def train_toy_example():
# embedding_layer = Embedding(1000, 64)
max_feature = 10000
maxlen = 20
(x_train, y_train), (x_test,
y_test) = imdb.load_data(num_words=max_feature)
x_train = preprocessing.sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = preprocessing.sequence.pad_sequences(x_test, maxlen=maxlen)
model = Sequential()
# 10000 => max vocab size, 8 => Embedding vector length, input_length => len(sample)
# output will be (len(sampleS), len(sample), 8)
# https://keras.io/api/layers/core_layers/embedding/
model.add(Embedding(10000, 8, input_length=maxlen))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['acc'])
model.summary()
history = model.fit(x_train,
y_train,
epochs=10,
batch_size=32,
validation_split=.2)
plot_acc_loss(history, 10)
def train_model_pretrained_embedding(model, save=False):
model.layers[0].set_weights([embedding_matrix])
model.layers[0].trainable = False
model, history = compile_fit(model)
if save:
model.save_weights('pre_trained_glove_model.h5')
plot_acc_loss(history, epochs)
def train_plot_LSTM():
model = Sequential()
model.add(Embedding(max_features, 32))
model.add(LSTM(32))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])
history = model.fit(input_train, y_train, epochs=10, batch_size=128, validation_split=.2)
plot_acc_loss(history, epochs)
def try_reverse_order():
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
x_train = [x[::-1] for x in x_train]
x_test = [x[::-1] for x in x_test]
x_train = preprocessing.sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = preprocessing.sequence.pad_sequences(x_test, maxlen=maxlen)
model = Sequential()
model.add(Embedding(max_features, 128))
model.add(LSTM(32))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])
history = model.fit(x_train, y_train, epochs=10, batch_size=128, validation_split=.2)
plot_acc_loss(history, 10)
def train_model_fresh_embedding(model, save=False):
model, history = compile_fit(model)
if save:
model.save_weights('fresh_embedding_model.h5')
plot_acc_loss(history, epochs)