model = LSTM()
model.compile(optimizer="adam",
loss="categorical_crossentropy",
metrics=["accuracy"])
cp_path = "training_2/cp-{epoch:04d}.h5py"
cp_dir = os.path.dirname(cp_path)
# Create a callback that saves the model's weights
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=cp_path,
verbose=1,
save_weights_only=True,
period=1)
log_dir = "./runs"
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir)
print("Initiating Training.")
# model.fit(train_ds, epochs = 10, validation_data = val_ds, steps_per_epoch = train_ct, validation_steps = val_ct, shuffle = True, callbacks = [cp_callback])
model.fit(train_ds,
epochs=10,
validation_data=val_ds,
steps_per_epoch=train_ct,
validation_steps=val_ct,
shuffle=True,
callbacks=[cp_callback, tensorboard_callback])
model.save_weights("./training_1/model.h5py")
print("Finished Training.")
# export PATH=/usr/local/cuda-10.0/bin:/usr/local/cuda-10.0/NsightCompute-1.0${PATH:+:${PATH}}
# export LD_LIBRARY_PATH=/usr/local/cuda-10.0/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
adam = tf.keras.optimizers.Adam(lr=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08)
rmsprop = tf.keras.optimizers.RMSprop(lr=0.001, rho=0.9, epsilon=1e-06)
lstm.compile(loss='categorical_crossentropy', optimizer=adam)
if MODE == 'train':
lstm.fit(input_train,
tr_one_hot,
batch_size=32,
epochs=20,
verbose=1,
shuffle=True)
# Save model
lstm.save_weights(r'./saved_model/LSTM/lstm_20.HDF5')
print('model saved.')
else:
# Load model
lstm.load_weights(r'./saved_model/LSTM/lstm_20.HDF5')
print('model loaded.')
pred = lstm.predict(input_validation)
pred = np.argmax(pred, axis=1)
print('On validate data: ')
metrics(y_test, pred)
pred_tr = lstm.predict(input_train)
pred_tr = np.argmax(pred_tr, axis=1)
print('On train data: ')
metrics(y_train, pred_tr)
