I have added attention layer in an LStM model for encoder-decoder.
The model.fit function
history = model.fit_generator(generator = generate_batch(X_train, y_train, batch_size = batch_size),
steps_per_epoch = train_samples//batch_size,
epochs=epochs,
validation_data = generate_batch(X_test, y_test, batch_size = batch_size),
validation_steps = val_samples//batch_size)
And this is the error I am getting
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-42-dc64566948be> in <module>()
3 epochs=epochs,
4 validation_data = generate_batch(X_test, y_test, batch_size = batch_size),
----> 5 validation_steps = val_samples//batch_size)
9 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
58 ctx.ensure_initialized()
59 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60 inputs, attrs, num_outputs)
61 except core._NotOkStatusException as e:
62 if name is not None:
InvalidArgumentError: Incompatible shapes: [128,37] vs. [128,34]
[[node metrics_3/acc/Equal (defined at /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3009) ]] [Op:__inference_keras_scratch_graph_19367]
Function call stack:
keras_scratch_graph
My batch size is 128.
The generate batch function is
def generate_batch(X = X_train, y = y_train, batch_size = 128):
''' Generate a batch of data '''
while True:
for j in range(0, len(X), batch_size):
encoder_input_data = np.zeros((batch_size, max_length_src),dtype='float32')
decoder_input_data = np.zeros((batch_size, 34),dtype='float32')
decoder_target_data = np.zeros((batch_size, max_length_tar, num_decoder_tokens),dtype='float32')
for i, (input_text, target_text) in enumerate(zip(X[j:j+batch_size], y[j:j+batch_size])):
for t, word in enumerate(input_text.split()):
encoder_input_data[i, t] = input_token_index[word] # encoder input seq
for t, word in enumerate(target_text.split()):
if t<len(target_text.split())-1:
decoder_input_data[i, t] = target_token_index[word] # decoder input seq
if t>0:
# decoder target sequence (one hot encoded)
# does not include the START_ token
# Offset by one timestep
decoder_target_data[i, t - 1, target_token_index[word]] = 1.
yield([encoder_input_data, decoder_input_data], decoder_target_data)
Here max_length_src = 34, max_length_tar=37. The error seems to come due to this.
Please help.
from Add attention layer to Seq2Seq model this is your model (retry to paste and copy it):
ENCODER
num_encoder_tokens = 30
num_decoder_tokens = 10
latent_dim = 100
encoder_inputs = Input(shape=(None,))
enc_emb = Embedding(num_encoder_tokens, latent_dim, mask_zero = True)(encoder_inputs)
encoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)
encoder_outputs, state_h, state_c = encoder_lstm(enc_emb)
# We discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]
# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None,))
dec_emb_layer = Embedding(num_decoder_tokens, latent_dim, mask_zero = True)
dec_emb = dec_emb_layer(decoder_inputs)
# We set up our decoder to return full output sequences,
# and to return internal states as well. We don't use the
# return states in the training model, but we will use them in inference.
decoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(dec_emb,
initial_state=encoder_states)
decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)
# Define the model that will turn
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
model.summary()
DECODER
# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None,))
dec_emb_layer = Embedding(num_decoder_tokens, latent_dim, mask_zero = True)
dec_emb = dec_emb_layer(decoder_inputs)
# We set up our decoder to return full output sequences,
# and to return internal states as well. We don't use the
# return states in the training model, but we will use them in inference.
decoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, state_h, state_c = decoder_lstm(dec_emb, initial_state=encoder_states)
attention = dot([decoder_outputs, encoder_outputs], axes=[2, 2])
attention = Activation('softmax')(attention)
context = dot([attention, encoder_outputs], axes=[2,1])
decoder_outputs = concatenate([context, decoder_outputs])
decoder_dense = Dense(num_decoder_tokens, activation='softmax')(decoder_outputs)
# Define the model that will turn
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`
model = Model([encoder_inputs, decoder_inputs], decoder_dense)
model.summary()
I have no problem fitting the model...
model.compile('adam', 'categorical_crossentropy')
n_samples = 5
X_enc = np.random.randint(0,num_encoder_tokens, (n_samples,37))
X_dec = np.random.randint(0,num_decoder_tokens, (n_samples,34))
y = np.ones((n_samples,34,num_decoder_tokens))
model.fit([X_enc, X_dec], y, epochs=10)