神经网络个人总结

 

darknet：网络挺快，但是权重比较大，占用内存比较多 

darknet53 512 p100 gpu 15ms

 

ShuffleNetV2 

512 p100 gpu 15ms，但是权重比较小，占用内存小。

 

dla_34 p100 512 512 23ms 训练比较慢

 

if __name__ == '__main__':
  arch="dla_34"
  head_conv=256
  heads = {'hm': 5, 'wh': 2, 'hps': 2}
  model = create_model(arch, heads, head_conv)

  model.cuda()
  model.eval()
  x = torch.rand(1, 3, 512, 512).cuda()
  for i in range(10):
    t1 = time.time()
    # out3, out4, out5 = model(x)
    out3 = model(x)
    # print(out3)
    # print(out3.size())
    # print(out4.size())
    # print(out5.size())
    cnt = time.time() - t1
    print(cnt)