search

yeguixin / captcha_solver

Source code for ACM CCS 2018
145 stars 57 forks source link

Lenet model overfitting #18

Open thograce opened 4 years ago

thograce commented 4 years ago

Your paper used 200,000 synthetic images to train the LeNet5 model. I used the same number of data sets, but my accuracy and loss are declining, and I think there is an overfitting problem. Have you encountered this problem?

yeguixin commented 4 years ago

Hi, I also have encountered this phenomenon. The accuracy output during the training process may be inaccurate because the number of test data is small. You can test all the trained model one by one using more test data and select the best model.