Model mismatch occurs when training student network with own data set

[rogressing]

I used my own data set for training. According to the training steps given by the author, I first pre-trained the supernet and parameters, and then obtained the search file to train the teacher network. **After training the teacher network, I distilled it to the student network again, but when the student network is loaded, The problem occurs as follows**：

And the prompt is that the loaded model and the current model do not match the prompt in the code here:

I would like to ask the author or other experts if they have encountered this kind of problem and how to solve it? And what I am very confused about is that the accuracy of my teacher's network training and verification is very low, only about 29%.

[rogressing]

I used my own data set for training. According to the training steps given by the author, I first pre-trained the supernet and parameters, and then obtained the search file to train the teacher network. After training the teacher network, I distilled it to the student network again, but when the student network is loaded, The problem occurs as follows：

[rogressing]

Thank you ,It's been solved