In train.py or train_unet.py, the default epoch size is 20000000.
But, you trained model 20 epochs with LRS2 dataset in the paper.
How many epochs do I have to train the model if I want to get accuracy like your proposed trained weights?
Please train for around 20 epochs on LRS2. We have set that so that we can just stop the training whenever desired (as convergence will be different for different datasets).
In train.py or train_unet.py, the default epoch size is 20000000. But, you trained model 20 epochs with LRS2 dataset in the paper. How many epochs do I have to train the model if I want to get accuracy like your proposed trained weights?
Thanks!