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.

hubconf.py 5.2KB

4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
3 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
4 jaren geleden
3 jaren geleden
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. from pathlib import Path
  7. import torch
  8. from models.yolo import Model, attempt_load
  9. from utils.general import check_requirements, set_logging
  10. from utils.google_utils import attempt_download
  11. from utils.torch_utils import select_device
  12. dependencies = ['torch', 'yaml']
  13. check_requirements(Path(__file__).parent / 'requirements.txt', exclude=('tensorboard', 'pycocotools', 'thop'))
  14. def create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
  15. """Creates a specified YOLOv5 model
  16. Arguments:
  17. name (str): name of model, i.e. 'yolov5s'
  18. pretrained (bool): load pretrained weights into the model
  19. channels (int): number of input channels
  20. classes (int): number of model classes
  21. autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
  22. verbose (bool): print all information to screen
  23. Returns:
  24. YOLOv5 pytorch model
  25. """
  26. set_logging(verbose=verbose)
  27. fname = Path(name).with_suffix('.pt') # checkpoint filename
  28. try:
  29. if pretrained and channels == 3 and classes == 80:
  30. model = attempt_load(fname, map_location=torch.device('cpu')) # download/load FP32 model
  31. else:
  32. cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0] # model.yaml path
  33. model = Model(cfg, channels, classes) # create model
  34. if pretrained:
  35. attempt_download(fname) # download if not found locally
  36. ckpt = torch.load(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') # default to GPU if available
  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):
  52. # YOLOv5 custom or local model
  53. return create(path, autoshape=autoshape, verbose=verbose)
  54. def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
  55. # YOLOv5-small model https://github.com/ultralytics/yolov5
  56. return create('yolov5s', pretrained, channels, classes, autoshape, verbose)
  57. def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
  58. # YOLOv5-medium model https://github.com/ultralytics/yolov5
  59. return create('yolov5m', pretrained, channels, classes, autoshape, verbose)
  60. def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
  61. # YOLOv5-large model https://github.com/ultralytics/yolov5
  62. return create('yolov5l', pretrained, channels, classes, autoshape, verbose)
  63. def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
  64. # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
  65. return create('yolov5x', pretrained, channels, classes, autoshape, verbose)
  66. def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
  67. # YOLOv5-small-P6 model https://github.com/ultralytics/yolov5
  68. return create('yolov5s6', pretrained, channels, classes, autoshape, verbose)
  69. def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
  70. # YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5
  71. return create('yolov5m6', pretrained, channels, classes, autoshape, verbose)
  72. def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
  73. # YOLOv5-large-P6 model https://github.com/ultralytics/yolov5
  74. return create('yolov5l6', pretrained, channels, classes, autoshape, verbose)
  75. def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
  76. # YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5
  77. return create('yolov5x6', pretrained, channels, classes, autoshape, verbose)
  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()