Develop Reference

Tensorflow Keras multiple input model

I need to adapt this model for two text columns input (instead one column)
tfhub_handle_encoder = \
"https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-4_H-512_A-8/1"
tfhub_handle_preprocess = \
"https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3"
def build_classifier_model():
text_input = tf.keras.layers.Input(
shape=(), dtype=tf.string, name='text')
preprocessing_layer = hub.KerasLayer(
tfhub_handle_preprocess, name='preprocessing')
encoder_inputs = preprocessing_layer(text_input)
encoder = hub.KerasLayer(
tfhub_handle_encoder, trainable=True, name='BERT_encoder')
outputs = encoder(encoder_inputs)
net = outputs['pooled_output']
net = tf.keras.layers.Dropout(0.1)(net)
net = tf.keras.layers.Dense(
6, activation='softmax', name='classifier')(net)
model = tf.keras.Model(text_input, net)
loss = tf.keras.losses.CategoricalCrossentropy(from_logits=False) # (from_logits=True)
metric = tf.metrics.CategoricalAccuracy('accuracy')
optimizer = Adam(
learning_rate=5e-05, epsilon=1e-08, decay=0.01, clipnorm=1.0)
model.compile(
optimizer=optimizer, loss=loss, metrics=metric)
model.summary()
return model
history = classifier_model.fit(
x=X_train['f'].values,
y=y_train_c,
validation_data=(X_valid['f'].values, y_valid_c),
epochs=15)
Seems like this is model from tutorial: https://www.tensorflow.org/text/tutorials/classify_text_with_bert
I have tried modify code for two input layer, but get error because after concatenate there is wrong tensor dimensions:
def build_classifier_model():
input1 = tf.keras.layers.Input(
shape=(), dtype=tf.string, name='text')
input2 = tf.keras.layers.Input(
shape=(), dtype=tf.string, name='text1')
text_input = tf.keras.layers.concatenate([input1, input2], axis=-1)
preprocessing_layer = hub.KerasLayer(
tfhub_handle_preprocess, name='preprocessing')
encoder_inputs = preprocessing_layer(text_input)
encoder = hub.KerasLayer(
tfhub_handle_encoder, trainable=True, name='BERT_encoder')
outputs = encoder(encoder_inputs)
net = outputs['pooled_output']
net = tf.keras.layers.Dropout(0.1)(net)
net = tf.keras.layers.Dense(
6, activation='softmax', name='classifier')(net)
model = tf.keras.Model([input1, input2], net)
loss = tf.keras.losses.CategoricalCrossentropy(from_logits=False) # (from_logits=True)
metric = tf.metrics.CategoricalAccuracy('accuracy')
optimizer = Adam(
learning_rate=5e-05, epsilon=1e-08, decay=0.01, clipnorm=1.0)
model.compile(
optimizer=optimizer, loss=loss, metrics=metric)
model.summary()
return model
Error:
InvalidArgumentError: logits and labels must be broadcastable: logits_size=[64,6] labels_size=[32,6]
[[node categorical_crossentropy/softmax_cross_entropy_with_logits (defined at tmp/ipykernel_39/1837193519.py:5) ]] [Op:__inference_train_function_271676]
If use concatenate with another dimension then model doensn't compile

Weirdly enough, replacing your Concatenation layer with tf.strings.join inside your model seems to work:
def build_classifier_model():
input1 = tf.keras.layers.Input(
shape=(), dtype=tf.string, name='text')
input2 = tf.keras.layers.Input(
shape=(), dtype=tf.string, name='text1')
text_input = tf.strings.join([input1, input2])
preprocessing_layer = hub.KerasLayer(
tfhub_handle_preprocess, name='preprocessing')
encoder_inputs = preprocessing_layer(text_input)
encoder = hub.KerasLayer(
tfhub_handle_encoder, trainable=True, name='BERT_encoder')
outputs = encoder(encoder_inputs)
net = outputs['pooled_output']
net = tf.keras.layers.Dropout(0.1)(net)
output = tf.keras.layers.Dense(
6, activation='softmax', name='classifier')(net)
model = tf.keras.Model([input1, input2], output)
loss = tf.keras.losses.CategoricalCrossentropy(from_logits=False) # (from_logits=True)
metric = tf.metrics.CategoricalAccuracy('accuracy')
optimizer = Adam(
learning_rate=5e-05, epsilon=1e-08, decay=0.01, clipnorm=1.0)
model.compile(
optimizer=optimizer, loss=loss, metrics=metric)
model.summary()
return model
Epoch 1/5
497/1094 [============>.................] - ETA: 2:14 - loss: 1.8664 - accuracy: 0.1641
You could also consider simply doing text_input = input1 + input2 , since the Concatenation layer seems to mess up the batch dimension. Or you could feed each input to your encoder and concatenate the results afterwards:
def build_classifier_model():
input1 = tf.keras.layers.Input(
shape=(), dtype=tf.string, name='text')
input2 = tf.keras.layers.Input(
shape=(), dtype=tf.string, name='text1')
preprocessing_layer = hub.KerasLayer(
tfhub_handle_preprocess, name='preprocessing')
encoder_input1 = preprocessing_layer(input1)
encoder_input2 = preprocessing_layer(input2)
encoder = hub.KerasLayer(
tfhub_handle_encoder, trainable=True, name='BERT_encoder')
output1 = encoder(encoder_input1)
output2 = encoder(encoder_input2)
net = tf.keras.layers.Concatenate(axis=-1)([output1['pooled_output'], output2['pooled_output']])
net = tf.keras.layers.Dropout(0.1)(net)
output = tf.keras.layers.Dense(
6, activation='softmax', name='classifier')(net)
model = tf.keras.Model([input1, input2], output)
loss = tf.keras.losses.CategoricalCrossentropy(from_logits=False) # (from_logits=True)
metric = tf.metrics.CategoricalAccuracy('accuracy')
optimizer = Adam(
learning_rate=5e-05, epsilon=1e-08, decay=0.01, clipnorm=1.0)
model.compile(
optimizer=optimizer, loss=loss, metrics=metric)
model.summary()
return model

How to use BERT for performing regression?

Here is the code and dataset
This is the function used for building the model:
def build_regression_model():
text_input = tf.keras.layers.Input(shape=(), dtype=tf.string, name='text')
preprocessing_layer = hub.KerasLayer(tfhub_handle_preprocess, name='preprocessing')
encoder_inputs = preprocessing_layer(text_input)
encoder = hub.KerasLayer(tfhub_handle_encoder, trainable=True, name='BERT_encoder')
outputs = encoder(encoder_inputs)
net = outputs['pooled_output']
net = tf.keras.layers.Dense(units=1)(net)
return tf.keras.Model(text_input, net)
regression_model = build_regression_model()
The loss is:
loss='mean_absolute_error'
The optimizer is:
optimizer=tf.optimizers.Adam(learning_rate=0.1)
Can someone please provide tips to solve this problem. Thank you!

Graph disconnected: cannot obtain value for tensor "x" Tensor at layer "x" . The following previous layers were accessed without issue: []

I am building a small network using some custom network boxes for each use case, It looks like this :
def top_block(dropout = None, training = None):
# scaled input
input_1 = tf.keras.Input(shape=(1,15), dtype='float32')
input_2 = tf.keras.Input(shape=(1,15), dtype='float32')
if dropout:
layer_one = tf.keras.layers.Dropout(rate = dropout)(input_1, training = training)
layer_two = tf.keras.layers.Dropout(rate = dropout)(input_2, training = training)
return [layer_one,layer_two]
return [input_1,input_2]
def bottom_layer(input_layers):
data = tf.reduce_mean(input_layers,0)
cls_layer = tf.keras.layers.Dense(1,
kernel_initializer = keras.initializers.glorot_uniform(seed=200),
activation = 'sigmoid')(data)
model = tf.keras.Model([input_layers[0], input_layers[1]], cls_layer , name = 'model_1')
model.compile(loss = 'binary_crossentropy', optimizer = 'adam', metrics=['accuracy'])
model.summary()
return model
If I am trying to access this network without dropout, it's working fine :
top_ = top_block()
model = bottom_layer(top_ )
But if I am accessing with dropout, it's giving error:
top_ = top_block(dropout = 0.2, training = True)
model = bottom_layer(top_ )
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_72:0", shape=(None, 1, 15), dtype=float32) at layer "input_72". The following previous layers were accessed without issue: []
How to access the model with dropout layer?
How to disable training = False during evaluate? Do I need to load full model and old model weights?
Thank You!

I just realized my input is coming from intermediate layer (dropout layer), It should come directly from Input layer :
def top_block():
# scaled input
input_1 = tf.keras.Input(shape=(1,15), dtype='float32')
input_2 = tf.keras.Input(shape=(1,15), dtype='float32')
return [input_1, input_2]
def apply_dropout(layers_data, dropout_val, training):
layer_one = tf.keras.layers.Dropout(rate = dropout_val)(layers_data[0], training = training)
layer_two = tf.keras.layers.Dropout(rate = dropout_val)(layers_data[1], training = training)
return [layer_one, layer_two]
def bottom_layer(input_layers, data):
data = tf.reduce_mean(data, 0)
cls_layer = tf.keras.layers.Dense(1,
kernel_initializer = keras.initializers.glorot_uniform(seed=200),
activation = 'sigmoid')(data)
model = tf.keras.Model(input_layers, cls_layer , name = 'model_1')
model.compile(loss = 'binary_crossentropy', optimizer = 'adam', metrics=['accuracy'])
model.summary()
return model
It's working now
top_ = top_block()
dropout_ = apply_dropout(top_, 0.2, True)
model = bottom_layer(top_ , dropout_)

Training in inference mode in seq-to-seq model

This is apparently the code for seq2seq model with embedding that i wrote
encoder_inputs = Input(shape=(MAX_LEN, ), dtype='int32',)
encoder_embedding = embed_layer(encoder_inputs)
encoder_LSTM = LSTM(HIDDEN_DIM, return_state=True)
encoder_outputs, state_h, state_c = encoder_LSTM(encoder_embedding)
encoder_states = [state_h, state_c]
decoder_inputs = Input(shape=(MAX_LEN, ))
decoder_embedding = embed_layer(decoder_inputs)
decoder_LSTM = LSTM(HIDDEN_DIM, return_state=True, return_sequences=True)
decoder_outputs, _, _ = decoder_LSTM(
decoder_embedding, initial_state=encoder_states)
outputs = TimeDistributed(
Dense(VOCAB_SIZE, activation='softmax'))(decoder_outputs)
model = Model([encoder_inputs, decoder_inputs], outputs)
# defining inference model
encoder_model = Model(encoder_inputs, encoder_states)
decoder_state_input_h = Input(shape=(None,))
decoder_state_input_c = Input(shape=(None,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs, state_h, state_c = decoder_LSTM(
decoder_embedding, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
outputs = TimeDistributed(
Dense(VOCAB_SIZE, activation='softmax'))(decoder_outputs)
decoder_model = Model(
[decoder_inputs] + decoder_states_inputs, [outputs] + decoder_states)
return model, encoder_model, decoder_model
we are using inference mode for predictions particularly encoder and decoder model, but i am not sure where the training is happening for the encoder and decoder?
Edit 1
Code is build upon: https://keras.io/examples/lstm_seq2seq/,
with added embedding layer and Time Distributed dense layer.
for more info on issue: github repo

Encoder and decoder are trained simultaneously, or more precisely the model that is composed of these two is trained which in turn trains both of them (this is not GAN where you need some fancy training cycle)
If you look closely in the provided link, there is a section where the model is trained.
# Run training
model.compile(optimizer='rmsprop', loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit([encoder_input_data, decoder_input_data], decoder_target_data,
batch_size=batch_size,
epochs=epochs,
validation_split=0.2)
Edit: from comments
If you look more closely, the "new" model that you are defining after fit consists of layers that have already been trained in the previous step. i.e Model(encoder_inputs, encoder_states) both encoder_inputs and encoder_states were used during the initial training, you are just repackaging them.

Restore keras seq2seq model

I'm working with the keras seq2seq example here:
https://github.com/keras-team/keras/blob/master/examples/lstm_seq2seq.py
I would like to persist the vocabulary and decoder so that I can load it again later, and apply it to new sequences.
While the code calls model.save(), this is insufficient because I can see the decoding setup referencing a number of other variables which are deep pointers into the trained model:
encoder_model = Model(encoder_inputs, encoder_states)
decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs, state_h, state_c = decoder_lstm(
decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
decoder_outputs = decoder_dense(decoder_outputs)
decoder_model = Model(
[decoder_inputs] + decoder_states_inputs,
[decoder_outputs] + decoder_states)
I would like to translate this code to determine encoder_inputs, encoder_states, latent_dim, decoder_inputs from a model loaded from disk. It's ok to assume I know the model architecture in advance. Is there a straightforward way to do this?
Update:
I have made some progress using the decoder construction code and pulling out the layer inputs/outputs as needed.
encoder_inputs = model.input[0] #input_1
decoder_inputs = model.input[1] #input_2
encoder_outputs, state_h_enc, state_c_enc = model.layers[2].output # lstm_1
_, state_h_dec, state_c_dec = model.layers[3].output # lstm_2
decoder_outputs = model.layers[4].output # dense_1
encoder_states = [state_h_enc, state_c_enc]
encoder_model = Model(encoder_inputs, encoder_states)
latent_dim = 256 # TODO: infer this from the model. Should match lstm_1 outputs.
decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_states = [state_h_dec, state_c_dec]
decoder_model = Model(
[decoder_inputs] + decoder_states_inputs,
[decoder_outputs] + decoder_states)
However, when I try to construct the decoder model, I encounter this error:
RuntimeError: Graph disconnected: cannot obtain value for tensor Tensor("input_1:0", shape=(?, ?, 96), dtype=float32) at layer "input_1". The following previous layers were accessed without issue: []
As a test I tried Model(decoder_inputs,decoder_outputs) with the same result. It's not clear to me what is disconnected from the graph, since these layers are loaded from the model.

Ok, I solved this problem and the decoder is producing reasonable results. In my code above I missed a couple details in the decoder step, specifically that it call()s the LSTM and Dense layers in order to wire them up. In addition, the new decoder inputs need unique names so they don't collide with input_1 and input_2 (this detail smells like a keras bug).
encoder_inputs = model.input[0] #input_1
encoder_outputs, state_h_enc, state_c_enc = model.layers[2].output # lstm_1
encoder_states = [state_h_enc, state_c_enc]
encoder_model = Model(encoder_inputs, encoder_states)
decoder_inputs = model.input[1] #input_2
decoder_state_input_h = Input(shape=(latent_dim,),name='input_3')
decoder_state_input_c = Input(shape=(latent_dim,),name='input_4')
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_lstm = model.layers[3]
decoder_outputs, state_h_dec, state_c_dec = decoder_lstm(
decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h_dec, state_c_dec]
decoder_dense = model.layers[4]
decoder_outputs=decoder_dense(decoder_outputs)
decoder_model = Model(
[decoder_inputs] + decoder_states_inputs,
[decoder_outputs] + decoder_states)
A big drawback with this code is the fact we know the full architecture in advance. I would like to eventually be able to load an architecture-agnostic decoder.

At a point in the code of the Keras seq2seq example you will have a finished encoder and decoder model. You can save the architecture and weights of these models to disk and load them later. The following works for me:
Save the models to disk:
with open('encoder_model.json', 'w', encoding='utf8') as f:
f.write(encoder_model.to_json())
encoder_model.save_weights('encoder_model_weights.h5')
with open('decoder_model.json', 'w', encoding='utf8') as f:
f.write(decoder_model.to_json())
decoder_model.save_weights('decoder_model_weights.h5')
Later load the encoder and decoder:
def load_model(model_filename, model_weights_filename):
with open(model_filename, 'r', encoding='utf8') as f:
model = model_from_json(f.read())
model.load_weights(model_weights_filename)
return model
encoder = load_model('encoder_model.json', 'encoder_model_weights.h5')
decoder = load_model('decoder_model.json', 'decoder_model_weights.h5')
During prediction you will also need a number of other data, like number of encoder/decoder tokens, dictionaries mapping char to index etc. You can just save these to file after training and load them later, just like with the models.