使用paddleslim的模型自动化压缩工具ACT优化TPSMM模型报错

[kiyojimini]

Traceback (most recent call last):
File "run.py", line 212, in
main()
File "run.py", line 205, in main
ac.compress()
File "/data/huangyan/anaconda/anaconda3/envs/yolov5sperson/lib/python3.8/site-packages/paddleslim-0.0.0.dev0-py3.8.egg/paddleslim/auto_compression/compressor.py", line 586, in compress
self.single_strategy_compress(strategy, config, strategy_idx,
File "/data/huangyan/anaconda/anaconda3/envs/yolov5sperson/lib/python3.8/site-packages/paddleslim-0.0.0.dev0-py3.8.egg/paddleslim/auto_compression/compressor.py", line 753, in single_strategy_compress
metric = self.eval_function(self._exe, inference_program,
File "run.py", line 104, in eval_function
pred = exe.run(
File "/data/huangyan/anaconda/anaconda3/envs/yolov5sperson/lib/python3.8/site-packages/paddle/base/executor.py", line 1746, in run
res = self._run_impl(
File "/data/huangyan/anaconda/anaconda3/envs/yolov5sperson/lib/python3.8/site-packages/paddle/base/executor.py", line 1952, in _run_impl
ret = new_exe.run(
File "/data/huangyan/anaconda/anaconda3/envs/yolov5sperson/lib/python3.8/site-packages/paddle/base/executor.py", line 831, in run
tensors = self._new_exe.run(
ValueError: In user code:

File "/data/huangyan/anaconda/anaconda3/envs/paddle/bin/x2paddle", line 8, in <module>
  sys.exit(main())
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle/convert.py", line 497, in main
  enable_onnx_checker=args.enable_onnx_checker)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle/convert.py", line 311, in onnx2paddle
  mapper.paddle_graph.gen_model(save_dir)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle/core/program.py", line 297, in gen_model
  self.dygraph2static(save_dir, input_shapes, input_types)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle/core/program.py", line 583, in dygraph2static
  osp.join(save_dir, "inference_model/model"))
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/jit.py", line 631, in wrapper
  func(layer, path, input_spec, **configs)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/decorator.py", line 232, in fun
  return caller(func, *(extras + args), **kw)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__
  return wrapped_func(*args, **kwargs)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/base.py", line 51, in __impl__
  return func(*args, **kwargs)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/jit.py", line 861, in save
  inner_input_spec, with_hook=with_hook)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 528, in concrete_program_specify_input_spec
  *desired_input_spec, with_hook=with_hook)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 436, in get_concrete_program
  concrete_program, partial_program_layer = self._program_cache[cache_key]
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 801, in __getitem__
  self._caches[item_id] = self._build_once(item)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 790, in _build_once
  **cache_key.kwargs)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/decorator.py", line 232, in fun
  return caller(func, *(extras + args), **kw)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__
  return wrapped_func(*args, **kwargs)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/base.py", line 51, in __impl__
  return func(*args, **kwargs)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 733, in from_func_spec
  outputs = static_func(*inputs)
File "./x2paddle_code.py", line 103, in forward
  x2paddle_onnx__Gemm_190 = paddle.reshape(x=x2paddle_onnx__Flatten_189, shape=[1, 512])
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/tensor/manipulation.py", line 2139, in reshape
  return paddle.fluid.layers.reshape(x=x, shape=shape, name=name)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/nn.py", line 6450, in reshape
  "XShape": x_shape})
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layer_helper.py", line 44, in append_op
  return self.main_program.current_block().append_op(*args, **kwargs)
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/framework.py", line 3621, in append_op
  attrs=kwargs.get("attrs", None))
File "/data/huangyan/anaconda/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/framework.py", line 2635, in __init__
  for frame in traceback.extract_stack():

InvalidArgumentError: The 'shape' in ReshapeOp is invalid. The input tensor X'size must be equal to the capacity of 'shape'. But received X's shape = [2, 512, 1, 1], X's size = 1024, 'shape' is [1, 512], the capacity of 'shape' is 512.
  [Hint: Expected capacity == in_size, but received capacity:512 != in_size:1024.] (at ../paddle/fluid/operators/reshape_op.cc:234)
  [operator < reshape2 > error]

请问该如何修改呢，期待解答！！

[YZW-explorer]

您好，错误是发生在这里：
... File "./x2paddle_code.py", line 103, in forward x2paddle_onnx__Gemm_190 = paddle.reshape(x=x2paddle_onnx__Flatten_189, shape=[1, 512]) ... InvalidArgumentError: The 'shape' in ReshapeOp is invalid. The input tensor X'size must be equal to the capacity of 'shape'. But received X's shape = [2, 512, 1, 1], X's size = 1024, 'shape' is [1, 512], the capacity of 'shape' is 512. [Hint: Expected capacity == in_size, but received capacity:512 != in_size:1024.] (at ../paddle/fluid/operators/reshape_op.cc:234) [operator < reshape2 > error]
是纬度不匹配的问题，请修改该代码为后再次尝试：
x2paddle_onnx__Gemm_190 = paddle.reshape(x=x2paddle_onnx__Flatten_189, shape=[2, 512])