CTC Loss InvalidArgumentError: sequence_length (b) <= time

Question

I use this error when trying to use tf.nn.ctc_loss via keras (ctc_batch_cost):

InvalidArgumentError (see above for traceback): sequence_length (4) <= 471

According to the documentation for tf.nn.ctc_loss input requirements:

sequence_length (b) <= time for all b

max (labels.indices (labels.indices [:, 1] == b, 2)) <= sequence_length (b) for all b.

It's hard for me to understand what this means - what is it band what is it sequence_length(b)?

Answer 1

b - -. sequence_length(b) - , . sequence_length, tf.nn.ctc_loss, 1- .

Answer 2

, (0) <= 8? , 8 8?

def get_model(img_h,nclass=None):
start_epoch = 0
stop_epoch = 30
img_w = 32

# Input Parameters
img_h = img_h
words_per_epoch = 16000
val_split = 0.2
val_words = int(words_per_epoch * (val_split))

# Network parameters
conv_filters = 16
kernel_size = (3, 3)
pool_size = 2
time_dense_size = 32
rnn_size = 512
minibatch_size = 32

if K.image_data_format() == 'channels_first':
    input_shape = (1, img_w, img_h)
else:
    input_shape = (img_w, None, 1)
act = 'relu'
input_data = Input(name='the_input', shape=input_shape, dtype='float32')
inner = Conv2D(conv_filters, kernel_size, padding='same',
               activation=act, kernel_initializer='he_normal',
               name='conv1')(input_data)
inner = MaxPooling2D(pool_size=(pool_size, pool_size), name='max1')(inner)
inner = Conv2D(conv_filters, kernel_size, padding='same',
               activation=act, kernel_initializer='he_normal',
               name='conv2')(inner)
inner = MaxPooling2D(pool_size=(pool_size, pool_size), name='max2')(inner)

conv_to_rnn_dims = (img_w // (pool_size ** 2), (img_h // (pool_size ** 2)) * conv_filters)
inner = Reshape(target_shape=conv_to_rnn_dims, name='reshape')(inner)

# cuts down input size going into RNN:
inner = Dense(time_dense_size, activation=act, name='dense1')(inner)

# Two layers of bidirectional GRUs
# GRU seems to work as well, if not better than LSTM:
gru_1 = GRU(rnn_size, return_sequences=True, kernel_initializer='he_normal', name='gru1')(inner)
gru_1b = GRU(rnn_size, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='gru1_b')(inner)
gru1_merged = add([gru_1, gru_1b])
gru_2 = GRU(rnn_size, return_sequences=True, kernel_initializer='he_normal', name='gru2')(gru1_merged)
gru_2b = GRU(rnn_size, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='gru2_b')(gru1_merged)

# transforms RNN output to character activations:
inner = Dense(12, kernel_initializer='he_normal',
              name='dense2')(concatenate([gru_2, gru_2b]))
y_pred = Activation('softmax', name='softmax')(inner)
Model(inputs=input_data, outputs=y_pred).summary()

labels = Input(name='the_labels', shape=[None],dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
# Keras doesn't currently support loss funcs with extra parameters
# so CTC loss is implemented in a lambda layer
loss_out = Lambda(ctc_lambda_func, output_shape=(1,), name='ctc')([y_pred, labels, input_length, label_length])
# clipnorm seems to speeds up convergence
sgd = SGD(lr=0.02, decay=1e-6, momentum=0.9, nesterov=True, clipnorm=5)
model = Model(inputs=[input_data, labels, input_length, label_length], outputs=loss_out)
# the loss calc occurs elsewhere, so use a dummy lambda func for the loss
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd)
return model