You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Merge `develop` branch into `master` (#3518) * update ci-testing.yml (#3322) * update ci-testing.yml * update greetings.yml * bring back os matrix * update ci-testing.yml (#3322) * update ci-testing.yml * update greetings.yml * bring back os matrix * Enable direct `--weights URL` definition (#3373) * Enable direct `--weights URL` definition @KalenMike this PR will enable direct --weights URL definition. Example use case: ``` python train.py --weights https://storage.googleapis.com/bucket/dir/model.pt ``` * cleanup * bug fixes * weights = attempt_download(weights) * Update experimental.py * Update hubconf.py * return bug fix * comment mirror * min_bytes * Update tutorial.ipynb (#3368) add Open in Kaggle badge * `cv2.imread(img, -1)` for IMREAD_UNCHANGED (#3379) * Update datasets.py * comment Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com> * COCO evolution fix (#3388) * COCO evolution fix * cleanup * update print * print fix * Create `is_pip()` function (#3391) Returns `True` if file is part of pip package. Useful for contextual behavior modification. ```python def is_pip(): # Is file in a pip package? return 'site-packages' in Path(__file__).absolute().parts ``` * Revert "`cv2.imread(img, -1)` for IMREAD_UNCHANGED (#3379)" (#3395) This reverts commit 21a9607e00f1365b21d8c4bd81bdbf5fc0efea24. * Update FLOPs description (#3422) * Update README.md * Changing FLOPS to FLOPs. Co-authored-by: BuildTools <unconfigured@null.spigotmc.org> * Parse URL authentication (#3424) * Parse URL authentication * urllib.parse.unquote() * improved error handling * improved error handling * remove %3F * update check_file() * Add FLOPs title to table (#3453) * Suppress jit trace warning + graph once (#3454) * Suppress jit trace warning + graph once Suppress harmless jit trace warning on TensorBoard add_graph call. Also fix multiple add_graph() calls bug, now only on batch 0. * Update train.py * Update MixUp augmentation `alpha=beta=32.0` (#3455) Per VOC empirical results https://github.com/ultralytics/yolov5/issues/3380#issuecomment-853001307 by @developer0hye * Add `timeout()` class (#3460) * Add `timeout()` class * rearrange order * Faster HSV augmentation (#3462) remove datatype conversion process that can be skipped * Add `check_git_status()` 5 second timeout (#3464) * Add check_git_status() 5 second timeout This should prevent the SSH Git bug that we were discussing @KalenMike * cleanup * replace timeout with check_output built-in timeout * Improved `check_requirements()` offline-handling (#3466) Improve robustness of `check_requirements()` function to offline environments (do not attempt pip installs when offline). * Add `output_names` argument for ONNX export with dynamic axes (#3456) * Add output names & dynamic axes for onnx export Add output_names and dynamic_axes names for all outputs in torch.onnx.export. The first four outputs of the model will have names output0, output1, output2, output3 * use first output only + cleanup Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai> Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Revert FP16 `test.py` and `detect.py` inference to FP32 default (#3423) * fixed inference bug ,while use half precision * replace --use-half with --half * replace space and PEP8 in detect.py * PEP8 detect.py * update --half help comment * Update test.py * revert space Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Add additional links/resources to stale.yml message (#3467) * Update stale.yml * cleanup * Update stale.yml * reformat * Update stale.yml HUB URL (#3468) * Stale `github.actor` bug fix (#3483) * Explicit `model.eval()` call `if opt.train=False` (#3475) * call model.eval() when opt.train is False call model.eval() when opt.train is False * single-line if statement * cleanup Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com> * check_requirements() exclude `opencv-python` (#3495) Fix for 3rd party or contrib versions of installed OpenCV as in https://github.com/ultralytics/yolov5/issues/3494. * Earlier `assert` for cpu and half option (#3508) * early assert for cpu and half option early assert for cpu and half option * Modified comment Modified comment * Update tutorial.ipynb (#3510) * Reduce test.py results spacing (#3511) * Update README.md (#3512) * Update README.md Minor modifications * 850 width * Update greetings.yml revert greeting change as PRs will now merge to master. Co-authored-by: Piotr Skalski <SkalskiP@users.noreply.github.com> Co-authored-by: SkalskiP <piotr.skalski92@gmail.com> Co-authored-by: Peretz Cohen <pizzaz93@users.noreply.github.com> Co-authored-by: tudoulei <34886368+tudoulei@users.noreply.github.com> Co-authored-by: chocosaj <chocosaj@users.noreply.github.com> Co-authored-by: BuildTools <unconfigured@null.spigotmc.org> Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com> Co-authored-by: Sam_S <SamSamhuns@users.noreply.github.com> Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai> Co-authored-by: edificewang <609552430@qq.com>
3 年之前
3 年之前
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125
  1. """YOLOv5 PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5/
  2. Usage:
  3. import torch
  4. model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
  5. """
  6. import torch
  7. def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
  8. """Creates a specified YOLOv5 model
  9. Arguments:
  10. name (str): name of model, i.e. 'yolov5s'
  11. pretrained (bool): load pretrained weights into the model
  12. channels (int): number of input channels
  13. classes (int): number of model classes
  14. autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
  15. verbose (bool): print all information to screen
  16. device (str, torch.device, None): device to use for model parameters
  17. Returns:
  18. YOLOv5 pytorch model
  19. """
  20. from pathlib import Path
  21. from models.yolo import Model, attempt_load
  22. from utils.general import check_requirements, set_logging
  23. from utils.google_utils import attempt_download
  24. from utils.torch_utils import select_device
  25. check_requirements(requirements=Path(__file__).parent / 'requirements.txt',
  26. exclude=('tensorboard', 'thop', 'opencv-python'))
  27. set_logging(verbose=verbose)
  28. fname = Path(name).with_suffix('.pt') # checkpoint filename
  29. try:
  30. if pretrained and channels == 3 and classes == 80:
  31. model = attempt_load(fname, map_location=torch.device('cpu')) # download/load FP32 model
  32. else:
  33. cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0] # model.yaml path
  34. model = Model(cfg, channels, classes) # create model
  35. if pretrained:
  36. ckpt = torch.load(attempt_download(fname), map_location=torch.device('cpu')) # load
  37. msd = model.state_dict() # model state_dict
  38. csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
  39. csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape} # filter
  40. model.load_state_dict(csd, strict=False) # load
  41. if len(ckpt['model'].names) == classes:
  42. model.names = ckpt['model'].names # set class names attribute
  43. if autoshape:
  44. model = model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS
  45. device = select_device('0' if torch.cuda.is_available() else 'cpu') if device is None else torch.device(device)
  46. return model.to(device)
  47. except Exception as e:
  48. help_url = 'https://github.com/ultralytics/yolov5/issues/36'
  49. s = 'Cache may be out of date, try `force_reload=True`. See %s for help.' % help_url
  50. raise Exception(s) from e
  51. def custom(path='path/to/model.pt', autoshape=True, verbose=True, device=None):
  52. # YOLOv5 custom or local model
  53. return _create(path, autoshape=autoshape, verbose=verbose, device=device)
  54. def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
  55. # YOLOv5-small model https://github.com/ultralytics/yolov5
  56. return _create('yolov5s', pretrained, channels, classes, autoshape, verbose, device)
  57. def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
  58. # YOLOv5-medium model https://github.com/ultralytics/yolov5
  59. return _create('yolov5m', pretrained, channels, classes, autoshape, verbose, device)
  60. def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
  61. # YOLOv5-large model https://github.com/ultralytics/yolov5
  62. return _create('yolov5l', pretrained, channels, classes, autoshape, verbose, device)
  63. def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
  64. # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
  65. return _create('yolov5x', pretrained, channels, classes, autoshape, verbose, device)
  66. def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
  67. # YOLOv5-small-P6 model https://github.com/ultralytics/yolov5
  68. return _create('yolov5s6', pretrained, channels, classes, autoshape, verbose, device)
  69. def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
  70. # YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5
  71. return _create('yolov5m6', pretrained, channels, classes, autoshape, verbose, device)
  72. def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
  73. # YOLOv5-large-P6 model https://github.com/ultralytics/yolov5
  74. return _create('yolov5l6', pretrained, channels, classes, autoshape, verbose, device)
  75. def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
  76. # YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5
  77. return _create('yolov5x6', pretrained, channels, classes, autoshape, verbose, device)
  78. if __name__ == '__main__':
  79. model = _create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True) # pretrained
  80. # model = custom(path='path/to/model.pt') # custom
  81. # Verify inference
  82. import cv2
  83. import numpy as np
  84. from PIL import Image
  85. imgs = ['data/images/zidane.jpg', # filename
  86. 'https://github.com/ultralytics/yolov5/releases/download/v1.0/zidane.jpg', # URI
  87. cv2.imread('data/images/bus.jpg')[:, :, ::-1], # OpenCV
  88. Image.open('data/images/bus.jpg'), # PIL
  89. np.zeros((320, 640, 3))] # numpy
  90. results = model(imgs) # batched inference
  91. results.print()
  92. results.save()