def test_train_meta_learner(backprop_depth: int, batch_size: int,
lr_bias: float) -> Model:
"""
:return: Keras Model for Meta-Learner used during training of Meta-Learner using BPTT
"""
# same inputs as in other models to use same API
grads_input = Input(batch_shape=(batch_size, backprop_depth, 1),
name='grads_input_train')
loss_input = Input(batch_shape=(batch_size, backprop_depth, 1),
name='loss_input_train')
params_input = Input(batch_shape=(batch_size, 1),
name='params_input_train')
full_input = Concatenate(
axis=-1, name='concat_grads_loss')([grads_input, loss_input])
lstm = LSTM(2, name='lstm')
lstm.trainable = False
dummy_lstm = lstm(full_input)
lr = Dense(1,
name='dense',
kernel_initializer=Constant(value=0.0),
bias_initializer=Constant(value=lr_bias),
activation='sigmoid')(dummy_lstm)
final_grad = Lambda(lambda x: x[:, -1, :],
name='final_grad_input')(grads_input)
right = Multiply(name='output_right')([lr, final_grad])
output = Subtract(name='output')([params_input, right])
return Model(inputs=[grads_input, loss_input, params_input],
outputs=output)
def test_predict_meta_learner(learner: Model, backprop_depth: int,
batch_size: int) -> MetaPredictLearnerModel:
"""
:return: MetaPredictLearnerModel for Meta-Learner used during training of Meta-Learner using BPTT
"""
grads_tensor = K.concatenate([
K.flatten(g) for g in K.gradients(learner.total_loss,
learner._collected_trainable_weights)
],
axis=0)
# reshape loss/grads so they have shape required for LSTM: (batch_size, 1, 1)
grads_tensor = K.reshape(grads_tensor, shape=(batch_size, 1, 1))
loss_tensor = tf.fill(value=learner.total_loss, dims=[batch_size, 1, 1])
grads_input = Input(tensor=grads_tensor,
batch_shape=(batch_size, 1, 1),
name='grads_input_predict')
loss_input = Input(tensor=loss_tensor,
batch_shape=(batch_size, 1, 1),
name='loss_input_predict')
params_tensor = K.concatenate(
[K.flatten(p) for p in learner._collected_trainable_weights])
params_input = Input(tensor=params_tensor,
batch_shape=(batch_size, ),
name='params_input_predict')
full_lstm_input = Concatenate(
axis=-1, name='concat_grads_loss')([grads_input, loss_input])
lstm = LSTM(2, stateful=True, return_state=True, name='lstm')
lstm.trainable = False
lstm_full_output = lstm(full_lstm_input)
lstm_output = lstm_full_output[0]
states_outputs = lstm_full_output[1:]
lr = Dense(1,
name='learning_rate_dense',
kernel_initializer=Constant(value=0.0),
bias_initializer=Constant(value=0.0),
activation='sigmoid')(lstm_output)
flat_grads = Flatten(name='flatten_grads_input')(grads_input)
right = Multiply(name='output_right')([lr, flat_grads])
output = Subtract(name='output')([params_input, right])
return MetaPredictLearnerModel(
learner=learner,
train_mode=True,
backpropagation_depth=backprop_depth,
inputs=[grads_input, loss_input, params_input],
input_tensors=[grads_tensor, loss_tensor, params_tensor],
states_outputs=states_outputs,
outputs=output)
texts_lstm = LSTM(lstm_size, return_sequences=True, input_shape=(maxlen, len(word_indices)),
dropout=dropout_rate, recurrent_dropout=dropout_rate, name='LSTM_input')(texts_input)
layer_0 = Dropout(dropout_rate)(concatenate(
[topic_embed, video_embed, texts_lstm], axis=2, name='merged_input'))
layer_1 = LSTM(lstm_size, return_sequences=False, input_shape=(lstm_size,),
dropout=dropout_rate, recurrent_dropout=dropout_rate, name='meta-LSTM')(layer_0)
layer_2 = Dense(len(word_indices), name='word_selector')(layer_1)
output = Activation('softmax', name='output')(layer_2)
topic_input.trainable = True
topic_embed.trainable = True
video_input.trainable = True
video_embed.trainable = True
texts_input.trainable = True
texts_lstm.trainable = True
layer_1.trainable = True
model_video = Model(inputs=[topic_input, video_input, texts_input], outputs=[output])
model_video.compile(loss='categorical_crossentropy', optimizer=optimiser)
params = np.repeat(np.atleast_2d(video_param), maxlen, axis=0)
Writing = True
while Writing or Loop:
model_video.load_weights(brain_file)
# glitch_layer = model_video.layers[10].get_weights()
# glitch_sublayer = copy(glitch_layer[1])
# max_val = np.abs(glitch_sublayer)[:].max()
# mut_ratio = 0.2*float(np.random.randint(1000))/10
