(batch_y.shape[0], 1), dtype=np.int) * ch2ind['<go>'],
batch_y[:, :-1]),
axis=1),
y_real_len:
by,
x_real_len:
bx,
y_max_len:
max(by)
})
train_loss_list.append(loss)
#tmp_train_acc = cal_acc(tran,batch_y)
#train_acc_list.append(tmp_train_acc)
exp_loss = loss if exp_loss == None else alpha * exp_loss + (
1 - alpha) * loss
pb.info = "iter {} loss:{} lr:{}".format(i + 1, exp_loss, lr)
with open('val/{}/train_loss.txt'.format(model_path), 'a') as whdl:
whdl.write("{}\t{}\t{}\n".format(one_epoch, one_batch, loss))
val_step = int(worksum / 4)
if j % val_step == 0 and j != 0:
test_loss, test_acc, bleu_score, predict_list, target_list, source_list = calc_test_loss(
test_x[::4], test_y[::4])
_, train_acc, train_bleu_score, train_predict_list, train_target_list, train_source_list = calc_test_loss(
train_x[::1000], train_y[::1000])
predict_texts = get_all_text(predict_list)
target_texts = get_all_text(target_list)
source_texts = get_all_en_text(source_list)
train_predict_texts = get_all_text(train_predict_list)
train_target_texts = get_all_text(train_target_list)
train_source_texts = get_all_en_text(train_source_list)
for one_epoch in range(1, 10):
pb = ProgressBar(worksum=MAX_SEQUENCE_LENGTH)
pb.startjob()
for one_batch in range(0, len(X_train), batch_size):
batch_x, batch_y = gen.__next__()
batch_x_len = np.asarray([len(x) for x in batch_x])
batch_lr = beginning_lr
_, batch_loss = sess.run([optimizer, loss],
feed_dict={
X: batch_x,
y: batch_y,
X_len: batch_x_len,
learning_rate: batch_lr
})
pb.info = "EPOCH {} batch{} lr {} loss {}".format(one_epoch, one_batch,
batch_lr, batch_loss)
pb.complete(batch_size)
losses.append(batch_loss)
batch_predict = sess.run(model_pred, feed_dict={
X: test_X,
X_len: test_X_len
})[:, 0]
batch_predict = [(1 if x > 0.5 else 0) for x in batch_predict]
# In[]
# =============================================================================
# Run Batch Prediction
# =============================================================================
pd.DataFrame(losses).plot()
df = pd.DataFrame({'id': testData.id, 'pred': batch_predict})
pred_path = os.path.join(dir_path, 'TF_RNN.csv')
batch_x, batch_y_ori, a, t, s = voice_flow_train.next()['data']
batch_y = sparse_tuple_from(batch_y_ori)
batch_seq_len = [i // 2 for i in s]
batch_target_len = [len(i) for i in batch_y_ori]
# learning rate decay strategy
batch_lr = begining_learning_rate * 10**-(one_epoch // DECAY_EPOCH)
step_dis, _, step_loss, step_summary, step_value = sess.run(
[dis, train_op, loss, summary_op, global_step],
feed_dict={
input_sound: batch_x,
targets: batch_y,
learning_rate: batch_lr,
voicelength: batch_seq_len,
seqlength: batch_target_len,
max_grad: clip_norm,
training: True
})
expdis.update(step_dis)
exploss.update(step_loss)
pb.info = "EPOCH {} STEP {} LOSS {} DIS {} ".format(
one_epoch, one_batch, exploss.getval(), expdis.getval())
train_summary_writer.add_summary(step_summary, step_value)
pb.complete(BATCH_SIZE)
print()
saver = tf.train.Saver(tf.global_variables())
saver.save(sess, "models/{}/model_{}".format(model_name, one_epoch))
