Use the Architecture of the pre-trained model – What we can do is that we use architecture of the model while we initialize all the weights randomly and train the model according to our dataset again. Train some layers while freeze others – Another way to use a pre-trained model is to train is partially.
To load model weights, you need to create an instance of the same model first, and then load the parameters using load_state_dict() method. be sure to call model. eval() method before inferencing to set the dropout and batch normalization layers to evaluation mode.