Basketball coaches often sketch plays on a whiteboard to help players get the ball through the net. A new AI model predicts how opponents would respond to these tactics.
I used the following commands to train, but the training time was much longer than expected. How did you train？ python Train_Triple.py --folder_path='tmp' --data_path='data' #7
“Then, we train the critic for 5 iterations before training the generator once, and with every 20 epochs we update the critic 10 iterations per generator iteration, as this strategy keeps the critic remaining strong. We stop the training process when the critics start overfitting.”
Are these operations done in train.py？
chychen
commented
2 years ago
“Then, we train the critic for 5 iterations before training the generator once, and with every 20 epochs we update the critic 10 iterations per generator iteration, as this strategy keeps the critic remaining strong. We stop the training process when the critics start overfitting.”
Are these operations done in train.py？