UnknownError: IndexError: list index out of range

[coderclear]

you can ignore
DATA_DIRECTORY = '/home/VOCdevkit', I have changed some settings to adapt my dataset.
I have referenced this #151, but this does not work for me. When I set NUM_CLASSES = 21,it can run successfully.
Below is setting：
DATA_DIRECTORY = '/home/VOCdevkit'
DATA_LIST_PATH = 'D:/UBUNTU/github/getdata/train.txt'
GRAD_UPDATE_EVERY = 10
IGNORE_LABEL = 255
INPUT_SIZE = '321,321'
LEARNING_RATE = 2.5e-4
MOMENTUM = 0.9
NUM_CLASSES = 91
NUM_STEPS = 20001
POWER = 0.9
RANDOM_SEED = 1234
RESTORE_FROM = 'D:/UBUNTU/github/tensorflow-deeplab-resnet/model/deeplab_resnet.ckpt'
SAVE_NUM_IMAGES = 1
SAVE_PRED_EVERY = 1000
SNAPSHOT_DIR = 'D:/UBUNTU/github/tensorflow-deeplab-resnet/snapshots/'
WEIGHT_DECAY = 0.0005

parser.add_argument("--not-restore-last", action="store_false",
help="Whether to not restore last (FC) layers.")

Below is Error：
UnknownError: IndexError: list index out of range
[[Node: PyFunc_1 = PyFunc[Tin=[DT_UINT8, DT_INT32, DT_INT32], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](create_inputs/batch:1, PyFunc_1/input_1, PyFunc_1/input_2)]]

Caused by op 'PyFunc_1', defined at:
File "F:\soft\anaconda\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 223, in
main()
File "F:\soft\anaconda\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 219, in main
kernel.start()
File "F:\soft\anaconda\lib\site-packages\ipykernel\kernelapp.py", line 474, in start
ioloop.IOLoop.instance().start()
File "F:\soft\anaconda\lib\site-packages\zmq\eventloop\ioloop.py", line 162, in start
super(ZMQIOLoop, self).start()
File "F:\soft\anaconda\lib\site-packages\tornado\ioloop.py", line 887, in start
handler_func(fd_obj, events)
File "F:\soft\anaconda\lib\site-packages\tornado\stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "F:\soft\anaconda\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "F:\soft\anaconda\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "F:\soft\anaconda\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "F:\soft\anaconda\lib\site-packages\tornado\stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "F:\soft\anaconda\lib\site-packages\ipykernel\kernelbase.py", line 276, in dispatcher
return self.dispatch_shell(stream, msg)
File "F:\soft\anaconda\lib\site-packages\ipykernel\kernelbase.py", line 228, in dispatch_shell
handler(stream, idents, msg)
File "F:\soft\anaconda\lib\site-packages\ipykernel\kernelbase.py", line 390, in execute_request
user_expressions, allow_stdin)
File "F:\soft\anaconda\lib\site-packages\ipykernel\ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "F:\soft\anaconda\lib\site-packages\ipykernel\zmqshell.py", line 501, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "F:\soft\anaconda\lib\site-packages\IPython\core\interactiveshell.py", line 2717, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "F:\soft\anaconda\lib\site-packages\IPython\core\interactiveshell.py", line 2827, in run_ast_nodes
if self.run_code(code, result):
File "F:\soft\anaconda\lib\site-packages\IPython\core\interactiveshell.py", line 2881, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
runfile('D:/UBUNTU/github/tensorflow-deeplab-resnet/train_msc.py', wdir='D:/UBUNTU/github/tensorflow-deeplab-resnet')
File "F:\soft\anaconda\lib\site-packages\spyder\utils\site\sitecustomize.py", line 866, in runfile
execfile(filename, namespace)
File "F:\soft\anaconda\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "D:/UBUNTU/github/tensorflow-deeplab-resnet/train_msc.py", line 317, in
main()
File "D:/UBUNTU/github/tensorflow-deeplab-resnet/train_msc.py", line 223, in main
labels_summary = tf.py_func(decode_labels, [label_batch, args.save_num_images, args.num_classes], tf.uint8)
File "F:\soft\anaconda\lib\site-packages\tensorflow\python\ops\script_ops.py", line 203, in py_func
input=inp, token=token, Tout=Tout, name=name)
File "F:\soft\anaconda\lib\site-packages\tensorflow\python\ops\gen_script_ops.py", line 38, in _py_func
name=name)
File "F:\soft\anaconda\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op
op_def=op_def)
File "F:\soft\anaconda\lib\site-packages\tensorflow\python\framework\ops.py", line 2628, in create_op
original_op=self._default_original_op, op_def=op_def)
File "F:\soft\anaconda\lib\site-packages\tensorflow\python\framework\ops.py", line 1204, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

UnknownError (see above for traceback): IndexError: list index out of range
[[Node: PyFunc_1 = PyFunc[Tin=[DT_UINT8, DT_INT32, DT_INT32], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](create_inputs/batch:1, PyFunc_1/input_1, PyFunc_1/input_2)]]

[coderclear]

I have solved this issue, just modify label_colours in ulils.py to adapt your dataset.