Tensor Flow shuffle_batch() blocks at end of epoch

Question

I\'m using tf.train.shuffle_batch() to create batches of input images. It includes a min_after_dequeue parameter that makes sure there\'s a specified number of elements inside t

Answer 1

There is an optional argument allow_smaller_final_batch

"allow_smaller_final_batch: (Optional) Boolean. If True, allow the final batch to be smaller if there are insufficient items left in the queue."