face_detection训练报错
Created by: xiegegege
在1.4分支上训练报错,应该是最新框架合入导致的,报错如下: Traceback (most recent call last): File "train.py", line 271, in train(args, config, train_parameters, train_file_list) File "train.py", line 200, in train [v.name for v in fetches]) File "/opt/_internal/cpython-3.6.0/lib/python3.6/site-packages/paddle/fluid/parallel_executor.py", line 205, in run return_numpy=return_numpy) File "/opt/_internal/cpython-3.6.0/lib/python3.6/site-packages/paddle/fluid/executor.py", line 544, in run return_numpy=return_numpy) File "/opt/_internal/cpython-3.6.0/lib/python3.6/site-packages/paddle/fluid/executor.py", line 445, in _run_parallel exe.run(fetch_var_names, fetch_var_name) paddle.fluid.core.EnforceNotMet: Invoke operator reshape2 error. Python Callstacks: File "/opt/_internal/cpython-3.6.0/lib/python3.6/site-packages/paddle/fluid/framework.py", line 1663, in append_op attrs=kwargs.get("attrs", None)) File "/opt/_internal/cpython-3.6.0/lib/python3.6/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op return self.main_program.current_block().append_op(*args, **kwargs) File "/opt/_internal/cpython-3.6.0/lib/python3.6/site-packages/paddle/fluid/layers/nn.py", line 6409, in reshape "XShape": x_shape}) File "/workspace/PaddleCV/face_detection/pyramidbox.py", line 241, in permute_and_reshape trans, shape=compile_shape, actual_shape=run_shape) File "/workspace/PaddleCV/face_detection/pyramidbox.py", line 254, in _pyramidbox head_loc = permute_and_reshape(head_loc, 4) File "/workspace/PaddleCV/face_detection/pyramidbox.py", line 95, in init self._pyramidbox() File "train.py", line 93, in build_program sub_network=use_pyramidbox) File "train.py", line 139, in train args=args) File "train.py", line 271, in train(args, config, train_parameters, train_file_list) C++ Callstacks: Enforce failed. Expected capacity == in_size, but received capacity:51200 != in_size:204800. Invalid shape is given. at [/home/Paddle/paddle/fluid/operators/reshape_op.cc:106]