update to 01.02.23 ultralytics/yolov5 (#214)

* update to latest ultralytics

* updates

* fix typo

* fix a typo

* fix classify predict

* fix typo

* fix typo

* update roboflow cls data

* remove roboflow cls ci

* refactor ci workflow, fix typo in roboflow util (#215)

* update workflow config and yolov5 version

* fix a typo in roboflow utils

* Co-authored-by: SkalskiP <piotr.skalski92@gmail.com>

* Update ci.yml

* fix a typo

* Update package_testing.yml

.github/workflows/ci.yml

@@ -48,9 +48,7 @@ jobs:
  run: |
  python -m unittest
 
- - name: Test scripts
- env:
- ROBOFLOW_TOKEN: ${{ secrets.ROBOFLOW_API_KEY }}
+ - name: Test yolov5 train
  shell: bash # for Windows compatibility
  run: |
  pip install -e .
@@ -66,34 +64,57 @@ jobs:
  python yolov5/train.py --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --epochs 1 --device cpu
  yolov5 train --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --epochs 1 --device cpu --freeze 10
  yolov5 train --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --epochs 1 --device cpu --evolve 2
- # detect
+
+ - name: Test yolov5 detect
+ shell: bash # for Windows compatibility
+ run: |
  python yolov5/detect.py --weights yolov5/weights/yolov5n.pt --device cpu
  yolov5 detect --weights yolov5/weights/yolov5n.pt --device cpu
  python yolov5/detect.py --weights runs/train/exp/weights/last.pt --device cpu
  yolov5 detect --weights runs/train/exp/weights/last.pt --device cpu
- # val
+
+ - name: Test yolov5 val
+ shell: bash # for Windows compatibility
+ run: |
  python yolov5/val.py --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --device cpu
  yolov5 val --data yolov5/data/coco128.yaml --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --device cpu
  python yolov5/val.py --img 128 --batch 16 --weights runs/train/exp/weights/last.pt --device cpu
  yolov5 val --data yolov5/data/coco128.yaml --img 128 --batch 16 --weights runs/train/exp/weights/last.pt --device cpu
- # export
+
+ - name: Test yolov5 export
+ shell: bash # for Windows compatibility
+ run: |
  pip install onnx onnx-simplifier tensorflowjs
  python yolov5/export.py --weights yolov5/weights/yolov5n.pt --device cpu --include torchscript,onnx,tflite
  yolov5 export --weights yolov5/weights/yolov5n.pt --device cpu --simplify --include torchscript,onnx,saved_model,pb,tfjs
- # benckmarks
+
+ - name: Test yolov5 benchmarks
+ shell: bash # for Windows compatibility
+ run: |
  yolov5 benchmarks --weights yolov5n.pt --img 128 --pt-only --device cpu
- # classify
+
+ - name: Test yolov5 classify
+ shell: bash # for Windows compatibility
+ run: |
  yolov5 classify train --img 128 --data mnist2560 --model yolov5n-cls.pt --epochs 1 --device cpu
  yolov5 classify train --img 128 --data mnist2560 --model fcakyon/yolov5n-cls-v7.0 --epochs 1 --device cpu
  yolov5 classify val --img 128 --data datasets/mnist2560 --weights yolov5n-cls.pt --device cpu
  yolov5 classify predict --img 128 --weights yolov5n-cls.pt --device cpu 
- # segment
+
+ - name: Test yolov5 segment
+ shell: bash # for Windows compatibility
+ run: |
  yolov5 segment train --img 128 --weights yolov5n-seg.pt --epochs 1 --device cpu
  yolov5 segment train --img 128 --weights fcakyon/yolov5n-seg-v7.0 --epochs 1 --device cpu
  # yolov5 segment val --img 128 --weights yolov5n-seg.pt --device cpu
  yolov5 segment predict --img 128 --weights yolov5n-seg.pt --device cpu
- # roboflow
- yolov5 train --data https://universe.roboflow.com/jacob-solawetz/aerial-maritime/dataset/10 --weights yolov5/weights/yolov5n.pt --device cpu --roboflow_token ${{ env.ROBOFLOW_TOKEN }}
- yolov5 classify train --data https://universe.roboflow.com/bagas-etcfr/flowerdata1/dataset/1 --img 128 --model yolov5n-cls.pt --epochs 1 --device cpu --roboflow_token ${{ env.ROBOFLOW_TOKEN }}
- yolov5 segment train --data https://universe.roboflow.com/scaffolding/scaffolding-distance/dataset/2 --img 128 --weights yolov5n-seg.pt --epochs 1 --device cpu --roboflow_token ${{ env.ROBOFLOW_TOKEN }}
+
+ - name: Test roboflow train
+ shell: bash # for Windows compatibility
+ env:
+ ROBOFLOW_TOKEN: ${{ secrets.ROBOFLOW_API_KEY }}
+ run: |
+ yolov5 train --data https://universe.roboflow.com/gdit/aerial-airport/dataset/1 --weights yolov5/weights/yolov5n.pt --img 128 --epochs 1 --device cpu --roboflow_token ${{ env.ROBOFLOW_TOKEN }}
+ # yolov5 classify train --data https://universe.roboflow.com/carlos-gabriel-da-silva-machado-siwvs/turtles-i1tlr/dataset/1 --img 128 --model yolov5n-cls.pt --epochs 1 --device cpu --roboflow_token ${{ env.ROBOFLOW_TOKEN }}
+ yolov5 segment train --data https://universe.roboflow.com/aymane-outani-auooc/cable-fzjik/dataset/2 --img 128 --weights yolov5n-seg.pt --epochs 1 --device cpu --roboflow_token ${{ env.ROBOFLOW_TOKEN }}
 

.github/workflows/package_testing.yml

@@ -46,9 +46,9 @@ jobs:
  run: |
  python -m unittest
 
- - name: Test scripts
+ - name: Test yolov5 train
+ shell: bash # for Windows compatibility
  run: |
- pip install -e .
  # donwload coco formatted testing data
  python tests/download_test_coco_dataset.py
  # train (dl base model from hf hub)
@@ -61,29 +61,49 @@ jobs:
  python yolov5/train.py --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --epochs 1 --device cpu
  yolov5 train --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --epochs 1 --device cpu --freeze 10
  yolov5 train --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --epochs 1 --device cpu --evolve 2
- # detect
+ - name: Test yolov5 detect
+ shell: bash # for Windows compatibility
+ run: |
  python yolov5/detect.py --weights yolov5/weights/yolov5n.pt --device cpu
  yolov5 detect --weights yolov5/weights/yolov5n.pt --device cpu
  python yolov5/detect.py --weights runs/train/exp/weights/last.pt --device cpu
  yolov5 detect --weights runs/train/exp/weights/last.pt --device cpu
- # val
+ - name: Test yolov5 val
+ shell: bash # for Windows compatibility
+ run: |
  python yolov5/val.py --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --device cpu
  yolov5 val --data yolov5/data/coco128.yaml --img 128 --batch 16 --weights yolov5/weights/yolov5n.pt --device cpu
  python yolov5/val.py --img 128 --batch 16 --weights runs/train/exp/weights/last.pt --device cpu
  yolov5 val --data yolov5/data/coco128.yaml --img 128 --batch 16 --weights runs/train/exp/weights/last.pt --device cpu
- # export
+ - name: Test yolov5 export
+ shell: bash # for Windows compatibility
+ run: |
  pip install onnx onnx-simplifier tensorflowjs
  python yolov5/export.py --weights yolov5/weights/yolov5n.pt --device cpu --include torchscript,onnx,tflite
  yolov5 export --weights yolov5/weights/yolov5n.pt --device cpu --simplify --include torchscript,onnx,saved_model,pb,tfjs
- # benckmarks
+ - name: Test yolov5 benchmarks
+ shell: bash # for Windows compatibility
+ run: |
  yolov5 benchmarks --weights yolov5n.pt --img 128 --pt-only --device cpu
- # classify
+ - name: Test yolov5 classify
+ shell: bash # for Windows compatibility
+ run: |
  yolov5 classify train --img 128 --data mnist2560 --model yolov5n-cls.pt --epochs 1 --device cpu
  yolov5 classify train --img 128 --data mnist2560 --model fcakyon/yolov5n-cls-v7.0 --epochs 1 --device cpu
  yolov5 classify val --img 128 --data datasets/mnist2560 --weights yolov5n-cls.pt --device cpu
  yolov5 classify predict --img 128 --weights yolov5n-cls.pt --device cpu 
- # segment
+ - name: Test yolov5 segment
+ shell: bash # for Windows compatibility
+ run: |
  yolov5 segment train --img 128 --weights yolov5n-seg.pt --epochs 1 --device cpu
  yolov5 segment train --img 128 --weights fcakyon/yolov5n-seg-v7.0 --epochs 1 --device cpu
  # yolov5 segment val --img 128 --weights yolov5n-seg.pt --device cpu
  yolov5 segment predict --img 128 --weights yolov5n-seg.pt --device cpu
+ - name: Test roboflow train
+ shell: bash # for Windows compatibility
+ env:
+ ROBOFLOW_TOKEN: ${{ secrets.ROBOFLOW_API_KEY }}
+ run: |
+ yolov5 train --data https://universe.roboflow.com/gdit/aerial-airport/dataset/1 --weights yolov5/weights/yolov5n.pt --img 128 --epochs 1 --device cpu --roboflow_token ${{ env.ROBOFLOW_TOKEN }}
+ # yolov5 classify train --data https://universe.roboflow.com/carlos-gabriel-da-silva-machado-siwvs/turtles-i1tlr/dataset/1 --img 128 --model yolov5n-cls.pt --epochs 1 --device cpu --roboflow_token ${{ env.ROBOFLOW_TOKEN }}
+ yolov5 segment train --data https://universe.roboflow.com/aymane-outani-auooc/cable-fzjik/dataset/2 --img 128 --weights yolov5n-seg.pt --epochs 1 --device cpu --roboflow_token ${{ env.ROBOFLOW_TOKEN }}

README.md

@@ -25,7 +25,7 @@ You can finally install <a href="https://github.com/ultralytics/yolov5">YOLOv5 o
 </div>
 
 <br>
-This yolov5 package contains everything from ultralytics/yolov5 <a href="https://github.com/ultralytics/yolov5/tree/357cde9ee7da13ba3095995488c5a23631467f1a">at this commit</a> plus:
+This yolov5 package contains everything from ultralytics/yolov5 <a href="https://github.com/ultralytics/yolov5/tree/064365d8683fd002e9ad789c1e91fa3d021b44f0">at this commit</a> plus:
 <br>
 1. Easy installation via pip: <b>pip install yolov5</b>
 <br>

requirements.txt

@@ -1,4 +1,4 @@
-# YOLOv5 🚀 requirements
+# YOLOv5 requirements
 # Usage: pip install -r requirements.txt
 
 # Base ------------------------------------------------------------------------
@@ -29,7 +29,7 @@ seaborn>=0.11.0
 
 # Export ----------------------------------------------------------------------
 # coremltools>=6.0 # CoreML export
-# onnx>=1.9.0 # ONNX export
+# onnx>=1.12.0 # ONNX export
 # onnx-simplifier>=0.4.1 # ONNX simplifier
 # nvidia-pyindex # TensorRT export
 # nvidia-tensorrt # TensorRT export
@@ -44,7 +44,7 @@ seaborn>=0.11.0
 # Extras ----------------------------------------------------------------------
 # mss # screenshots
 # albumentations>=1.0.3
-# pycocotools>=2.0 # COCO mAP
+# pycocotools>=2.0.6 # COCO mAP
 # roboflow>=0.2.27
 # ultralytics # HUB https://hub.ultralytics.com
 
@@ -55,4 +55,4 @@ boto3>=1.19.1
 # coco to yolov5 conversion
 sahi>=0.11.10
 # huggingface
-huggingface-hub>=0.11.1
+huggingface-hub>=0.12.0

yolov5/__init__.py

@@ -1,4 +1,4 @@
 from yolov5.helpers import YOLOv5
 from yolov5.helpers import load_model as load
 
-__version__ = "7.0.7"
+__version__ = "7.0.8"

yolov5/classify/predict.py

@@ -213,7 +213,7 @@ def parse_opt():
  parser.add_argument('--augment', action='store_true', help='augmented inference')
  parser.add_argument('--visualize', action='store_true', help='visualize features')
  parser.add_argument('--update', action='store_true', help='update all models')
- parser.add_argument('--project', default=ROOT / 'runs/predict-cls', help='save results to project/name')
+ parser.add_argument('--project', default='runs/predict-cls', help='save results to project/name')
  parser.add_argument('--name', default='exp', help='save results to project/name')
  parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
  parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
@@ -227,7 +227,7 @@ def parse_opt():
 
 def main():
  opt = parse_opt()
- #check_requirements(exclude=('tensorboard', 'thop'))
+ check_requirements(exclude=('tensorboard', 'thop'))
  run(**vars(opt))
 
 

yolov5/classify/train.py

@@ -6,7 +6,7 @@
  $ python classify/train.py --model yolov5s-cls.pt --data imagenette160 --epochs 5 --img 224
 
 Usage - Multi-GPU DDP training:
- $ 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
+ $ python -m torch.distributed.run --nproc_per_node 4 --master_port 2022 classify/train.py --model yolov5s-cls.pt --data imagenet --epochs 5 --img 224 --device 0,1,2,3
 
 Datasets: --data mnist, fashion-mnist, cifar10, cifar100, imagenette, imagewoof, imagenet, or 'path/to/data'
 YOLOv5-cls models: --model yolov5n-cls.pt, yolov5s-cls.pt, yolov5m-cls.pt, yolov5l-cls.pt, yolov5x-cls.pt
@@ -30,7 +30,7 @@
 from torch.cuda import amp
 from tqdm import tqdm
 
-from yolov5.utils.downloads import attempt_donwload_from_hub
+from yolov5.utils.downloads import attempt_download_from_hub
 from yolov5.utils.roboflow import check_dataset_roboflow
 
 FILE = Path(__file__).resolve()
@@ -43,18 +43,12 @@
 from yolov5.models.experimental import attempt_load
 from yolov5.models.yolo import ClassificationModel, DetectionModel
 from yolov5.utils.dataloaders import create_classification_dataloader
-from yolov5.utils.general import (DATASETS_DIR, LOGGER, TQDM_BAR_FORMAT,
- WorkingDirectory, check_git_info,
- check_git_status, check_requirements,
- colorstr, download, increment_path,
- init_seeds, print_args, yaml_save)
+from yolov5.utils.general import (DATASETS_DIR, LOGGER, TQDM_BAR_FORMAT, WorkingDirectory, check_git_info, check_git_status,
+ check_requirements, colorstr, download, increment_path, init_seeds, print_args, yaml_save)
 from yolov5.utils.loggers import GenericLogger
 from yolov5.utils.plots import imshow_cls
-from yolov5.utils.torch_utils import (ModelEMA, model_info,
- reshape_classifier_output, select_device,
- smart_DDP, smart_optimizer,
- smartCrossEntropyLoss,
- torch_distributed_zero_first)
+from yolov5.utils.torch_utils import (ModelEMA, model_info, reshape_classifier_output, select_device, smart_DDP,
+ smart_optimizer, smartCrossEntropyLoss, torch_distributed_zero_first)
 
 LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html
 RANK = int(os.getenv('RANK', -1))
@@ -116,7 +110,7 @@ def train(opt, device):
 
  # Model
  # try to download from hf hub
- result = attempt_donwload_from_hub(opt.model, hf_token=None)
+ result = attempt_download_from_hub(opt.model, hf_token=None)
  if result is not None:
  opt.model = result
  with torch_distributed_zero_first(LOCAL_RANK), WorkingDirectory(ROOT):
@@ -266,7 +260,7 @@ def train(opt, device):
  f"\nPredict: yolov5 classify predict --weights {best} --source im.jpg"
  f"\nValidate: yolov5 classify val --weights {best} --data {data_dir}"
  f"\nExport: yolov5 export --weights {best} --include onnx"
- f"\nPyPi:  model = yolov5.load('custom.pt')"
+ f"\nPython: model = yolov5.load('{best}')"
  f"\nVisualize: https://netron.app\n")
 
  # Plot examples

yolov5/classify/val.py

@@ -43,7 +43,7 @@
 
 @smart_inference_mode()
 def run(
- data=ROOT / '../datasets/mnist', # dataset dir
+ data='../datasets/mnist', # dataset dir
  weights='yolov5s-cls.pt', # model.pt path(s)
  batch_size=None, # batch size
  batch=None, # batch size
@@ -155,14 +155,14 @@ def run(
 
 def parse_opt():
  parser = argparse.ArgumentParser()
- parser.add_argument('--data', type=str, default=ROOT / '../datasets/mnist', help='dataset path')
- parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s-cls.pt', help='model.pt path(s)')
+ parser.add_argument('--data', type=str, default='../datasets/mnist', help='dataset path')
+ parser.add_argument('--weights', nargs='+', type=str, default='yolov5s-cls.pt', help='model.pt path(s)')
  parser.add_argument('--batch-size', type=int, default=128, help='batch size')
  parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=224, help='inference size (pixels)')
  parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
  parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
  parser.add_argument('--verbose', nargs='?', const=True, default=True, help='verbose output')
- parser.add_argument('--project', default=ROOT / 'runs/val-cls', help='save to project/name')
+ parser.add_argument('--project', default='runs/val-cls', help='save to project/name')
  parser.add_argument('--name', default='exp', help='save to project/name')
  parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
  parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')

yolov5/data/hyps/hyp.no-augmentation.yaml

@@ -0,0 +1,35 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+# Hyperparameters when using Albumentations frameworks
+# python train.py --hyp hyp.no-augmentation.yaml
+# See https://github.com/ultralytics/yolov5/pull/3882 for YOLOv5 + Albumentations Usage examples
+
+lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.1 # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937 # SGD momentum/Adam beta1
+weight_decay: 0.0005 # optimizer weight decay 5e-4
+warmup_epochs: 3.0 # warmup epochs (fractions ok)
+warmup_momentum: 0.8 # warmup initial momentum
+warmup_bias_lr: 0.1 # warmup initial bias lr
+box: 0.05 # box loss gain
+cls: 0.3 # cls loss gain
+cls_pw: 1.0 # cls BCELoss positive_weight
+obj: 0.7 # obj loss gain (scale with pixels)
+obj_pw: 1.0 # obj BCELoss positive_weight
+iou_t: 0.20 # IoU training threshold
+anchor_t: 4.0 # anchor-multiple threshold
+# anchors: 3 # anchors per output layer (0 to ignore)
+# this parameters are all zero since we want to use albumentation framework
+fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0 # image HSV-Hue augmentation (fraction)
+hsv_s: 00 # image HSV-Saturation augmentation (fraction)
+hsv_v: 0 # image HSV-Value augmentation (fraction)
+degrees: 0.0 # image rotation (+/- deg)
+translate: 0 # image translation (+/- fraction)
+scale: 0 # image scale (+/- gain)
+shear: 0 # image shear (+/- deg)
+perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0 # image flip up-down (probability)
+fliplr: 0.0 # image flip left-right (probability)
+mosaic: 0.0 # image mosaic (probability)
+mixup: 0.0 # image mixup (probability)
+copy_paste: 0.0 # segment copy-paste (probability)

yolov5/detect.py

@@ -262,7 +262,7 @@ def parse_opt():
 
 def main():
  opt = parse_opt()
- #check_requirements(exclude=('tensorboard', 'thop'))
+ check_requirements(exclude=('tensorboard', 'thop'))
  run(**vars(opt))