Last active
August 4, 2019 16:56
-
-
Save samarth-agrawal-86/4aea7efda2e400741da53fa22300ad1f to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# loss and optimization functions | |
lr=0.001 | |
criterion = nn.BCELoss() | |
optimizer = torch.optim.Adam(net.parameters(), lr=lr) | |
# training params | |
epochs = 4 # 3-4 is approx where I noticed the validation loss stop decreasing | |
counter = 0 | |
print_every = 100 | |
clip=5 # gradient clipping | |
# move model to GPU, if available | |
if(train_on_gpu): | |
net.cuda() | |
net.train() | |
# train for some number of epochs | |
for e in range(epochs): | |
# initialize hidden state | |
h = net.init_hidden(batch_size) | |
# batch loop | |
for inputs, labels in train_loader: | |
counter += 1 | |
if(train_on_gpu): | |
inputs, labels = inputs.cuda(), labels.cuda() | |
# Creating new variables for the hidden state, otherwise | |
# we'd backprop through the entire training history | |
h = tuple([each.data for each in h]) | |
# zero accumulated gradients | |
net.zero_grad() | |
# get the output from the model | |
inputs = inputs.type(torch.LongTensor) | |
output, h = net(inputs, h) | |
# calculate the loss and perform backprop | |
loss = criterion(output.squeeze(), labels.float()) | |
loss.backward() | |
# `clip_grad_norm` helps prevent the exploding gradient problem in RNNs / LSTMs. | |
nn.utils.clip_grad_norm_(net.parameters(), clip) | |
optimizer.step() | |
# loss stats | |
if counter % print_every == 0: | |
# Get validation loss | |
val_h = net.init_hidden(batch_size) | |
val_losses = [] | |
net.eval() | |
for inputs, labels in valid_loader: | |
# Creating new variables for the hidden state, otherwise | |
# we'd backprop through the entire training history | |
val_h = tuple([each.data for each in val_h]) | |
if(train_on_gpu): | |
inputs, labels = inputs.cuda(), labels.cuda() | |
inputs = inputs.type(torch.LongTensor) | |
output, val_h = net(inputs, val_h) | |
val_loss = criterion(output.squeeze(), labels.float()) | |
val_losses.append(val_loss.item()) | |
net.train() | |
print("Epoch: {}/{}...".format(e+1, epochs), | |
"Step: {}...".format(counter), | |
"Loss: {:.6f}...".format(loss.item()), | |
"Val Loss: {:.6f}".format(np.mean(val_losses))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment