v6.2 - YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai integrations #8996

glenn-jocher · 2022-08-17T10:26:06Z

glenn-jocher
Aug 17, 2022
Maintainer

This release incorporates 401 PRs from 41 contributors since our last release in February 2022. It adds Classification training, validation, prediction and export (to all 11 formats), and also provides ImageNet-pretrained YOLOv5m-cls, ResNet (18, 34, 50, 101) and EfficientNet (b0-b3) models.

My main goal with this release is to introduce super simple YOLOv5 classification workflows just like our existing object detection models. The new v6.2 YOLOv5-cls models below are just a start, we will continue to improve these going forward together with our existing detection models. We'd love your contributions on this effort!

Our next release, v6.3 is scheduled for September and will bring official instance segmentation support to YOLOv5, with a major v7.0 release later this year updating architectures across all 3 tasks - classification, detection and segmentation.

Important Updates

Classification Models ⭐ NEW: YOLOv5-cls ImageNet-pretrained classification models are now available for the first time (New YOLOv5 Classification Models #8956 by @glenn-jocher)
ClearML logging ⭐ NEW: Integration with the open-source experiment tracker ClearML. Installing with pip install clearml will enable the integration and allow users to track every training run in ClearML. This in turn allows users to track and compare runs and even schedule runs remotely. (ClearML experiment tracking integration #8620 by @thepycoder)
Deci.ai optimization ⭐ NEW: Automatically compile and quantize YOLOv5 for better inference performance in one click at Deci (New YOLOv5 Classification Models #8956 by @glenn-jocher).
GPU Export Benchmarks: Benchmark (mAP and speed) all YOLOv5 export formats with python utils/benchmarks.py --weights yolov5s.pt --device 0 for GPU benchmarks or --device cpu for CPU benchmarks (YOLOv5 Export Benchmarks for GPU #6963 by @glenn-jocher).
Training Reproducibility: Single-GPU YOLOv5 training with torch>=1.12.0 is now fully reproducible, and a new --seed argument can be used (default seed=0) (Training reproducibility improvements #8213 by @AyushExel).
Apple Metal Performance Shader (MPS) Support: MPS support for Apple M1/M2 devices with --device mps (full functionality is pending torch updates in General MPS op coverage tracking issue pytorch/pytorch#77764) (YOLOv5 Apple Metal Performance Shader (MPS) support #7878 by @glenn-jocher)

New Classification Checkpoints

We trained YOLOv5-cls classification models on ImageNet for 90 epochs using a 4xA100 instance, and we trained ResNet and EfficientNet models alongside with the same default training settings to compare. We exported all models to ONNX FP32 for CPU speed tests and to TensorRT FP16 for GPU speed tests. We ran all speed tests on Google Colab Pro for easy reproducibility.

Model	size ^(pixels)	accuracy ^top1	accuracy ^top5	Train time ^{90 epochs 4x A100 (hours)}	Speed ^{ONNX-CPU (ms)}	Speed ^{TensorRT-V100 (ms)}	params ^(M)	FLOPs ^{@224 (B)}
YOLOv5n-cls	224	64.6	85.4	7:59	3.3	0.5	2.5	0.5
YOLOv5s-cls	224	71.5	90.2	8:09	6.6	0.6	5.4	1.4
YOLOv5m-cls	224	75.9	92.9	10:06	15.5	0.9	12.9	3.9
YOLOv5l-cls	224	78.0	94.0	11:56	26.9	1.4	26.5	8.5
YOLOv5x-cls	224	79.0	94.4	15:04	54.3	1.8	48.1	15.9

ResNet18	224	70.3	89.5	6:47	11.2	0.5	11.7	3.7
ResNet34	224	73.9	91.8	8:33	20.6	0.9	21.8	7.4
ResNet50	224	76.8	93.4	11:10	23.4	1.0	25.6	8.5
ResNet101	224	78.5	94.3	17:10	42.1	1.9	44.5	15.9

EfficientNet_b0	224	75.1	92.4	13:03	12.5	1.3	5.3	1.0
EfficientNet_b1	224	76.4	93.2	17:04	14.9	1.6	7.8	1.5
EfficientNet_b2	224	76.6	93.4	17:10	15.9	1.6	9.1	1.7
EfficientNet_b3	224	77.7	94.0	19:19	18.9	1.9	12.2	2.4

All checkpoints are trained to 90 epochs with SGD optimizer with lr0=0.001 and weight_decay=5e-5 at image size 224 and all default settings.
Runs logged to https://wandb.ai/glenn-jocher/YOLOv5-Classifier-v6-2
Accuracy values are for single-model single-scale on ImageNet-1k dataset.
Reproduce by python classify/val.py --data ../datasets/imagenet --img 224
Speed averaged over 100 inference images using a Colab Pro V100 High-RAM instance.
Reproduce by python classify/val.py --data ../datasets/imagenet --img 224 --batch 1
Export to ONNX at FP32 and TensorRT at FP16 done with export.py.
Reproduce by python export.py --weights yolov5s-cls.pt --include engine onnx --imgsz 224

New Classification Model Usage Examples

Train

YOLOv5 classification training supports auto-download of MNIST, Fashion-MNIST, CIFAR10, CIFAR100, Imagenette, Imagewoof, and ImageNet datasets with the --data argument. To start training on MNIST for example use --data mnist.

# Single-GPU
python classify/train.py --model yolov5s-cls.pt --data cifar100 --epochs 5 --img 224 --batch 128

# Multi-GPU DDP
python -m torch.distributed.run --nproc_per_node 4 --master_port 1 classify/train.py --model yolov5s-cls.pt --data imagenet --epochs 5 --img 224 --device 0,1,2,3

Val

Validate YOLOv5m-cls accuracy on ImageNet-1k dataset:

bash data/scripts/get_imagenet.sh --val  # download ImageNet val split (6.3G, 50000 images)
python classify/val.py --weights yolov5m-cls.pt --data ../datasets/imagenet --img 224  # validate

Predict

Use pretrained YOLOv5s-cls.pt to predict bus.jpg:

python classify/predict.py --weights yolov5s-cls.pt --data data/images/bus.jpg

model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s-cls.pt')  # load from PyTorch Hub

Export

Export a group of trained YOLOv5s-cls, ResNet and EfficientNet models to ONNX and TensorRT:

python export.py --weights yolov5s-cls.pt resnet50.pt efficientnet_b0.pt --include onnx engine --img 224

Changelog

Changes between previous release and this release: v6.1...v6.2
Changes since this release: v6.2...HEAD

🛠️ New Features and Bug Fixes (401)

Pre-commit table fix by @glenn-jocher in Pre-commit table fix #6744
Update tutorial.ipynb (2 CPUs, 12.7 GB RAM, 42.2/166.8 GB disk) by @glenn-jocher in Update tutorial.ipynb (2 CPUs, 12.7 GB RAM, 42.2/166.8 GB disk) #6767
Update min warmup iterations from 1k to 100 by @glenn-jocher in Update min warmup iterations from 1k to 100 #6768
Default OMP_NUM_THREADS=8 by @glenn-jocher in Default OMP_NUM_THREADS=8 #6770
Update tutorial.ipynb by @glenn-jocher in Update tutorial.ipynb #6771
Update hyp.VOC.yaml by @glenn-jocher in Update hyp.VOC.yaml #6772
Fix export for 1-channel images by @lcombaldieu in Fix export for 1-channel images #6780
Update EMA decay tau by @glenn-jocher in Update EMA decay tau #6769
YOLOv5s6 params FLOPs fix by @glenn-jocher in YOLOv5s6 params FLOPs fix #6782
Update PULL_REQUEST_TEMPLATE.md by @glenn-jocher in Update PULL_REQUEST_TEMPLATE.md #6783
Update autoanchor.py by @glenn-jocher in Update autoanchor.py #6794
Update sweep.yaml by @lcombaldieu in Update sweep.yaml #6825
AutoAnchor improved initialization robustness by @glenn-jocher in AutoAnchor improved initialization robustness #6854
Add *.ts to VID_FORMATS by @glenn-jocher in Add *.ts to VID_FORMATS #6859
Update --cache disk deprecate *_npy/ dirs by @glenn-jocher in Update --cache disk deprecate *_npy/ dirs #6876
Update yolov5s.yaml by @vnekat in Update yolov5s.yaml #6865
Default FP16 TensorRT export by @DavidBaldsiefen in Default FP16 TensorRT export #6798
Bump actions/setup-python from 2 to 3 by @dependabot in Bump actions/setup-python from 2 to 3 #6880
Bump actions/checkout from 2 to 3 by @dependabot in Bump actions/checkout from 2 to 3 #6881
Fix TRT max_workspace_size deprecation notice by @glenn-jocher in Fix TRT max_workspace_size deprecation notice #6856
Update bytes to GB with bit shift by @glenn-jocher in Update bytes to GB with bit shift #6886
Move git_describe() to general.py by @glenn-jocher in Move git_describe() to general.py #6918
PyTorch 1.11.0 compatibility updates by @glenn-jocher in PyTorch 1.11.0 compatibility updates #6932
Optimize PyTorch 1.11.0 compatibility update by @glenn-jocher in Optimize PyTorch 1.11.0 compatibility update #6933
Allow 3-point segments by @glenn-jocher in Allow 3-point segments #6938
Fix PyTorch Hub export inference shapes by @glenn-jocher in Fix PyTorch Hub export inference shapes #6949
DetectMultiBackend() --half handling by @glenn-jocher in DetectMultiBackend() --half handling #6945
Update Dockerfile torch==1.11.0+cu113 by @glenn-jocher in Update Dockerfile torch==1.11.0+cu113 #6954
New val.py cuda variable by @glenn-jocher in New val.py cuda variable #6957
DetectMultiBackend() return device update by @glenn-jocher in DetectMultiBackend() return device update #6958
Tensor initialization on device improvements by @glenn-jocher in Tensor initialization on device improvements #6959
EdgeTPU optimizations by @paradigmn in EdgeTPU optimizations #6808
Model ema key backward compatibility fix by @glenn-jocher in Model ema key backward compatibility fix #6972
YOLOv5 Export Benchmarks for GPU by @glenn-jocher in YOLOv5 Export Benchmarks for GPU #6963
Update TQDM bar format by @glenn-jocher in Update TQDM bar format #6988
Conditional Timeout() by OS (disable on Windows) by @glenn-jocher in Conditional Timeout() by OS (disable on Windows) #7013
fix: add default PIL font as fallback by @maxstrobel in fix: add default PIL font as fallback #7010
Consistent saved_model output format by @MrinalJain17 in Consistent saved_model output format #7032
ComputeLoss() indexing/speed improvements by @glenn-jocher in ComputeLoss() indexing/speed improvements #7048
Update Dockerfile to git clone instead of COPY by @glenn-jocher in Update Dockerfile to git clone instead of COPY #7053
Create SECURITY.md by @glenn-jocher in Create SECURITY.md #7054
Fix incomplete URL substring sanitation by @glenn-jocher in Fix incomplete URL substring sanitation #7056
Use PIL to eliminate chroma subsampling in crops by @LaserBorg in Use PIL to eliminate chroma subsampling in crops #7008
Fix check_anchor_order() in pixel-space not grid-space by @glenn-jocher in Fix check_anchor_order() in pixel-space not grid-space #7060
Update detect.py non-inplace with y.tensor_split() by @glenn-jocher in Update detect.py non-inplace with y.tensor_split() #7062
Update common.py lists for tuples by @glenn-jocher in Update common.py lists for tuples #7063
Update W&B message to LOGGER.info() by @glenn-jocher in Update W&B message to LOGGER.info() #7064
Update init.py by @glenn-jocher in Update __init__.py #7065
Add non-zero da check_anchor_order() condition by @glenn-jocher in Add non-zero da check_anchor_order() condition #7066
Fix2 check_anchor_order() in pixel-space not grid-space by @glenn-jocher in Fix2 check_anchor_order() in pixel-space not grid-space #7067
Revert "Update detect.py non-inplace with y.tensor_split()" by @glenn-jocher in Revert "Update detect.py non-inplace with y.tensor_split()" #7074
Update loss.py with if self.gr < 1: by @glenn-jocher in Update loss.py with if self.gr < 1: #7087
Update loss for FP16 tobj by @glenn-jocher in Update loss for FP16 tobj #7088
Display model name in model summary by @glenn-jocher in Display model name in model summary #7101
torch.split() 1.7.0 compatibility fix by @glenn-jocher in torch.split() 1.7.0 compatibility fix #7102
Update benchmarks significant digits by @glenn-jocher in Update benchmarks significant digits #7103
Model summary pathlib fix by @glenn-jocher in Model summary pathlib fix #7104
Remove named arguments where possible by @glenn-jocher in Remove named arguments where possible #7105
Multi-threaded VisDrone and VOC downloads by @glenn-jocher in Multi-threaded VisDrone and VOC downloads #7108
np.fromfile() Chinese image paths fix by @yeshanliu in np.fromfile() Chinese image paths fix #6979
Add PyTorch Hub results.save(labels=False) option by @glenn-jocher in Add PyTorch Hub results.save(labels=False) option #7129
Fix cv2.imwrite on non-ASCII paths by @CCRcmcpe in Fix cv2.imwrite on non-ASCII paths #7139
Fix detect.py --view-img for non-ASCII paths by @Zengyf-CVer in Fix detect.py --view-img for non-ASCII paths #7093
Add Architecture Summary to README Tutorials by @glenn-jocher in Add Architecture Summary to README Tutorials #7146
Adjust NMS time limit warning to batch size by @glenn-jocher in Adjust NMS time limit warning to batch size #7156
Sidestep os.path.relpath() Windows bug by @glenn-jocher in Sidestep os.path.relpath() Windows bug #7158
NMS unused variable fix by @glenn-jocher in NMS unused variable fix #7161
yolo.py --profile updates by @glenn-jocher in yolo.py --profile updates #7170
Revert C3() change by @glenn-jocher in Revert C3() change #7172
Bump actions/cache from 2.1.7 to 3 by @dependabot in Bump actions/cache from 2.1.7 to 3 #7175
yolo.py profiling updates by @glenn-jocher in yolo.py profiling updates #7178
Update tutorial.ipynb by @glenn-jocher in Update tutorial.ipynb #7212
ENV OMP_NUM_THREADS=8 by @glenn-jocher in ENV OMP_NUM_THREADS=8 #7215
Add train.py --name cfg option by @glenn-jocher in Add train.py --name cfg option #7202
precommit: yapf by @Borda in precommit: yapf #5494
CLI fire prep updates by @glenn-jocher in CLI fire prep updates #7229
Update .pre-commit-config.yaml by @glenn-jocher in Update .pre-commit-config.yaml #7230
SavedModel TF Serve Fix by @glenn-jocher in SavedModel TF Serve Fix #7228
Create CODE_OF_CONDUCT.md by @glenn-jocher in Create CODE_OF_CONDUCT.md #7233
Fix www.youtube.com hostname by @glenn-jocher in Fix www.youtube.com hostname #7242
Update minimum Python>=3.7.0 by @glenn-jocher in Update minimum Python>=3.7.0 #7247
Update setup.cfg to description_file field by @glenn-jocher in Update setup.cfg to description_file field #7248
Update tutorial.ipynb by @glenn-jocher in Update tutorial.ipynb #7254
Update tutorial.ipynb by @glenn-jocher in Update tutorial.ipynb #7255
Fix Flask REST API by @Zengyf-CVer in Fix Flask REST API #7210
Export with official nn.SiLU() by @glenn-jocher in Export with official nn.SiLU() #7256
Refactor out-of-place Detect() for reduced ops by @glenn-jocher in Refactor out-of-place Detect() for reduced ops #7257
torch.split() replace slicing on out-of-place inference by @glenn-jocher in torch.split() replace slicing on out-of-place inference #7258
Export single output only by @glenn-jocher in Export single output only #7259
TorchScript single-output fix by @glenn-jocher in TorchScript single-output fix #7261
Integrate offset into grid by @glenn-jocher in Integrate offset into grid #7262
[pre-commit.ci] pre-commit suggestions by @pre-commit-ci in [pre-commit.ci] pre-commit suggestions #7279
Update Dockerfile by @glenn-jocher in Update Dockerfile #7282
Enable TensorFlow ops for --nms and --agnostic-nms by @leeflix in Enable TensorFlow ops for --nms and --agnostic-nms #7281
Update cv2.imread() patch with flags argument by @glenn-jocher in Update cv2.imread() patch with flags argument #7287
Context manager open(file) as f fixes by @glenn-jocher in Context manager open(file) as f fixes #7289
val.py --weights and --data compatibility check by @glenn-jocher in val.py --weights and --data compatibility check #7292
Add dataset sizes (zipped) by @glenn-jocher in Add dataset sizes (zipped) #7293
Add check_requirements(('pycocotools>=2.0',)) by @glenn-jocher in Add check_requirements(('pycocotools>=2.0',)) #7295
fix: disable usage of root logger by @maxstrobel in fix: disable usage of root logger #7296
Update export.py by @glenn-jocher in Update export.py #7301
Use tqdm.auto by @glenn-jocher in Use tqdm.auto #7311
Add retry=3 to download() by @glenn-jocher in Add retry=3 to download() #7313
Add callbacks by @glenn-jocher in Add callbacks #7315
Copy wandb param dict before training to avoid overwrites. by @n1mmy in Copy wandb param dict before training to avoid overwrites. #7317
Update Objects365.yaml by @glenn-jocher in Update Objects365.yaml #7323
Fix TF export for BottleneckCSP layer by @nrupatunga in Fix TF export for BottleneckCSP layer #7330
Objects365 images GB vs zips GB by @glenn-jocher in Objects365 images GB vs zips GB #7335
Simplify callbacks.py return by @glenn-jocher in Simplify callbacks.py return #7333
Print dataset scan only if RANK in (-1, 0) by @glenn-jocher in Print dataset scan only if RANK in (-1, 0) #7337
Update _make_grid() to model dtype by @glenn-jocher in Update _make_grid() to model dtype #7346
Rename 'MacOS' to 'macOS' by @glenn-jocher in Rename 'MacOS' to 'macOS' #7349
Add python benchmarks.py --test for export-only by @glenn-jocher in Add python benchmarks.py --test for export-only #7350
Add ONNX export metadata by @glenn-jocher in Add ONNX export metadata #7353
DetectMultiBackend() default stride=32 by @rglkt in DetectMultiBackend() default stride=32 #7342
Loss and IoU speed improvements by @glenn-jocher in Loss and IoU speed improvements #7361
Swap unsafe_chunk() for chunk() by @glenn-jocher in Swap unsafe_chunk() for chunk() #7362
Delete FUNDING.yml by @glenn-jocher in Delete FUNDING.yml #7363
Replace Slack with Community Forum in issues by @glenn-jocher in Replace Slack with Community Forum in issues #7364
Update ci-testing.yml by @glenn-jocher in Update ci-testing.yml #7365
Bump actions/stale from 4 to 5 by @dependabot in Bump actions/stale from 4 to 5 #7371
Update optimizer param group strategy by @glenn-jocher in Update optimizer param group strategy #7376
Add support for different normalization layers by @vardanagarwal in Add support for different normalization layers #7377
Dynamic normalization layer selection by @glenn-jocher in Dynamic normalization layer selection #7392
Add version warning for wandb by @AyushExel in Add version warning for wandb #7385
Remove OpenVINO ONNX opset<=12 check by @glenn-jocher in Remove OpenVINO ONNX opset<=12 check #7398
Fix EdgeTPU output directory by @glenn-jocher in Fix EdgeTPU output directory #7399
Update git_describe() by @glenn-jocher in Update git_describe() #7402
Remove tensorrt pip install check by @glenn-jocher in Remove tensorrt pip install check #7439
Disable pbar for DDP ranks > 0 by @glenn-jocher in Disable pbar for DDP ranks > 0 #7440
Add --half support for FP16 CoreML exports with by @Cedric-Perauer in Add --half support for FP16 CoreML exports with #7446
Bump cirrus-actions/rebase from 1.5 to 1.6 by @dependabot in Bump cirrus-actions/rebase from 1.5 to 1.6 #7462
Update val.py by @HERIUN in Update val.py #7478
Improved non-latin Annotator() plotting by @glenn-jocher in Improved non-latin Annotator() plotting #7488
check_fonts() download to CONFIG_DIR fix by @glenn-jocher in check_fonts() download to CONFIG_DIR fix #7489
Fix val.py Ensemble() by @glenn-jocher in Fix val.py Ensemble() #7490
Added YOLOv5_AUTOINSTALL environment variable by @jkocherhans in Added YOLOv5_AUTOINSTALL environment variable #7505
Refactor Dockerfiles to utils/docker by @glenn-jocher in Refactor Dockerfiles to utils/docker #7510
Add yesqa to precommit checks by @Zengyf-CVer in Add yesqa to precommit checks #7511
Fix val plots=plots by @glenn-jocher in Fix val plots=plots #7524
Reduce val device transfers by @glenn-jocher in Reduce val device transfers #7525
Add Docker --file argument to build by @glenn-jocher in Add Docker --file argument to build #7527
Empty val batch CUDA device fix by @glenn-jocher in Empty val batch CUDA device fix #7539
Autoinstall TensorRT if missing by @glenn-jocher in Autoinstall TensorRT if missing #7537
Add mdformat to precommit checks and update other version by @Zengyf-CVer in Add mdformat to precommit checks and update other version #7529
Update precommit monthly python 3.7+ by @glenn-jocher in Update precommit monthly python 3.7+ #7542
Update downloads.py current release by @Powercube7 in Update downloads.py current release #7541
Update check_requirements() with cmds=() argument by @glenn-jocher in Update check_requirements() with cmds=() argument #7543
Add --noplots flag to suppress figures and images logging by @AyushExel in Add --noplots flag to suppress figures and images logging #7534
Improve availability of YOLOv5 in Russia by @glenn-jocher in Improve availability of YOLOv5 in Russia #7545
Update restapi.py by @glenn-jocher in Update restapi.py #7309
Restrict TRT autoinstall to Linux-only by @glenn-jocher in Restrict TRT autoinstall to Linux-only #7549
PyTorch Hub _verbose=False fix2 by @glenn-jocher in PyTorch Hub _verbose=False fix2 #7550
Enable results.print() when _verbose=False by @glenn-jocher in Enable results.print() when _verbose=False #7558
Add print(results) override for PyTorch Hub results by @glenn-jocher in Add print(results) override for PyTorch Hub results #7559
TensorRT PyTorch Hub inference fix by @glenn-jocher in TensorRT PyTorch Hub inference fix #7560
Add PyTorch-only benchmark arg by @glenn-jocher in Add PyTorch-only benchmark arg #7564
Fix from yolov5 import utils statement by @Jack24658735 in Fix from yolov5 import utils statement #7578
Remove tqdm.auto by @glenn-jocher in Remove tqdm.auto #7599
Add --half support for OpenVINO exports by @djmmoss in Add --half support for OpenVINO exports #7615
increment_path() robustness improvements by @glenn-jocher in increment_path() robustness improvements #7628
Reduce opencv-python>=4.1.1 for Jetson Nano by @glenn-jocher in Reduce opencv-python>=4.1.1 for Jetson Nano #7645
Bump scipy>=1.5 to meet numpy constraints by @glenn-jocher in Bump scipy>=1.5 to meet numpy constraints #7646
Update plot.py by @sylvanding in Update plot.py #7654
Bump github/codeql-action from 1 to 2 by @dependabot in Bump github/codeql-action from 1 to 2 #7665
Disallow --dynamic when --half is passed by @dmatos2012 in Disallow --dynamic when --half is passed #7669
Update Dockerfile-cpu to force python3.9 by @glenn-jocher in Update Dockerfile-cpu to force python3.9 #7675
Pin Docker-cpu FROM ubuntu:20.04 by @glenn-jocher in Pin Docker-cpu FROM ubuntu:20.04 #7677
FROM nvcr.io/nvidia/pytorch:22.04-py3 by @glenn-jocher in FROM nvcr.io/nvidia/pytorch:22.04-py3 #7680
Update README.md by @glenn-jocher in Update README.md #7686
Update tutorial.ipynb by @glenn-jocher in Update tutorial.ipynb #7715
Update on_train_end callback by @glenn-jocher in Update on_train_end callback #7716
Report fused model summary by default by @glenn-jocher in Report fused model summary by default #7722
Ability to download older assets by @CristiFati in Ability to download older assets #7767
Pin downloads to release version by @glenn-jocher in Pin downloads to release version #7790
Implement DDP static_graph=True by @glenn-jocher in Implement DDP static_graph=True #6940
Add smoothing to curve plots and max F1 index by @glenn-jocher in Add smoothing to curve plots and max F1 index #7798
Add Dockerfile-M1 by @glenn-jocher in Add Dockerfile-M1 #7720
Add random interpolation method augmentation by @developer0hye in Add random interpolation method augmentation #6826
Rename utils/datasets.py -> utils/dataloaders.py by @glenn-jocher in Rename utils/datasets.py -> utils/dataloaders.py #7799
Add @threaded decorator by @glenn-jocher in Add @threaded decorator #7813
Add Python version output by @glenn-jocher in Add Python version output #7814
Refactor collections and fstrings by @glenn-jocher in Refactor collections and fstrings #7821
Refactor modules by @glenn-jocher in Refactor modules #7823
YOLOv5 OpenVINO PyTorch Hub inference fix by @glenn-jocher in YOLOv5 OpenVINO PyTorch Hub inference fix #7826
New TensorFlow TFDWConv() module by @glenn-jocher in New TensorFlow TFDWConv() module #7824
Bump cirrus-actions/rebase from 1.6 to 1.7 by @dependabot in Bump cirrus-actions/rebase from 1.6 to 1.7 #7831
New TensorFlow TFCrossConv() module by @glenn-jocher in New TensorFlow TFCrossConv() module #7827
Fix TFDWConv() c1 == c2 check by @glenn-jocher in Fix TFDWConv() c1 == c2 check #7842
Replace openvino-dev with OpenVINO Runtime inference by @GabrielDornelles in Replace openvino-dev with OpenVINO Runtime inference #7843
TFDWConv() depthwise_initializer fix by @glenn-jocher in TFDWConv() depthwise_initializer fix #7845
Update Dockerfile --no-install-recommends by @glenn-jocher in Update Dockerfile --no-install-recommends #7846
Update CI CPU badge by @glenn-jocher in Update CI CPU badge #7855
Create docker.yml by @glenn-jocher in Create docker.yml #7856
Update Dockerfile-cpu install libpython3.8-dev by @glenn-jocher in Update Dockerfile-cpu install libpython3.8-dev #7857
Add TFDWConv() depth_multiplier arg by @glenn-jocher in Add TFDWConv() depth_multiplier arg #7858
Update Dockerfile-arm64 by @glenn-jocher in Update Dockerfile-arm64 #7860
Invert Docker Image publishing order by @glenn-jocher in Invert Docker Image publishing order #7877
Removed shell=True from subprocess commands that require user inputs by @JWLee89 in Removed shell=True from subprocess commands that require user inputs #7875
Added Windows cmd to count GPU devices by @xylieong in Added Windows cmd to count GPU devices #7891
Bug fix mAP0.5-0.95 by @lebedevdes in Bug fix mAP0.5-0.95 #6787
cv2.resize interpolation fix by @glenn-jocher in cv2.resize interpolation fix #7903
Add DWConvTranspose2d() module by @glenn-jocher in Add DWConvTranspose2d() module #7881
Add check_yaml() to benchmarks.py by @glenn-jocher in Add check_yaml() to benchmarks.py #7916
Add --keras argument for TF exports by @glenn-jocher in Add --keras argument for TF exports #7921
Add PyTorch AMP check by @glenn-jocher in Add PyTorch AMP check #7917
Code refactor by @glenn-jocher in Code refactor #7923
AMP check image download backup by @glenn-jocher in AMP check image download backup #7936
Fix AMP check tolerance by @glenn-jocher in Fix AMP check tolerance #7937
Windows check_file() fix by @glenn-jocher in Windows check_file() fix #7938
Add OpenVINO metadata to export by @xylieong in Add OpenVINO metadata to export #7947
OpenVINO metadata fix by @glenn-jocher in OpenVINO metadata fix #7952
OpenVINO metadata fix2 by @xylieong in OpenVINO metadata fix2 #7954
YOLOv5 Apple Metal Performance Shader (MPS) support by @glenn-jocher in YOLOv5 Apple Metal Performance Shader (MPS) support #7878
Increase NMS time limit to 50 ms/img by @glenn-jocher in Increase NMS time limit to 50 ms/img #7956
Increase NMS fixed time limit 300ms + 30ms/img by @glenn-jocher in Increase NMS fixed time limit 300ms + 30ms/img #7957
AMP check improvements backup YOLOv5n pretrained by @glenn-jocher in AMP check improvements backup YOLOv5n pretrained #7959
Update greetings.yml by @glenn-jocher in Update greetings.yml #7965
Update requirements.txt with Usage example by @glenn-jocher in Update requirements.txt with Usage example #7966
Remove formats variable to avoid pd conflict by @glenn-jocher in Remove formats variable to avoid pd conflict #7993
check_requirements() Windows fix by @glenn-jocher in check_requirements() Windows fix #7997
Add psutil and ipython to requirements.txt by @glenn-jocher in Add psutil and ipython to requirements.txt #7998
cURL download double quotes by @glenn-jocher in cURL download double quotes #7999
Update and add benchmarks to ci-testing.yml by @glenn-jocher in Update and add benchmarks to ci-testing.yml #7996
Add warning emoji ⚠️ on --conf > 0.001 by @glenn-jocher in Add warning emoji ⚠️ on --conf > 0.001 #8005
Update CI benchmarks to ONNX autoinstall by @glenn-jocher in Update CI benchmarks to ONNX autoinstall #8008
Pin CI protobuf==3.20.1 by @glenn-jocher in Pin CI protobuf==3.20.1 #8015
check_requirements() "" Windows double quote by @glenn-jocher in check_requirements() "" Windows double quote #8016
Add requirements.txt protobuf<=3.20.1 by @glenn-jocher in Add requirements.txt protobuf<=3.20.1 #8017
Add best.pt PyTorch Hub inference to CI by @glenn-jocher in Add best.pt PyTorch Hub inference to CI #8024
Add Dockerfile descriptions by @glenn-jocher in Add Dockerfile descriptions #8031
Simplify and fix --save-period epoch 0 by @glenn-jocher in Simplify and fix --save-period epoch 0 #8042
.detach() on bias init by @tcmyxc in .detach() on bias init #8044
attempt_load() deserialize fix by @glenn-jocher in attempt_load() deserialize fix #8051
Fix FP32 TensorRT model export by @SahilChachra in Fix FP32 TensorRT model export #8046
Make Docker actions conditional on ultralytics/yolov5 repo by @glenn-jocher in Make Docker actions conditional on ultralytics/yolov5 repo #8060
Update stale.yml to 300 ops per run by @glenn-jocher in Update stale.yml to 300 ops per run #8061
Fix torch long to float tensor on HUB macOS by @glenn-jocher in Fix torch long to float tensor on HUB macOS #8067
Improved dataset error introspection by @glenn-jocher in Improved dataset error introspection #8091
experimental.py Apple MPS device fix by @glenn-jocher in experimental.py Apple MPS device fix #8121
[pre-commit.ci] pre-commit suggestions by @pre-commit-ci in [pre-commit.ci] pre-commit suggestions #8119
fix(utils): missing edge when resample segments by @HRan2004 in fix(utils): missing edge when resample segments #8092
AutoBatch checks against failed solutions by @glenn-jocher in AutoBatch checks against failed solutions #8159
FROM nvcr.io/nvidia/pytorch:22.05-py3 by @glenn-jocher in FROM nvcr.io/nvidia/pytorch:22.05-py3 #8162
Docker GPU pip install opencv-python<4.6.0.66 by @glenn-jocher in Docker GPU pip install opencv-python<4.6.0.66 #8164
Improved dataset_stats() YAML checks by @glenn-jocher in Improved dataset_stats() YAML checks #8125
Bump actions/setup-python from 3 to 4 by @dependabot in Bump actions/setup-python from 3 to 4 #8186
Reject webcam inference on Colab/Kaggle by @glenn-jocher in Reject webcam inference on Colab/Kaggle #8209
Remove streaming source sleep period by @glenn-jocher in Remove streaming source sleep period #8243
Prefer MPS over CPU if available by @glenn-jocher in Prefer MPS over CPU if available #8210
HUB dataset_stats() error reporting by @glenn-jocher in HUB dataset_stats() error reporting #8192
process_batch() as numpy arrays by @glenn-jocher in process_batch() as numpy arrays #8254
Created using Colaboratory by @glenn-jocher in Created using Colaboratory #8255
logging.ERROR on RANK not in (0, 1) by @glenn-jocher in logging.ERROR on RANK not in (0, 1) #8284
device_name="MYRIAD" for Intel NCS2 comment by @glenn-jocher in device_name="MYRIAD" for Intel NCS2 comment #8327
Allow preview resize in detect.py by @RyanHir in Allow preview resize in detect.py #8318
Create README_cn.md by @glenn-jocher in Create README_cn.md #8344
Allow detect.py to use video size for initial window size by @NicholasZolton in Allow detect.py to use video size for initial window size #8330
Revamp Chinese docs by @zhiqwang in Revamp Chinese docs #8350
Fix bias warmup LR init by @glenn-jocher in Fix bias warmup LR init #8356
Add File Size (MB) column to benchmarks by @glenn-jocher in Add File Size (MB) column to benchmarks #8359
Update protobuf requirement from <=3.20.1 to <4.21.3 by @dependabot in Update protobuf requirement from <=3.20.1 to <4.21.3 #8346
Fix ONNX --dynamic export on GPU by @glenn-jocher in Fix ONNX --dynamic export on GPU #8378
Update tutorial.ipynb by @glenn-jocher in Update tutorial.ipynb #8380
Implementation of Early Stopping for DDP training by @giacomoguiduzzi in Implementation of Early Stopping for DDP training #8345
Improve --local_rank arg comment by @pourmand1376 in Improve --local_rank arg comment #8409
Update cache comments by @glenn-jocher in Update cache comments #8414
TRT --half fix autocast images to FP16 by @glenn-jocher in TRT --half fix autocast images to FP16 #8435
Expose OpenVINO batch_size similarly to TensorRT by @democat3457 in Expose OpenVINO batch_size similarly to TensorRT #8437
Do not prefer Apple MPS by @glenn-jocher in Do not prefer Apple MPS #8446
Update stale.yml by @glenn-jocher in Update stale.yml #8465
[pre-commit.ci] pre-commit suggestions by @pre-commit-ci in [pre-commit.ci] pre-commit suggestions #8470
Exclude torch==1.12.0, torchvision==0.13.0 (Fix YOLOv5 issues with torch==1.12 on Multi-GPU systems #8395) by @mjun0812 in Exclude torch==1.12.0, torchvision==0.13.0 (Fix #8395) #8497
Update tutorial.ipynb by @glenn-jocher in Update tutorial.ipynb #8507
Training reproducibility improvements by @AyushExel in Training reproducibility improvements #8213
Revert "Expose OpenVINO batch_size similarly to TensorRT" by @glenn-jocher in Revert "Expose OpenVINO batch_size similarly to TensorRT" #8510
Avoid FP64 ops for MPS support in train.py by @glenn-jocher in Avoid FP64 ops for MPS support in train.py #8511
Fix ap calculation bug Val.py: No prediction on image follows in wrong AP calculation #8464 by @UnglvKitDe in Fix ap calculation bug #8464 #8484
Add --hard-fail argument to benchmarks for CI errors by @glenn-jocher in Add --hard-fail argument to benchmarks for CI errors #8513
Simplify benchmarks.py assertions by @glenn-jocher in Simplify benchmarks.py assertions #8515
Properly expose batch_size from OpenVINO similarly to TensorRT by @democat3457 in Properly expose batch_size from OpenVINO similarly to TensorRT #8514
Add --half arguments to export.py Usage examples by @glenn-jocher in Add --half arguments to export.py Usage examples #8516
XML export --half fix by @glenn-jocher in XML export --half fix #8522
Fix LoadImages() with dataset YAML lists by @democat3457 in Fix LoadImages() with dataset YAML lists #8517
val.py assert ncm == nc fix by @glenn-jocher in val.py assert ncm == nc fix #8545
CIoU protected divides by @glenn-jocher in CIoU protected divides #8546
Update metrics.py with IoU protected divides by @glenn-jocher in Update metrics.py with IoU protected divides #8550
Add TensorRT dependencies by @Zengyf-CVer in Add TensorRT dependencies #8553
Add thop>=0.1.0 by @glenn-jocher in Add thop>=0.1.0 #8558
Raise error on suffix-less model path by @democat3457 in Raise error on suffix-less model path #8561
Assert --optimize not used with cuda device by @democat3457 in Assert --optimize not used with cuda device #8569
Update requirements.txt comment spacing by @glenn-jocher in Update requirements.txt comment spacing #8562
Explicitly set weight_decay value by @developer0hye in Explicitly set weight_decay value #8592
Update scipy>=1.7.3 by @glenn-jocher in Update scipy>=1.7.3 #8595
Update tqdm>=4.64.0 and thop>=0.1.1 by @glenn-jocher in Update tqdm>=4.64.0 and thop>=0.1.1 #8596
Add pip install wheel to avoid legacy setup.py install by @glenn-jocher in Add pip install wheel to avoid legacy setup.py install #8597
Link fuse() to AutoShape() for Hub models by @glenn-jocher in Link fuse() to AutoShape() for Hub models #8599
FROM nvcr.io/nvidia/pytorch:22.06-py3 by @glenn-jocher in FROM nvcr.io/nvidia/pytorch:22.06-py3 #8600
Refactor optimizer initialization by @glenn-jocher in Refactor optimizer initialization #8607
assert torch!=1.12.0 for DDP training by @glenn-jocher in assert torch!=1.12.0 for DDP training #8621
Fix OMP_NUM_THREADS=1 for macOS by @glenn-jocher in Fix OMP_NUM_THREADS=1 for macOS #8624
Upgrade onnxsim to v0.4.1 by @daquexian in Upgrade onnxsim to v0.4.1 #8632
Check TensorBoard logger before adding graph by @JarnoRFB in Check TensorBoard logger before adding graph #8664
Use contextlib's suppress method to silence an error by @glenn-jocher in Use contextlib's suppress method to silence an error #8668
Update hubconf.py to reset LOGGER.level after load by @glenn-jocher in Update hubconf.py to reset LOGGER.level after load #8674
Update warning emojis by @glenn-jocher in Update warning emojis #8678
Update hubconf.py to reset logging level to INFO by @glenn-jocher in Update hubconf.py to reset logging level to INFO #8680
Add generator and worker seed by @UnglvKitDe in Add generator and worker seed #8602
Set torch.cuda.manual_seed_all() for DDP by @glenn-jocher in Set torch.cuda.manual_seed_all() for DDP #8688
Move .dockerignore to root by @glenn-jocher in Move .dockerignore to root #8690
Faster crop saving by @glenn-jocher in Faster crop saving #8696
Remove else: from load_image() by @glenn-jocher in Remove else: from load_image() #8692
Avoid cv2 window init code on Windows by @glenn-jocher in Avoid cv2 window init code on Windows #8712
Update dataloaders.py by @glenn-jocher in Update dataloaders.py #8714
New HUBDatasetStats() class by @glenn-jocher in New HUBDatasetStats() class #8716
Fix BGR->RGB Bug in albumentations Albumentations-Pipeline is applied to BGR not to RGB #8641 by @UnglvKitDe in Fix BGR->RGB Bug in albumentations #8641 #8695
coremltools>=5.2 for CoreML export by @glenn-jocher in coremltools>=5.2 for CoreML export #8725
Revert "Fix BGR->RGB Bug in albumentations Albumentations-Pipeline is applied to BGR not to RGB #8641" by @glenn-jocher in Revert "Fix BGR->RGB Bug in albumentations #8641" #8727
fix: broken is_docker check by @maxstrobel in fix: broken is_docker check #8711
Revert protobuf<=3.20.1 by @glenn-jocher in Revert protobuf<=3.20.1 #8742
Dynamic batch size support for TensorRT by @democat3457 in Dynamic batch size support for TensorRT #8526
Fix confusion matrix update when no predictions are made by @jbutle55 in Fix confusion matrix update when no predictions are made #8748
Add val.py no label warning by @glenn-jocher in Add val.py no label warning #8782
Fix detect.py --update list bug by @glenn-jocher in Fix detect.py --update list bug #8783
ci-testing.yml Windows-friendly ENV variables by @glenn-jocher in ci-testing.yml Windows-friendly ENV variables #8794
Add hubconf.py argparser by @glenn-jocher in Add hubconf.py argparser #8799
Print hubconf.py args by @glenn-jocher in Print hubconf.py args #8800
Update Colab Notebook CI by @glenn-jocher in Update Colab Notebook CI #8798
Deprecate torch 1.6.0 compat _non_persistent_buffers_set by @glenn-jocher in Deprecate torch 1.6.0 compat _non_persistent_buffers_set #8797
Detect.inplace=False for multithread-safe inference by @glenn-jocher in Detect.inplace=False for multithread-safe inference #8801
Update train.py for val.run(half=amp) by @glenn-jocher in Update train.py for val.run(half=amp) #8804
Fix val.py 'no labels found bug' by @glenn-jocher in Fix val.py 'no labels found bug' #8806
Update requirements.txt with tf-cpu and tf-aarch64 by @glenn-jocher in Update requirements.txt with tf-cpu and tf-aarch64 #8807
FROM nvcr.io/nvidia/pytorch:22.07-py3 by @glenn-jocher in FROM nvcr.io/nvidia/pytorch:22.07-py3 #8808
Update ci-testing.yml streamlined tests by @glenn-jocher in Update ci-testing.yml streamlined tests #8809
Check git status on upstream ultralytics or origin dynamically by @pourmand1376 in Check git status on upstream ultralytics or origin dynamically #8694
Fix Colab-update pre-commit EOF bug by @glenn-jocher in Fix Colab-update pre-commit EOF bug #8810
Update .pre-commit-config.yaml by @glenn-jocher in Update .pre-commit-config.yaml #8811
Update .pre-commit-config.yaml by @glenn-jocher in Update .pre-commit-config.yaml #8812
Remove assert not is_docker() from GitHub checks by @glenn-jocher in Remove assert not is_docker() from GitHub checks #8813
Add .git to .dockerignore by @glenn-jocher in Add .git to .dockerignore #8815
Add tensor hooks and 10.0 gradient clipping by @UnglvKitDe in Add tensor hooks and 10.0 gradient clipping #8598
Update README.md with contributors.png by @glenn-jocher in Update README.md with contributors.png #8820
Remove hook torch.nan_to_num(x) by @glenn-jocher in Remove hook torch.nan_to_num(x) #8826
RUN git clone instead of COPY to /usr/src/app by @glenn-jocher in RUN git clone instead of COPY to /usr/src/app #8827
[pre-commit.ci] pre-commit suggestions by @pre-commit-ci in [pre-commit.ci] pre-commit suggestions #8828
Fix missing attr model.model when loading custom yolov model by @jacksonargo in Fix missing attr model.model when loading custom yolov model #8830
New smart_resume() by @glenn-jocher in New smart_resume() #8838
Self-contained checkpoint --resume by @glenn-jocher in Self-contained checkpoint --resume #8839
Add check_file(data) i.e. --data coco128.yaml by @glenn-jocher in Add check_file(data) i.e. --data coco128.yaml #8851
export.py replace check_file -> check_yaml by @glenn-jocher in export.py replace check_file -> check_yaml #8852
Update dataloaders.py remove float64 shapes by @glenn-jocher in Update dataloaders.py remove float64 shapes #8865
Fix TensorRT --dynamic excess outputs bug by @glenn-jocher in Fix TensorRT --dynamic excess outputs bug #8869
Single-line TRT dynamic assertion by @glenn-jocher in Single-line TRT dynamic assertion #8871
HUBDatasetStats() preview images to 50 quality by @glenn-jocher in HUBDatasetStats() preview images to 50 quality #8880
--resume training from URL weights by @glenn-jocher in --resume training from URL weights #8882
--resume training from URL weights fix by @glenn-jocher in --resume training from URL weights fix #8884
Update CI to default Python 3.10 by @glenn-jocher in Update CI to default Python 3.10 #8883
ClearML experiment tracking integration by @thepycoder in ClearML experiment tracking integration #8620
smart_optimizer() improved reporting by @glenn-jocher in smart_optimizer() improved reporting #8887
emoji-safe default logging by @glenn-jocher in emoji-safe default logging #8888
Fix/improve social media bar by @kalenmike in Fix/improve social media bar #8893
Update README.md Environments icons by @glenn-jocher in Update README.md Environments icons #8895
Fix anchor incorrectly initialized by @YellowAndGreen in Fix anchor incorrectly initialized #8891
Edge TPU add --search_delegate fix by @glenn-jocher in Edge TPU add --search_delegate fix #8902
Capitalize YouTube by @glenn-jocher in Capitalize YouTube #8903
About "os.R_OK" in general.py by @19190205wzy in About "os.R_OK" in general.py #8909
Scope torchvision.utils.draw_bounding_boxes import by @glenn-jocher in Scope torchvision.utils.draw_bounding_boxes import #8915
Add torch==1.7.0 to CI tests by @glenn-jocher in Add torch==1.7.0 to CI tests #8916
Direct download table links by @glenn-jocher in Direct download table links #8917
Fix --source 'path/*.jpg' glob example by @glenn-jocher in Fix --source 'path/*.jpg' glob example #8927
Deci.ai optimization and deployment Integration by @glenn-jocher in Deci.ai optimization and deployment Integration #8928
Allow train to use zipped content by @kalenmike in Allow train to use zipped content #8940
Remove DDP destroy_process_group() on train end by @glenn-jocher in Remove DDP destroy_process_group() on train end #8935
GFLOPs computation fix for classification models by @glenn-jocher in GFLOPs computation fix for classification models #8954
New smart_inference_mode() conditional decorator by @glenn-jocher in New smart_inference_mode() conditional decorator #8957
Fix windows LOGGER with emojis output by @glenn-jocher in Fix windows LOGGER with emojis output #8958
Add bash script arguments by @glenn-jocher in Add bash script arguments #8962
Add .tar support for datasets by @glenn-jocher in Add .tar support for datasets #8963
Allow multiple-model serving from Flask REST API by @mpromonet in Allow multiple-model serving from Flask REST API #8973
Colab and Kaggle loggers removeHandler by @glenn-jocher in Colab and Kaggle loggers removeHandler #8985
Fix bug with resume by @savchenkoyana in Fix bug with resume #8912

😃 New Contributors (41)

@lcombaldieu made their first contribution in Fix export for 1-channel images #6780
@vnekat made their first contribution in Update yolov5s.yaml #6865
@DavidBaldsiefen made their first contribution in Default FP16 TensorRT export #6798
@paradigmn made their first contribution in EdgeTPU optimizations #6808
@maxstrobel made their first contribution in fix: add default PIL font as fallback #7010
@LaserBorg made their first contribution in Use PIL to eliminate chroma subsampling in crops #7008
@yeshanliu made their first contribution in np.fromfile() Chinese image paths fix #6979
@CCRcmcpe made their first contribution in Fix cv2.imwrite on non-ASCII paths #7139
@leeflix made their first contribution in Enable TensorFlow ops for --nms and --agnostic-nms #7281
@n1mmy made their first contribution in Copy wandb param dict before training to avoid overwrites. #7317
@rglkt made their first contribution in DetectMultiBackend() default stride=32 #7342
@vardanagarwal made their first contribution in Add support for different normalization layers #7377
@Cedric-Perauer made their first contribution in Add --half support for FP16 CoreML exports with #7446
@HERIUN made their first contribution in Update val.py #7478
@jkocherhans made their first contribution in Added YOLOv5_AUTOINSTALL environment variable #7505
@Powercube7 made their first contribution in Update downloads.py current release #7541
@Jack24658735 made their first contribution in Fix from yolov5 import utils statement #7578
@djmmoss made their first contribution in Add --half support for OpenVINO exports #7615
@sylvanding made their first contribution in Update plot.py #7654
@dmatos2012 made their first contribution in Disallow --dynamic when --half is passed #7669
@GabrielDornelles made their first contribution in Replace openvino-dev with OpenVINO Runtime inference #7843
@JWLee89 made their first contribution in Removed shell=True from subprocess commands that require user inputs #7875
@xylieong made their first contribution in Added Windows cmd to count GPU devices #7891
@lebedevdes made their first contribution in Bug fix mAP0.5-0.95 #6787
@tcmyxc made their first contribution in .detach() on bias init #8044
@SahilChachra made their first contribution in Fix FP32 TensorRT model export #8046
@HRan2004 made their first contribution in fix(utils): missing edge when resample segments #8092
@RyanHir made their first contribution in Allow preview resize in detect.py #8318
@NicholasZolton made their first contribution in Allow detect.py to use video size for initial window size #8330
@giacomoguiduzzi made their first contribution in Implementation of Early Stopping for DDP training #8345
@pourmand1376 made their first contribution in Improve --local_rank arg comment #8409
@democat3457 made their first contribution in Expose OpenVINO batch_size similarly to TensorRT #8437
@mjun0812 made their first contribution in Exclude torch==1.12.0, torchvision==0.13.0 (Fix #8395) #8497
@UnglvKitDe made their first contribution in Fix ap calculation bug #8464 #8484
@daquexian made their first contribution in Upgrade onnxsim to v0.4.1 #8632
@JarnoRFB made their first contribution in Check TensorBoard logger before adding graph #8664
@jbutle55 made their first contribution in Fix confusion matrix update when no predictions are made #8748
@jacksonargo made their first contribution in Fix missing attr model.model when loading custom yolov model #8830
@thepycoder made their first contribution in ClearML experiment tracking integration #8620
@YellowAndGreen made their first contribution in Fix anchor incorrectly initialized #8891
@19190205wzy made their first contribution in About "os.R_OK" in general.py #8909
@mpromonet made their first contribution in Allow multiple-model serving from Flask REST API #8973
@savchenkoyana made their first contribution in Fix bug with resume #8912

sotaDetector · 2022-08-18T06:23:35Z

sotaDetector
Aug 18, 2022

will you add keypoint task in this project later?

1 reply

AyushExel Aug 18, 2022

There's a lot of things coming. Stay tuned :)

daikankan · 2022-09-01T12:20:18Z

daikankan
Sep 1, 2022

8 replies

daikankan Sep 1, 2022

@glenn-jocher referring to detection training

glenn-jocher Sep 1, 2022
Maintainer Author

@daikankan detection training is unaffected by v6.2

daikankan Sep 2, 2022

@glenn-jocher After I disabled [self.tb, self.clearml, self.wandb] in on_fit_epoch_end(), and on_model_save(), It's still stuck in early epochs.

AyushExel Sep 2, 2022

@daikankan hey can you please share the original training command that got stuck? I'd like to test it to make sure we don't have a bug specific to large datasets. Thanks!

daikankan Sep 2, 2022

@AyushExel nohup python -m torch.distributed.launch --nproc_per_node 4 train.py --workers 8 --cfg models/mymodel.yaml --batch-size 2048 --epochs 300 --noautoanchor --device 0,1,2,3 > ../log.out 2>&1 &

rkechols · 2022-11-21T19:22:26Z

rkechols
Nov 21, 2022

These release notes refer to 6.3:

Our next release, v6.3 is scheduled for September

It is now late November. Is there any chance of a new tag/release coming soon?
My organization would like to make use of some of the recent changes (newer than 6.2), but don't want our code to pull the always-moving "latest from master", for stability reasons. (Note that torch.hub.load only allows pinning by branch or tag, not by commit SHA)

@glenn-jocher

1 reply

glenn-jocher Nov 21, 2022
Maintainer Author

Tomorrow. #10245

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

v6.2 - YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai integrations #8996

{{title}}

{{editor}}'s edit

{{editor}}'s edit

Replies: 3 comments 10 replies

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

Select a reply

v6.2 - YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai integrations #8996

glenn-jocher Aug 17, 2022 Maintainer

Important Updates

New Classification Checkpoints

New Classification Model Usage Examples

Train

Val

Predict

Export

Changelog

Replies: 3 comments · 10 replies

glenn-jocher Sep 1, 2022 Maintainer Author

glenn-jocher Nov 21, 2022 Maintainer Author

glenn-jocher
Aug 17, 2022
Maintainer

Replies: 3 comments 10 replies

glenn-jocher Sep 1, 2022
Maintainer Author

glenn-jocher Nov 21, 2022
Maintainer Author