Python Deep Learning Projects

Training the LSTM model

Now that we've established our LSTM intuition and built the model, let's train it as follows:

EARLY_STOPPING, CURRENT_CHECKPOINT, CURRENT_ACC, EPOCH = 5, 0, 0, 0while True:    lasttime = time.time()    if CURRENT_CHECKPOINT == EARLY_STOPPING:        print('break epoch:%d\n'%(EPOCH))        break            train_acc, train_loss, test_acc, test_loss = 0, 0, 0, 0    for i in range(0, (len(train_X) // batch_size) * batch_size, batch_size):        batch_x = str_idx(train_X[i:i+batch_size],dictionary,maxlen)        acc, loss, _ = sess.run([model.accuracy, model.cost, model.optimizer],                            feed_dict = {model.X : batch_x, model.Y : train_onehot[i:i+batch_size]})        train_loss += loss        train_acc += acc     for i in range(0, (len(test_X) // batch_size) * batch_size, batch_size): ...