#Add Time Distributed Dense layer
#Time distributed outputs a prediction for each time step
out = TimeDistributed(Dense(num_classes, activation=args.dense_act),
name="dense_layer")(model)
#Finalise model
model = Model(input, out)
#Used for loading pre-saved model weights
if load_weights or trans_learn:
print("Loading Weights")
model.load_weights(args.weights_filepath, by_name=True)
#Compile model
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=["accuracy"])
#Prints a summary of model layers and parameters
#print(model.summary())
#Custom metric calculations
metrics = Metrics_Approx(tag_index=all_labels, k=k)
#Train model
if not trans_learn:
history = model.fit(X_train,
np.array(y_train),
batch_size=batch_size,
epochs=int(args.num_epochs),
verbose=1,
embedding_weight_matrix = getEmbeddingWeightMatrix(embedding_vectors, tokenizer_words.word_index)
print(embedding_weight_matrix.shape)
#build model
input = Input(shape=(X_train.shape[1],))
model = Embedding(input_dim=vocab_size, output_dim=word_embed_size,
input_length=seq_maxlen, weights=[embedding_weight_matrix],
trainable = False) (input)
model = LSTM(100, return_sequences=True)(model)
output = TimeDistributed(Dense(num_tags, activation="softmax"))(model)
model = Model(inputs=input, outputs=output)
print(model.summary())
model.compile(optimizer="rmsprop", loss="categorical_crossentropy", metrics=["accuracy"])
save_weights = ModelCheckpoint('model.h5', monitor='val_loss', save_best_only=True)
model.fit(x=X_train, y=y_train, batch_size=batch_size,
epochs=epochs, validation_data=(X_validation, y_validation), callbacks=[save_weights])
sentences_test, tags_test = load_data(os.path.join(data_dir, 'test.txt'))
X_test = getSequences(sentences_test, tokenizer_words, seq_maxlen, 0)
y_test = getSequences(tags_test, tokenizer_tags, seq_maxlen, tokenizer_tags.word_index['o'])
y_pred = model.predict(X_test)
y_pred_tags, y_test_tags = decode_output(X_test, y_pred, y_test, tokenizer_words, tokenizer_tags, seq_maxlen)
report = classification_report(y_pred=y_pred_tags, y_true=y_test_tags)
