capacity size error

[takuseno]

Caused by op 'deepq/DND_2/lookup/sub', defined at:
File "train.py", line 96, in
main()
File "train.py", line 73, in main
model, actions, replay_buffer, explorer, learning_starts=132
File "/Users/takuma/work/nec/agent.py", line 48, in init
grad_norm_clipping=10.0
File "/Users/takuma/work/nec/build_graph.py", line 32, in build_train
encoded_state, hin, vin, epsize[i]
File "/Users/takuma/work/nec/dnd.py", line 38, in _build_network
self.reader = self._build_reader(readerin, epsize)
File "/Users/takuma/work/nec/dnd.py", line 93, in _build_reader
expanded_h, [1, epsize, 1]
File "/Users/takuma/.pyenv/versions/sokushukai/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 865, in binary_op_wrapper
return func(x, y, name=name)
File "/Users/takuma/.pyenv/versions/sokushukai/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 2629, in _sub
result = _op_def_lib.apply_op("Sub", x=x, y=y, name=name)
File "/Users/takuma/.pyenv/versions/sokushukai/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/Users/takuma/.pyenv/versions/sokushukai/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/Users/takuma/.pyenv/versions/sokushukai/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1204, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): Incompatible shapes: [1,200,512] vs. [1,201,512]
[[Node: deepq/DND_2/lookup/sub = Sub[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](deepq/DND_2/lookup/Tile, deepq/DND_2/lookup/Tile_1)]]