In my understanding an epoch is an arbitrarily often repeated run over the whole dataset, which in turn is processed in parts, so called batches. After each train_on_batch
a loss is calculated, the weights are updated and the next batch will get better results. These losses are indicators of the quality and learning state of my to NNs.
In several sources the loss is calculated (and printed) per epoch. Therefore I am not sure if I am doing this right.
At the moment my GAN looks like this:
for epoch:
for batch:
fakes = generator.predict_on_batch(batch)
dlc = discriminator.train_on_batch(batch, ..)
dlf = discriminator.train_on_batch(fakes, ..)
dis_loss_total = 0.5 * np.add(dlc, dlf)
g_loss = gan.train_on_batch(batch,..)
# save losses to array to work with later
These losses are for each batch. How do I get them for an epoch? As an aside: Do I need losses for an epoch, what for?
If you would like to calculate the loss for each epoch, divide the running_loss by the number of batches and append it to train_losses in each epoch. Accuracy is the number of correct classifications / the total amount of classifications.
"loss" refers to the loss value over the training data after each epoch. This is what the optimization process is trying to minimize with the training so, the lower, the better. "accuracy" refers to the ratio between correct predictions and the total number of predictions in the training data. The higher, the better.
Generally batch size of 32 or 25 is good, with epochs = 100 unless you have large dataset. in case of large dataset you can go with batch size of 10 with epochs b/w 50 to 100. Again the above mentioned figures have worked fine for me. Value for batch size should be (preferred) in powers of 2.
The batch size is a number of samples processed before the model is updated. The number of epochs is the number of complete passes through the training dataset. The size of a batch must be more than or equal to one and less than or equal to the number of samples in the training dataset.
There is no direct way to compute the loss for an epoch. Actually, the loss of an epoch is usually defined as the average of the loss of batches in that epoch. So you can accumulate the loss values during an epoch and at the end divide it by the number of batches in the epoch:
epoch_loss = []
for epoch in range(n_epochs):
acc_loss = 0.
for batch in range(n_batches):
# do the training
loss = model.train_on_batch(...)
acc_loss += loss
epoch_loss.append(acc_loss / n_batches)
As for the other question, one usage of epoch loss might be to use it as an indicator to stop the training (however, the validation loss is usually used for that, not the training loss).
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With