Input to reshape is a tensor with 32768 values, but the requested shape requires a multiple of 80
Opened this issue · 1 comments
There are no other questions, only the last one. I don't know how to solve them. I look forward to your answer!
The error is shown below：
Caused by op 'tower_0/postprocess_fastrcnn/Reshape', defined at:
File "multi_gpu_train.py", line 364, in
train()
File "multi_gpu_train.py", line 216, in train
gpu_id=i)
File "../libs/networks/build_whole_network.py", line 661, in build_whole_detection_network
gpu_id=gpu_id)
File "../libs/networks/build_whole_network.py", line 58, in postprocess_fastrcnn
bbox_ppred = tf.reshape(bbox_ppred, [-1, cfgs.CLASS_NUM + 1, 5])
File "/home/user/.conda/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 6482, in reshape
"Reshape", tensor=tensor, shape=shape, name=name)
File "/home/user/.conda/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/user/.conda/envs/tf/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/home/user/.conda/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/home/user/.conda/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in init
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 32768 values, but the requested shape requires a multiple
[[node tower_0/postprocess_fastrcnn/Reshape (defined at ../libs/networks/build_whole_network.py:58) = Reshape[T=DT_FLOAT, Tshape=plica:0/task:0/device:GPU:0"](tower_0/Fast-RCNN/reg_fc/BiasAdd, tower_0/postprocess_fastrcnn/Reshape/shape)]]
bug is fixed, please update the code. @beikeren