# Initialize models and start training
encoder = CharCNN(char_vocab, args.hidden_size)
decoder = DecoderRNN(args.hidden_size, numOutputClass)
encoder_optimizer = torch.optim.Adam(encoder.parameters(),
lr=args.learning_rate)
decoder_optimizer = torch.optim.Adam(decoder.parameters(),
lr=args.learning_rate)
criterion = nn.CrossEntropyLoss()
if args.cuda:
criterion.cuda()
encoder.cuda()
decoder.cuda()
start = time.time()
all_losses = []
loss_avg = 0
try:
print("Training for %d epochs..." % args.n_epochs)
numMiniBatches = len(linesInTrain) / args.batch_size
for epoch in tqdm(range(1, args.n_epochs + 1)):
minibatchesSinceLastPrint = 0
for j in range(0, len(linesInTrain), args.batch_size):
batch_size = args.batch_size
if j + args.batch_size >= len(linesInTrain):
#number of input char types
char_vocab = len(string.printable)
# number of output classes = vocab size
numOutputClass = len(labelCorpus.dictionary)
# Initialize models and start training
decoder = CharCNN(char_vocab, args.hidden_size, numOutputClass)
decoder_optimizer = torch.optim.Adam(decoder.parameters(),
lr=args.learning_rate)
criterion = nn.CrossEntropyLoss()
if args.cuda:
decoder.cuda()
start = time.time()
all_losses = []
loss_avg = 0
try:
print("Training for %d epochs..." % args.n_epochs)
for epoch in tqdm(range(1, args.n_epochs + 1)):
loss = train(*random_training_set(args.batch_size, linesInTrain))
loss_avg += loss
if epoch % args.print_every == 0:
val_loss = evaluate(
args.batch_size, linesInValid
) # test the model on validation data to check performance