Você não pode selecionar mais de 25 tópicos Os tópicos devem começar com uma letra ou um número, podem incluir traços ('-') e podem ter até 35 caracteres.

autobatch.py 2.0KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556
  1. # YOLOv5 🚀 by Ultralytics, GPL-3.0 license
  2. """
  3. Auto-batch utils
  4. """
  5. from copy import deepcopy
  6. import numpy as np
  7. import torch
  8. from torch.cuda import amp
  9. from utils.general import colorstr
  10. from utils.torch_utils import profile
  11. def check_train_batch_size(model, imgsz=640):
  12. # Check YOLOv5 training batch size
  13. with amp.autocast():
  14. return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size
  15. def autobatch(model, imgsz=640, fraction=0.9, batch_size=16):
  16. # Automatically estimate best batch size to use `fraction` of available CUDA memory
  17. # Usage:
  18. # import torch
  19. # from utils.autobatch import autobatch
  20. # model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False)
  21. # print(autobatch(model))
  22. prefix = colorstr('autobatch: ')
  23. print(f'{prefix}Computing optimal batch size for --imgsz {imgsz}')
  24. device = next(model.parameters()).device # get model device
  25. if device.type == 'cpu':
  26. print(f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}')
  27. return batch_size
  28. d = str(device).upper() # 'CUDA:0'
  29. t = torch.cuda.get_device_properties(device).total_memory / 1024 ** 3 # (GB)
  30. r = torch.cuda.memory_reserved(device) / 1024 ** 3 # (GB)
  31. a = torch.cuda.memory_allocated(device) / 1024 ** 3 # (GB)
  32. f = t - (r + a) # free inside reserved
  33. print(f'{prefix}{d} {t:.3g}G total, {r:.3g}G reserved, {a:.3g}G allocated, {f:.3g}G free')
  34. batch_sizes = [1, 2, 4, 8, 16]
  35. try:
  36. img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes]
  37. y = profile(img, model, n=3, device=device)
  38. except Exception as e:
  39. print(f'{prefix}{e}')
  40. y = [x[2] for x in y if x] # memory [2]
  41. batch_sizes = batch_sizes[:len(y)]
  42. p = np.polyfit(batch_sizes, y, deg=1) # first degree polynomial fit
  43. b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size)
  44. print(f'{prefix}Using colorstr(batch-size {b}) for {d} {t * fraction:.3g}G/{t:.3g}G ({fraction * 100:.0f}%)')
  45. return b