训练后的模型使用报错

[wy353208214]

1. 模型配置

   {
   "lr": 0.1,
   "milestones": [10, 15, 22],
   "gamma": 0.1,
   "epochs": 25,
   "momentum": 0.9,
   "batch_size": 1024,
   "num_classes": 3,
   "input_channel": 3,
   "embedding_size": 128,
   "train_root_path": "./datasets/rgb_image",
   "snapshot_dir_path": "./saved_logs/snapshot",
   "log_path": "./saved_logs/jobs/Anti_Spoofing_2.7_80x80/Oct18_11-21-58 ",
   "board_loss_every": 10,
   "save_every": 30,
   "devices": [0],
   "patch_info": "2.7_80x80",
   "input_size": [80, 80],
   "kernel_size": [5, 5],
   "device": "cpu",
   "ft_height": 10,
   "ft_width": 10,
   "model_path": "./saved_logs/snapshot/Anti_Spoofing_2.7_80x80",
   "job_name": "Anti_Spoofing_2.7_80x80"
   }

生成的模型文件：

2. 这里的模型需要改文件名吗，替换之后报如下错误：

   Traceback (most recent call last):
   File "/Users/steven/Dev_Project/Python/Silent-Face-Anti-Spoofing/test.py", line 111, in <module>
   test(args.image_name, args.model_dir, args.device_id)
   File "/Users/steven/Dev_Project/Python/Silent-Face-Anti-Spoofing/test.py", line 61, in test
   prediction += model_test.predict(img, os.path.join(model_dir, model_name))
   File "/Users/steven/Dev_Project/Python/Silent-Face-Anti-Spoofing/src/anti_spoof_predict.py", line 88, in predict
   self._load_model(model_path)
   File "/Users/steven/Dev_Project/Python/Silent-Face-Anti-Spoofing/src/anti_spoof_predict.py", line 77, in _load_model
   self.model.load_state_dict(new_state_dict)
   File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 2041, in load_state_dict
   raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
   RuntimeError: Error(s) in loading state_dict for MiniFASNet:
       Missing key(s) in state_dict: "conv1.conv.weight", "conv1.bn.weight", "conv1.bn.bias", "conv1.bn.running_mean", "conv1.bn.running_var", "conv1.prelu.weight", "conv2_dw.conv.weight", "conv2_dw.bn.weight", "conv2_dw.bn.bias", "conv2_dw.bn.running_mean", "conv2_dw.bn.running_var", "conv2_dw.prelu.weight", "conv_23.conv.conv.weight", "conv_23.conv.bn.weight", "conv_23.conv.bn.bias", "conv_23.conv.bn.running_mean", "conv_23.conv.bn.running_var", "conv_23.conv.prelu.weight", "conv_23.conv_dw.conv.weight", "conv_23.conv_dw.bn.weight", "conv_23.conv_dw.bn.bias", "conv_23.conv_dw.bn.running_mean", "conv_23.conv_dw.bn.running_var", "conv_23.conv_dw.prelu.weight", "conv_23.project.conv.weight", "conv_23.project.bn.weight", "conv_23.project.bn.bias", "conv_23.project.bn.running_mean", "conv_23.project.bn.running_var", "conv_3.model.0.conv.conv.weight", "conv_3.model.0.conv.bn.weight", "conv_3.model.0.conv.bn.bias", "conv_3.model.0.conv.bn.running_mean", "conv_3.model.0.conv.bn.running_var", "conv_3.model.0.conv.prelu.weight", "conv_3.model.0.conv_dw.conv.weight", "conv_3.model.0.conv_dw.bn.weight", "conv_3.model.0.conv_dw.bn.bias", "conv_3.model.0.conv_dw.bn.running_mean", "conv_3.model.0.conv_dw.bn.running_var", "conv_3.model.0.conv_dw.prelu.weight",

[wy353208214]

参考这里

43

[wy353208214]

训练后，生成的多个model，选用哪个？