Closed CaptainEven closed 2 years ago
For obtaining feat.npy, calculate features for all images on which you want to train the linear regressor using the frozen encoder module as demonstrated in demo_score.py. Once the features are calculated the regressor can be trained using train_regressor.py.
@pavancm Thanks for replying! By the way, is there any code for reference?
Please refer to demo_feat.py for calculating features. The script calculates features for a single image, for multiple images rerun the script by changing image paths
Hello, I have learned a lot from your discussion, but I have some questions, that is, I repeatedly run demo_feat.py to get feat.npy, then what is the internal format of score, thanks.
score will be a numpy array with dimensions equal to the number of images you are using to train the regressor.
I have made custom data set and labels with Matlab code and the below python scripts:
the loss reduced from 11.7 to 3.4 now after 29 epoches...
How to train the seond stage regressor?