def calc_val_loss(val):
loss = []
for i in range(len(val)):
sentence = val[i][0]
tags = val[i][1]
sentence_in = prepare_sentence(sentence, word_to_ix)
targets = prepare_tags(tags, tag_to_ix)
nll = model.neg_log_likelihood(sentence_in, targets)
loss.append(nll.item())
return sum(loss) / len(loss)
features_dim = len(features[0][0])
print("how many additional features: ", features_dim)
EMBEDDING_DIM = 16
HIDDEN_DIM = 16
MAX_CHARS = 10
print("len(char_to_ix): ", len(char_to_ix))
print("len(word_to_ix): ", len(word_to_ix))
print("features_dim: ", features_dim)
model = CNN_BLSTM_CRF(len(char_to_ix), MAX_CHARS, len(word_to_ix), tag_to_ix,
features_dim, EMBEDDING_DIM, HIDDEN_DIM, False)
model.load_state_dict(torch.load("out/lstm_crf_char/epoch20.hdf5"))
# predict on val set
true_tags = []
pred_tags = []
with torch.no_grad():
for i in range(len(examples)):
precheck_sent = prepare_sentence(examples[i][0], word_to_ix)
precheck_tags = prepare_tags(examples[i][1], tag_to_ix)
precheck_features = prepare_features(features[i])
precheck_chars = prepare_char_level_sentence(examples[i][0],
char_to_ix, MAX_CHARS)
predicts = model(precheck_sent, precheck_features, precheck_chars)
print("After training: {}\n ".format(predicts))
true_tags.extend(precheck_tags.tolist())
pred_tags.extend(predicts[1])
print(classification_report(true_tags, pred_tags))
for epoch in range(
EPOCHES
): # again, normally you would NOT do 300 epochs, it is toy data
print("epoch %d" % epoch)
# generate new order of index
idx = np.random.choice(NUM_TO_TRAIN, replace=False, size=NUM_TO_TRAIN)
for i in idx:
sentence = train[i][0]
tags = train[i][1]
# Step 1. Remember that Pytorch accumulates gradients.
# We need to clear them out before each instance
model.zero_grad()
# Step 2. Get our inputs ready for the network, that is,
# turn them into Tensors of word indices.
sentence_in = prepare_sentence(sentence, word_to_ix)
targets = prepare_tags(tags, tag_to_ix)
features_in = prepare_features(features_train[i])
# Step 3. Run our forward pass.
loss = model.neg_log_likelihood(sentence_in, targets, features_in)
# if i % 10 == 0: print("loss: ", loss)
train_loss.append(loss.item())
# Step 4. Compute the loss, gradients, and update the parameters by
# calling optimizer.step()
loss.backward()
optimizer.step()
# print average loss after each iteration
val_loss = calc_val_loss(val)