自己构建的模型转换成inference model时报错

[CharmingHue]

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

• 系统环境/System Environment：

• ubuntu

• 版本号/Version：

• 18.04

• Paddle：2.4.0 PaddleOCR：

• dygraph

• 问题相关组件/Related components：

• export_model.py

• 运行指令/Command Code：

• python3 tools/export_model.py -c configs/rec/rec_cloformer_cppd.yml -o Global.pretrained_model=./pretrain/rec_cloformer_cppd_base/best_accuracy_old.pdparams Global.save_inference_dir=./rec_cloformer_cppd_infer

• 完整报错/Complete Error Message：
  Traceback (most recent call last):
  File "tools/export_model.py", line 293, in
  main()
  File "tools/export_model.py", line 288, in main
  export_single_model(
  File "tools/export_model.py", line 199, in export_single_model
  paddle.jit.save(model, save_path)
  File "/root/miniconda3/lib/python3.8/site-packages/decorator.py", line 232, in fun
  return caller(func, *(extras + args), **kw)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/wrapped_decorator.py", line 26, in impl
  return wrapped_func(*args, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/jit.py", line 649, in wrapper
  func(layer, path, input_spec, **configs)
  File "/root/miniconda3/lib/python3.8/site-packages/decorator.py", line 232, in fun
  return caller(func, *(extras + args), **kw)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/wrapped_decorator.py", line 26, in impl
  return wrapped_func(*args, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/base.py", line 67, in impl
  return func(*args, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/jit.py", line 927, in save
  concrete_program = static_func.concrete_program_specify_input_spec(
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 577, in concrete_program_specify_input_spec
  concrete_program, _ = self.get_concrete_program(
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 485, in get_concrete_program
  concrete_program, partial_program_layer = self._program_cache[cache_key]
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 955, in getitem
  self._caches[item_id] = self._build_once(item)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 939, in build_once
  concrete_program = ConcreteProgram.from_func_spec(
  File "/root/miniconda3/lib/python3.8/site-packages/decorator.py", line 232, in fun
  return caller(func, *(extras + args), **kw)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/wrapped_decorator.py", line 26, in impl
  return wrapped_func(*args, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/base.py", line 67, in impl
  return func(*args, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/dygraph_to_static/program_translator.py", line 895, in from_func_spec
  error_data.raise_new_exception()
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/dygraph_to_static/error.py", line 350, in raise_new_exception
  six.exec("raise new_exception from None")
  File "", line 1, in
  ValueError: In transformed code:

  File "/root/PaddleOCR/ppocr/modeling/architectures/base_model.py", line 85, in forward
  if self.use_backbone:
  File "/root/PaddleOCR/ppocr/modeling/architectures/base_model.py", line 86, in forward
  x = self.backbone(x)
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 544, in forward
  x = self.forward_feature(x)
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 535, in forward_feature
  for layer in self.layers:
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 536, in forward_feature
  x = layer(x)
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 418, in forward
  for blk in self.blocks:
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 419, in forward
  x = blk(x)
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 375, in forward
  x = x + self.drop_path(self.attn(self.norm1(x)))
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 314, in forward
  for i in range(len(self.kernel_sizes)):
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 317, in forward
  res.append(self.high_fre_attntion(x, self.qkvs[i], self.convs[i], self.act_blocks[i]))
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 287, in high_fre_attntion
  attn = attn_block(q.multiply(k)).multiply(paddle.to_tensor(self.scalor))
  File "/root/PaddleOCR/ppocr/modeling/backbones/rec_cloformer.py", line 234, in forward
  return self.act_block(x)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/container.py", line 97, in forward
  for layer in self._sub_layers.values():
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/container.py", line 98, in forward
  def forward(self, input):
  for layer in self._sub_layers.values():
  input = layer(input)
  ~~~~~~~~~~~~~~~~~~~~ <--- HERE
  return input

  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 950, in call
  return self._dygraph_call_func(*inputs, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 935, in _dygraph_call_func
  outputs = self.forward(*inputs, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/nn/layer/conv.py", line 712, in forward
  out = F.conv._conv_nd(
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/nn/functional/conv.py", line 276, in _conv_nd
  helper.append_op(
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/layer_helper.py", line 45, in append_op
  return self.main_program.current_block().append_op(*args, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/framework.py", line 4017, in append_op
  op = Operator(
  File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/framework.py", line 3016, in init
  self.desc.infer_shape(self.block.desc)

  ValueError: (InvalidArgument) The number of input's channels should be equal to filter's channels * groups for Op(Conv). But received: the input's channels is -1, the input's shape is [-1, -1, 8, 32]; the filter's channels is 64, the filter's shape is [64, 64, 1, 1]; the groups is 1, the data_format is NCHW. The error may come from wrong data_format setting.
  [Hint: Expected input_channels == filter_dims[1] * groups, but received input_channels:-1 != filter_dims[1] * groups:64.] (at /paddle/paddle/fluid/operators/conv_op.cc:131)
  [operator < conv2d > error]
  请尽量不要包含图片在问题中/Please try to not include the image in the issue.

[cuicheng01]

麻烦问下自己构建的模型和官方的模型差异大吗？

[CharmingHue]

麻烦问下自己构建的模型和官方的模型差异大吗？

我是自己构建的文本识别编码器，解码器直接用的是CPPD，模型可以正常训练和测试，但是在转inference模型想测试FPS时，会报上面的错误