Error arises from the size of own training data about icnet-tensorflow HOT 7 CLOSED

Hey @YiSyuanChen, sorry for confusing you. I have only updated the inference code enabling to fit every different size. For training code, you need to adjust the size to the multiple of 32 because the output stride of network is 32 ( that is, your feature map is 32x smaller than input image ). Is the comment helpful for you? If you have any question, feel free to let me know.

from icnet-tensorflow.

Hey @YiSyuanChen, @hellochick I did the very same steps as YiSyuanChen, my images are 480x480 and I only changed the tf.image.decode_jpeg function to tf.image.decode_image, when I try to train I get the following error:
`Traceback (most recent call last):
File "train.py", line 210, in
main()
File "train.py", line 199, in main
loss_value, loss1, loss2, loss3, _ = sess.run([reduced_loss, loss_sub4, loss_sub24, loss_sub124, train_op], feed_dict=feed_dict)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 778, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 982, in _run
feed_dict_string, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1032, in _do_run
target_list, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1052, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.OutOfRangeError: FIFOQueue '_1_create_inputs/batch/fifo_queue' is closed and has insufficient elements (requested 48, current size 0)
[[Node: create_inputs/batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](create_inputs/batch/fifo_queue, create_inputs/batch/n)]]

Caused by op u'create_inputs/batch', defined at:
File "train.py", line 210, in
main()
File "train.py", line 135, in main
image_batch, label_batch = reader.dequeue(args.batch_size)
File "/home/ubuntu/githubrepo/ICNET2/ICNet-tensorflow/image_reader.py", line 116, in dequeue
num_elements)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/input.py", line 917, in batch
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/input.py", line 712, in _batch
dequeued = queue.dequeue_many(batch_size, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/data_flow_ops.py", line 458, in dequeue_many
self._queue_ref, n=n, component_types=self._dtypes, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 1328, in _queue_dequeue_many_v2
timeout_ms=timeout_ms, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1228, in init
self._traceback = _extract_stack()

OutOfRangeError (see above for traceback): FIFOQueue '_1_create_inputs/batch/fifo_queue' is closed and has insufficient elements (requested 48, current size 0)
[[Node: create_inputs/batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](create_inputs/batch/fifo_queue, create_inputs/batch/n)]]
`
Any clue?
Really thanks your help in advance.

from icnet-tensorflow.

@MikeyLev, it seems that the number of images are not enough to fill the input queue. Can you check your dataset size?

from icnet-tensorflow.

@hellochick Thanks for your reply!! It's really helpful, and I'll keep trying. Thanks for your help again :)

from icnet-tensorflow.

@YiSyuanChen Can you tell me some detail of modify the name "conv6_cls" , I want do detect on 12 classes, Thk.

from icnet-tensorflow.

@hellochick Thanks, This was the problem although I must understand what this means...

from icnet-tensorflow.

@MikeyLev I'm getting the same error, can you tell me your data-set size. I have around 260 training images.

from icnet-tensorflow.