all. I'm trying to get the CTC loss function here and it's not working very well. I keep getting this bug:
2020-11-04 07:28:53.647946: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
2020-11-04 07:28:53.647977: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
2020-11-04 07:28:53.648009: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
2020-11-04 07:28:53.647992: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
2020-11-04 07:28:53.648021: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
2020-11-04 07:28:53.648063: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
2020-11-04 07:28:53.648052: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
2020-11-04 07:28:53.648074: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
2020-11-04 07:28:53.648080: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
2020-11-04 07:28:53.648308: W ./tensorflow/core/util/ctc/ctc_loss_calculator.h:499] No valid path found.
I have scoured the internet for information on this and I'm not getting anything.
Here is code for it:
def loss_fn(self, y_true, y_pred):
batch_len = tf.keras.backend.cast(tf.shape(y_true)[0], dtype="int64")
input_length = tf.keras.backend.cast(tf.shape(y_pred)[1], dtype="int64") #Comes out to be 30
label_length = tf.keras.backend.cast(tf.shape(y_true)[1], dtype="int64") #Comes out to be 25
input_length = 30 * tf.ones(shape=(batch_len, 1), dtype="int64") #Just hardcoded 30 for now
label_length = 25 * tf.ones(shape=(batch_len, 1), dtype="int64") #Just hardcoded 25 for now
y_true = tf.keras.layers.Softmax()(y_true)
y_pred = tf.keras.layers.Softmax()(y_pred)
print("y_true shape %s" %y_true.shape) #Outputs y_true shape (32, 25)
print(y_true) #outputs Tensor("loss_fn/softmax/Softmax:0", shape=(32, 25), dtype=float32)
print("y_pred shape %s" %y_pred.shape) #Outputs y_pred shape (32, 30, 67)
print(y_pred) #outputs Tensor("loss_fn/softmax_1/Softmax:0", shape=(32, 30, 67), dtype=float32)
loss = tf.keras.backend.ctc_batch_cost(y_true, y_pred, input_length, label_length)
return tf.reduce_mean(loss)
The loss function is being called here:
...
def ResNet:
...
out = tf.keras.layers.Reshape((out.shape[2], out.shape[3]))(out)
print("out %s" %out.shape) #Comes out to be: out (None, 30, 768)
weight_initializer = tf.keras.initializers.he_uniform()
bias_initializer = tf.keras.initializers.constant()
logits = tf.keras.layers.Dense(67, kernel_initializer=weight_initializer, bias_initializer=bias_initializer, name="logits")(out)
print("logits %s" %logits.shape) #Comes out to be: logits (None, 30, 67)
print("________________________")
print(logits)
model = tf.keras.Model(inputs=[input, labels], outputs=logits, name="full_model")
model.compile(optimizer="RMSprop", loss=self.loss_fn)
print(model.summary())
Main function that calls this:
...
...
d = dataset.Dataset(confs)
train_data = d.read_data(confs["trn_data_files"])
valid_data = d.read_data(confs["val_data_files"])
callbacks = [
tf.keras.callbacks.ModelCheckpoint("./model_checkpoint", monitor="val_loss")
]
for x,y in train_data:
history = model.fit(
x=x,
y=y,
validation_data=valid_data,
epochs=50,
callbacks=callbacks,
)
Dataset has preprocessing.
As you can see, the dimensions of the label is smaller than the logits. I know that if this is not the case, the "no valid path found" error happens.
Am I doing something wrong? Please help. Thank you so much in advance.
