights: str, task=None):
"""
Initializes a new model and infers the task type from the model head.
Args:
weights (str): model checkpoint to be loaded
task (str) or (None): model task
"""
suffix = Path(weights).suffix
if suffix == '.pt':
@ -137,7 +138,7 @@ class YOLO:
else:
weights = check_file(weights)
self.model, self.ckpt = weights, None
self.task = guess_model_task(weights)
self.task = task or guess_model_task(weights)
self.ckpt_path = weights
self.overrides['model'] = weights

1
ultralytics/yolo/engine/predictor.py
View File

@ -32,7 +32,6 @@ from collections import defaultdict
from pathlib import Path
import cv2
import torch
from ultralytics.nn.autobackend import AutoBackend
from ultralytics.yolo.cfg import get_cfg

2
ultralytics/yolo/engine/trainer.py
View File

@ -242,7 +242,7 @@ class BaseTrainer:
metric_keys = self.validator.metrics.keys + self.label_loss_items(prefix='val')
self.metrics = dict(zip(metric_keys, [0] * len(metric_keys))) # TODO: init metrics for plot_results()?
self.ema = ModelEMA(self.model)
if self.args.plots:
if self.args.plots and not self.args.v5loader:
self.plot_training_labels()
self.resume_training(ckpt)
self.scheduler.last_epoch = self.start_epoch - 1 # do not move

4
ultralytics/yolo/utils/__init__.py
View File

@ -18,7 +18,6 @@ from typing import Union
import cv2
import numpy as np
import pandas as pd
import requests
import torch
import yaml
@ -517,10 +516,7 @@ def set_sentry():
((is_pip_package() and not is_git_dir()) or
(get_git_origin_url() == 'https://github.com/ultralytics/ultralytics.git' and get_git_branch() == 'main')):
import hashlib
import sentry_sdk # noqa
sentry_sdk.init(
dsn='https://f805855f03bb4363bc1e16cb7d87b654@o4504521589325824.ingest.sentry.io/4504521592406016',
debug=False,

25
ultralytics/yolo/utils/benchmarks.py
View File

@ -30,14 +30,14 @@ import pandas as pd
from ultralytics import YOLO
from ultralytics.yolo.engine.exporter import export_formats
from ultralytics.yolo.utils import LOGGER, ROOT, SETTINGS
from ultralytics.yolo.utils import LINUX, LOGGER, ROOT, SETTINGS
from ultralytics.yolo.utils.checks import check_yolo
from ultralytics.yolo.utils.downloads import download
from ultralytics.yolo.utils.files import file_size
from ultralytics.yolo.utils.torch_utils import select_device
def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt', imgsz=160, half=False, device='cpu', hard_fail=0.30):
def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt', imgsz=160, half=False, device='cpu', hard_fail=False):
device = select_device(device, verbose=False)
if isinstance(model, (str, Path)):
model = YOLO(model)
@ -45,11 +45,10 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt', imgsz=160, hal
y = []
t0 = time.time()
for i, (name, format, suffix, cpu, gpu) in export_formats().iterrows(): # index, (name, format, suffix, CPU, GPU)
emoji = '❌' # indicates export failure
try:
assert i not in (9, 10), 'inference not supported' # Edge TPU and TF.js are unsupported
assert i != 5 or platform.system() == 'Darwin', 'inference only supported on macOS>=10.13' # CoreML
assert i != 11 or model.task != 'classify', 'paddle-classify bug'
assert i != 11, 'paddle exports coming soon'
assert i != 9 or LINUX, 'Edge TPU export only supported on Linux'
if 'cpu' in device.type:
assert cpu, 'inference not supported on CPU'
if 'cuda' in device.type:
@ -61,13 +60,16 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt', imgsz=160, hal
export = model # PyTorch format
else:
filename = model.export(imgsz=imgsz, format=format, half=half, device=device) # all others
export = YOLO(filename)
export = YOLO(filename, task=model.task)
assert suffix in str(filename), 'export failed'
emoji = '❎' # indicates export succeeded
# Predict
assert i not in (9, 10), 'inference not supported' # Edge TPU and TF.js are unsupported
assert i != 5 or platform.system() == 'Darwin', 'inference only supported on macOS>=10.13' # CoreML
if not (ROOT / 'assets/bus.jpg').exists():
download(url='https://ultralytics.com/images/bus.jpg', dir=ROOT / 'assets')
export.predict(ROOT / 'assets/bus.jpg', imgsz=imgsz, device=device, half=half) # test
export.predict(ROOT / 'assets/bus.jpg', imgsz=imgsz, device=device, half=half)
# Validate
if model.task == 'detect':
@ -84,17 +86,16 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt', imgsz=160, hal
if hard_fail:
assert type(e) is AssertionError, f'Benchmark hard_fail for {name}: {e}'
LOGGER.warning(f'ERROR ❌️ Benchmark failure for {name}: {e}')
y.append([name, '❌', None, None, None]) # mAP, t_inference
y.append([name, emoji, None, None, None]) # mAP, t_inference
# Print results
check_yolo(device=device) # print system info
c = ['Format', 'Status❔', 'Size (MB)', key, 'Inference time (ms/im)']
df = pd.DataFrame(y, columns=c)
df = pd.DataFrame(y, columns=['Format', 'Status❔', 'Size (MB)', key, 'Inference time (ms/im)'])
name = Path(model.ckpt_path).name
s = f'\nBenchmarks complete for {name} on {data} at imgsz={imgsz} ({time.time() - t0:.2f}s)\n{df}\n'
LOGGER.info(s)
with open('benchmarks.log', 'a') as f:
with open('benchmarks.log', 'a', errors='ignore', encoding='utf-8') as f:
f.write(s)
if hard_fail and isinstance(hard_fail, float):

4
ultralytics/yolo/utils/callbacks/__init__.py
View File

@ -1,5 +1,3 @@
from .base import add_integration_callbacks, default_callbacks
__all__ = [
'add_integration_callbacks',
'default_callbacks',]
__all__ = 'add_integration_callbacks', 'default_callbacks'

3
ultralytics/yolo/utils/checks.py
View File

@ -137,7 +137,6 @@ def check_latest_pypi_version(package_name='ultralytics'):
def check_pip_update():
from ultralytics import __version__
latest = check_latest_pypi_version()
latest = '9.0.0'
if pkg.parse_version(__version__) < pkg.parse_version(latest):
LOGGER.info(f'New https://pypi.org/project/ultralytics/{latest} available 😃 '
f"Update with 'pip install -U ultralytics'")
@ -239,7 +238,7 @@ def check_requirements(requirements=ROOT.parent / 'requirements.txt', exclude=()
LOGGER.warning(f'{prefix} ❌ {e}')
def check_suffix(file='yolov8n.pt', suffix=('.pt',), msg=''):
def check_suffix(file='yolov8n.pt', suffix='.pt', msg=''):
# Check file(s) for acceptable suffix
if file and suffix:
if isinstance(suffix, str):

5
ultralytics/yolo/utils/instance.py
View File

@ -10,9 +10,8 @@ import numpy as np
from .ops import ltwh2xywh, ltwh2xyxy, resample_segments, xywh2ltwh, xywh2xyxy, xyxy2ltwh, xyxy2xywh
# From PyTorch internals
def _ntuple(n):
# From PyTorch internals
def parse(x):
return x if isinstance(x, abc.Iterable) else tuple(repeat(x, n))
@ -26,7 +25,7 @@ to_4tuple = _ntuple(4)
# `ltwh` means left top and width, height(coco format)
_formats = ['xyxy', 'xywh', 'ltwh']
__all__ = ['Bboxes']
__all__ = 'Bboxes', # tuple or list
class Bboxes:

3
ultralytics/yolo/utils/plotting.py
View File

@ -207,8 +207,7 @@ def plot_labels(boxes, cls, names=(), save_dir=Path('')):
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
b = xyxy2xywh(xyxy.view(-1, 4)) # 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

4
ultralytics/yolo/utils/torch_utils.py
View File

@ -195,7 +195,7 @@ def get_flops(model, imgsz=640):
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
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
flops = flops * imgsz[0] / stride * imgsz[1] / stride # 640x640 GFLOPs
return flops
@ -374,7 +374,7 @@ def profile(input, ops, n=10, device=None):
m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m
tf, tb, t = 0, 0, [0, 0, 0] # dt forward, backward
try:
flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # GFLOPs
flops = thop.profile(m, inputs=[x], verbose=False)[0] / 1E9 * 2 # GFLOPs
except Exception:
flops = 0

2
ultralytics/yolo/v8/__init__.py
View File

@ -2,4 +2,4 @@
from ultralytics.yolo.v8 import classify, detect, segment
__all__ = ['classify', 'segment', 'detect']
__all__ = 'classify', 'segment', 'detect'

2
ultralytics/yolo/v8/classify/__init__.py
View File

@ -4,4 +4,4 @@ from ultralytics.yolo.v8.classify.predict import ClassificationPredictor, predic
from ultralytics.yolo.v8.classify.train import ClassificationTrainer, train
from ultralytics.yolo.v8.classify.val import ClassificationValidator, val
__all__ = ['ClassificationPredictor', 'predict', 'ClassificationTrainer', 'train', 'ClassificationValidator', 'val']
__all__ = 'ClassificationPredictor', 'predict', 'ClassificationTrainer', 'train', 'ClassificationValidator', 'val'

2
ultralytics/yolo/v8/detect/__init__.py
View File

@ -4,4 +4,4 @@ from .predict import DetectionPredictor, predict
from .train import DetectionTrainer, train
from .val import DetectionValidator, val
__all__ = ['DetectionPredictor', 'predict', 'DetectionTrainer', 'train', 'DetectionValidator', 'val']
__all__ = 'DetectionPredictor', 'predict', 'DetectionTrainer', 'train', 'DetectionValidator', 'val'

2
ultralytics/yolo/v8/segment/__init__.py
View File

@ -4,4 +4,4 @@ from .predict import SegmentationPredictor, predict
from .train import SegmentationTrainer, train
from .val import SegmentationValidator, val
__all__ = ['SegmentationPredictor', 'predict', 'SegmentationTrainer', 'train', 'SegmentationValidator', 'val']
__all__ = 'SegmentationPredictor', 'predict', 'SegmentationTrainer', 'train', 'SegmentationValidator', 'val'