iterations += 1
answer = model(batch)
n_correct += (torch.max(answer, 1)[1].view(batch.label.size()).data == batch.label.data).sum()
n_total += batch.batch_size
train_acc = 100. * n_correct/n_total
loss = criterion(answer, batch.label)
loss.backward(); opt.step()
if iterations % args.save_every == 0:
snapshot_prefix = os.path.join(args.save_path, 'snapshot')
snapshot_path = snapshot_prefix + '_acc_{:.4f}_loss_{:.6f}_iter_{}_model.pt'.format(train_acc, loss.data[0], iterations)
torch.save(model, snapshot_path)
for f in glob.glob(snapshot_prefix + '*'):
if f != snapshot_path:
os.remove(f)
if iterations % args.dev_every == 0:
model.eval(); dev_iter.init_epoch()
n_dev_correct, dev_loss = 0, 0
for dev_batch_idx, dev_batch in enumerate(dev_iter):
answer = model(dev_batch)
n_dev_correct += (torch.max(answer, 1)[1].view(dev_batch.label.size()).data == dev_batch.label.data).sum()
dev_loss = criterion(answer, dev_batch.label)
dev_acc = 100. * n_dev_correct / len(dev)
print(dev_log_template.format(time.time()-start,
epoch, iterations, 1+batch_idx, len(train_iter),
100. * (1+batch_idx) / len(train_iter), loss.data[0], dev_loss.data[0], train_acc, dev_acc))
if dev_acc > best_dev_acc:
best_dev_acc = dev_acc
snapshot_prefix = os.path.join(args.save_path, 'best_snapshot')
snapshot_path = snapshot_prefix + '_devacc_{}_devloss_{}__iter_{}_model.pt'.format(dev_acc, dev_loss.data[0], iterations)
torch.save(model, snapshot_path)
for f in glob.glob(snapshot_prefix + '*'):
# checkpoint model periodically
if iterations % args.save_every == 0:
snapshot_prefix = os.path.join(args.save_path, 'snapshot')
snapshot_path = snapshot_prefix + '_acc_{:.4f}_loss_{:.6f}_iter_{}_model.pt'.format(
train_acc, loss.item(), iterations)
torch.save(model, snapshot_path)
for f in glob.glob(snapshot_prefix + '*'):
if f != snapshot_path:
os.remove(f)
# evaluate performance on validation set periodically
if iterations % args.dev_every == 0:
# switch model to evaluation mode
model.eval()
dev_iter.init_epoch()
# calculate accuracy on validation set
n_dev_correct, dev_loss = 0, 0
with torch.no_grad():
for dev_batch_idx, dev_batch in enumerate(dev_iter):
answer = model(dev_batch)
n_dev_correct += (torch.max(answer, 1)[1].view(
dev_batch.label.size()) == dev_batch.label
).sum().item()
dev_loss = criterion(answer, dev_batch.label)
dev_acc = 100. * n_dev_correct / len(dev)
print(
dev_log_template.format(
loss.backward(); opt.step()
# checkpoint model periodically
if iterations % args.save_every == 0:
snapshot_prefix = os.path.join(args.save_path, 'snapshot')
snapshot_path = snapshot_prefix + '_acc_{:.4f}_loss_{:.6f}_iter_{}_model.pt'.format(train_acc, loss.item(), iterations)
torch.save(model, snapshot_path)
for f in glob.glob(snapshot_prefix + '*'):
if f != snapshot_path:
os.remove(f)
# evaluate performance on validation set periodically
if iterations % args.dev_every == 0:
# switch model to evaluation mode
model.eval(); dev_iter.init_epoch()
# calculate accuracy on validation set
n_dev_correct, dev_loss = 0, 0
with torch.no_grad():
for dev_batch_idx, dev_batch in enumerate(dev_iter):
answer = model(dev_batch)
n_dev_correct += (torch.max(answer, 1)[1].view(dev_batch.label.size()) == dev_batch.label).sum().item()
dev_loss = criterion(answer, dev_batch.label)
dev_acc = 100. * n_dev_correct / len(dev)
print(dev_log_template.format(time.time()-start,
epoch, iterations, 1+batch_idx, len(train_iter),
100. * (1+batch_idx) / len(train_iter), loss.item(), dev_loss.item(), train_acc, dev_acc))
# update best valiation set accuracy
