Convolutional-MLPs改造

Convolutional-MLPs 

人脸识别用，112*112返回7*7特征：

调用代码：

      import torch
      from src import convmlp_s
      if __name__ == '__main__':
          model = convmlp_s(num_classes=100)
          state_dict = torch.load("convmlp_s_imagenet.pth")
          new_state_dict = {}
         for k, v in state_dict.items():
             if 'module.' in k:
                  new_state_dict[k[7:]] = v
             else:
                 if "head" in k:
                     continue
                  new_state_dict[k] = v
          model.load_state_dict(new_state_dict, strict=False)
         # model.load_state_dict(state_dict,strict=False)
          model.eval()
          model_path = "dicenet.pth"
          torch.save(model.state_dict(), model_path)
         import os
         import time
          fsize = os.path.getsize(model_path)
          fsize = fsize / float(1024 * 1024)
         print(f"model size {round(fs
  
 

文章来源: blog.csdn.net，作者：AI视觉网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/120904487