用kafka接收消息
No puede seleccionar más de 25 temas Los temas deben comenzar con una letra o número, pueden incluir guiones ('-') y pueden tener hasta 35 caracteres de largo.

135 líneas
5.0KB

  1. # YOLOv5 experimental modules
  2. import numpy as np
  3. import torch
  4. import torch.nn as nn
  5. from models.common import Conv, DWConv
  6. from utils.google_utils import attempt_download
  7. class CrossConv(nn.Module):
  8. # Cross Convolution Downsample
  9. def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
  10. # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
  11. super(CrossConv, self).__init__()
  12. c_ = int(c2 * e) # hidden channels
  13. self.cv1 = Conv(c1, c_, (1, k), (1, s))
  14. self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
  15. self.add = shortcut and c1 == c2
  16. def forward(self, x):
  17. return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
  18. class Sum(nn.Module):
  19. # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
  20. def __init__(self, n, weight=False): # n: number of inputs
  21. super(Sum, self).__init__()
  22. self.weight = weight # apply weights boolean
  23. self.iter = range(n - 1) # iter object
  24. if weight:
  25. self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True) # layer weights
  26. def forward(self, x):
  27. y = x[0] # no weight
  28. if self.weight:
  29. w = torch.sigmoid(self.w) * 2
  30. for i in self.iter:
  31. y = y + x[i + 1] * w[i]
  32. else:
  33. for i in self.iter:
  34. y = y + x[i + 1]
  35. return y
  36. class GhostConv(nn.Module):
  37. # Ghost Convolution https://github.com/huawei-noah/ghostnet
  38. def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups
  39. super(GhostConv, self).__init__()
  40. c_ = c2 // 2 # hidden channels
  41. self.cv1 = Conv(c1, c_, k, s, None, g, act)
  42. self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
  43. def forward(self, x):
  44. y = self.cv1(x)
  45. return torch.cat([y, self.cv2(y)], 1)
  46. class GhostBottleneck(nn.Module):
  47. # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
  48. def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride
  49. super(GhostBottleneck, self).__init__()
  50. c_ = c2 // 2
  51. self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1), # pw
  52. DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw
  53. GhostConv(c_, c2, 1, 1, act=False)) # pw-linear
  54. self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
  55. Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
  56. def forward(self, x):
  57. return self.conv(x) + self.shortcut(x)
  58. class MixConv2d(nn.Module):
  59. # Mixed Depthwise Conv https://arxiv.org/abs/1907.09595
  60. def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
  61. super(MixConv2d, self).__init__()
  62. groups = len(k)
  63. if equal_ch: # equal c_ per group
  64. i = torch.linspace(0, groups - 1E-6, c2).floor() # c2 indices
  65. c_ = [(i == g).sum() for g in range(groups)] # intermediate channels
  66. else: # equal weight.numel() per group
  67. b = [c2] + [0] * groups
  68. a = np.eye(groups + 1, groups, k=-1)
  69. a -= np.roll(a, 1, axis=1)
  70. a *= np.array(k) ** 2
  71. a[0] = 1
  72. c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
  73. self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
  74. self.bn = nn.BatchNorm2d(c2)
  75. self.act = nn.LeakyReLU(0.1, inplace=True)
  76. def forward(self, x):
  77. return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
  78. class Ensemble(nn.ModuleList):
  79. # Ensemble of models
  80. def __init__(self):
  81. super(Ensemble, self).__init__()
  82. def forward(self, x, augment=False):
  83. y = []
  84. for module in self:
  85. y.append(module(x, augment)[0])
  86. # y = torch.stack(y).max(0)[0] # max ensemble
  87. # y = torch.stack(y).mean(0) # mean ensemble
  88. y = torch.cat(y, 1) # nms ensemble
  89. return y, None # inference, train output
  90. def attempt_load(weights, map_location=None):
  91. # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
  92. model = Ensemble()
  93. for w in weights if isinstance(weights, list) else [weights]:
  94. attempt_download(w)
  95. ckpt = torch.load(w, map_location=map_location) # load
  96. model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
  97. # Compatibility updates
  98. for m in model.modules():
  99. if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
  100. m.inplace = True # pytorch 1.7.0 compatibility
  101. elif type(m) is Conv:
  102. m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
  103. if len(model) == 1:
  104. return model[-1] # return model
  105. else:
  106. print('Ensemble created with %s\n' % weights)
  107. for k in ['names', 'stride']:
  108. setattr(model, k, getattr(model[-1], k))
  109. return model # return ensemble