训练ppocrv4 报错ValueError: (InvalidArgument) The input of Op(Conv) should be a 4-D or 5-D Tensor.

[wangyang581]

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 20.04 环境为paddle官方docker
• 版本号/Version：paddlepaddle/paddle:2.5.2-gpu-cuda11.2-cudnn8.2-trt8.0
• Paddle：paddlepaddle-gpu：2.5.2.post112
• PaddleOCR：release/2.7
• 问题相关组件/Related components：tools/train.py
• 运行指令/Command Code：python tools/train.py -c configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_distill.yml
• 完整报错/Complete Error Message：
  Traceback (most recent call last):
  File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
  "main", mod_spec)
  File "/usr/lib/python3.7/runpy.py", line 85, in _run_code
  exec(code, run_globals)
  File "/root/.vscode-server/extensions/ms-python.python-2023.4.1/pythonFiles/lib/python/debugpy/adapter/../../debugpy/launcher/../../debugpy/main.py", line 39, in
  cli.main()
  File "/root/.vscode-server/extensions/ms-python.python-2023.4.1/pythonFiles/lib/python/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 430, in main
  run()
  File "/root/.vscode-server/extensions/ms-python.python-2023.4.1/pythonFiles/lib/python/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 284, in run_file
  runpy.run_path(target, run_name="main")
  File "/root/.vscode-server/extensions/ms-python.python-2023.4.1/pythonFiles/lib/python/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 322, in run_path
  pkg_name=pkg_name, script_name=fname)
  File "/root/.vscode-server/extensions/ms-python.python-2023.4.1/pythonFiles/lib/python/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 136, in _run_module_code
  mod_name, mod_spec, pkg_name, script_name)
  File "/root/.vscode-server/extensions/ms-python.python-2023.4.1/pythonFiles/lib/python/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 124, in _run_code
  exec(code, run_globals)
  File "/paddle/tools/train.py", line 227, in
  main(config, device, logger, vdl_writer)
  File "/paddle/tools/train.py", line 202, in main
  amp_dtype)
  File "/paddle/tools/program.py", line 301, in train
  preds = model(images, data=batch[1:])
  File "/usr/local/lib/python3.7/dist-packages/paddle/nn/layer/layers.py", line 1254, in call
  return self.forward(*inputs, **kwargs)
  File "/paddle/ppocr/modeling/architectures/distillation_model.py", line 59, in forward
  result_dict[model_name] = self.model_list[idx](x, data)
  File "/usr/local/lib/python3.7/dist-packages/paddle/nn/layer/layers.py", line 1254, in call
  return self.forward(*inputs, **kwargs)
  File "/paddle/ppocr/modeling/architectures/base_model.py", line 100, in forward
  x = self.head(x, targets=data)
  File "/usr/local/lib/python3.7/dist-packages/paddle/nn/layer/layers.py", line 1254, in call
  return self.forward(*inputs, **kwargs)
  File "/paddle/ppocr/modeling/heads/rec_multi_head.py", line 92, in forward
  ctc_encoder = self.ctc_encoder(x)
  File "/usr/local/lib/python3.7/dist-packages/paddle/nn/layer/layers.py", line 1254, in call
  return self.forward(*inputs, **kwargs)
  File "/paddle/ppocr/modeling/necks/rnn.py", line 261, in forward
  x = self.encoder(x)
  File "/usr/local/lib/python3.7/dist-packages/paddle/nn/layer/layers.py", line 1254, in call
  return self.forward(*inputs, **kwargs)
  File "/paddle/ppocr/modeling/necks/rnn.py", line 208, in forward
  z = self.conv1(z)
  File "/usr/local/lib/python3.7/dist-packages/paddle/nn/layer/layers.py", line 1254, in call
  return self.forward(*inputs, **kwargs)
  File "/paddle/ppocr/modeling/backbones/rec_svtrnet.py", line 68, in forward
  out = self.conv(inputs)
  File "/usr/local/lib/python3.7/dist-packages/paddle/nn/layer/layers.py", line 1254, in call
  return self.forward(*inputs, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/paddle/nn/layer/conv.py", line 722, in forward
  use_cudnn=self._use_cudnn,
  File "/usr/local/lib/python3.7/dist-packages/paddle/nn/functional/conv.py", line 141, in _conv_nd
  data_format,
  ValueError: (InvalidArgument) The input of Op(Conv) should be a 4-D or 5-D Tensor. But received: input's dimension is 3, input's shape is [8, 240, 256].
  [Hint: Expected in_dims.size() == 4 || in_dims.size() == 5 == true, but received in_dims.size() == 4 || in_dims.size() == 5:0 != true:1.] (at ../paddle/phi/infermeta/binary.cc:475)

我镜像中用相同的数据可以用ch_PP-OCRv4_rec_hgnet.yml配置文件训练，也可以用v3的配置文件训练，只有ch_PP-OCRv4_rec_distill.yml这个配置文件报错。

我采用的ch_PP-OCRv4_rec_distill.yml配置文件的内容如下：

Global:
debug: false
use_gpu: true
epoch_num: 200
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_dkd_400w_svtr_ctc_lcnet_blank_dkd0.1/
save_epoch_step: 40
eval_batch_step:

• 0
• 2000
  cal_metric_during_train: true
  pretrained_model: ./pre_train/rec/ch_PP-OCRv4_rec_train/student.pdparams
  checkpoints:
  save_inference_dir: doc/imgs_words/ch/
  use_visualdl: false
  infer_img: doc/imgs_words/ch/word_1.jpg
  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
  max_text_length: &max_text_length 25
  infer_mode: false
  use_space_char: true
  distributed: true
  save_res_path: ./output/rec/predicts_ppocrv3.txt
  Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
  name: Cosine
  learning_rate: 0.001
  warmup_epoch: 2
  regularizer:
  name: L2
  factor: 3.0e-05
  Architecture:
  model_type: rec
  name: DistillationModel
  algorithm: Distillation
  Models:
  Teacher:
  pretrained:
  freeze_params: true
  return_all_feats: true
  model_type: rec
  algorithm: SVTR
  Transform: null
  Backbone:
  name: SVTRNet
  img_size:
  - 48
  - 320
  out_char_num: 40
  out_channels: 192
  patch_merging: Conv
  embed_dim:
  - 64
  - 128
  - 256
  depth:
  - 3
  - 6
  - 3
  num_heads:
  - 2
  - 4
  - 8
  mixer:
  - Conv
  - Conv
  - Conv
  - Conv
  - Conv
  - Conv
  - Global
  - Global
  - Global
  - Global
  - Global
  - Global
  local_mixer:
  - - 5
  - 5
  - - 5
  - 5
  - - 5
  - 5
  last_stage: false
  prenorm: true
  Head:
  name: MultiHead
  head_list:
  - CTCHead:
  Neck:
  name: svtr
  dims: 120
  depth: 2
  hidden_dims: 120
  kernel_size: [1, 3]
  use_guide: True
  Head:
  fc_decay: 0.00001
  - NRTRHead:
  nrtr_dim: 384
  max_text_length: *max_text_length
  Student:
  pretrained:
  freeze_params: false
  return_all_feats: true
  model_type: rec
  algorithm: SVTR
  Transform: null
  Backbone:
  name: PPLCNetV3
  scale: 0.95
  Head:
  name: MultiHead
  head_list:
  - CTCHead:
  Neck:
  name: svtr
  dims: 120
  depth: 2
  hidden_dims: 120
  kernel_size: [1, 3]
  use_guide: True
  Head:
  fc_decay: 0.00001
  - NRTRHead:
  nrtr_dim: 384
  max_text_length: *max_text_length
  Loss:
  name: CombinedLoss
  loss_config_list:
• DistillationDKDLoss:
  weight: 0.1
  model_name_pairs:
  • • Student
    • Teacher
      key: head_out
      multi_head: true
      alpha: 1.0
      beta: 2.0
      dis_head: gtc
      name: dkd
• DistillationCTCLoss:
  weight: 1.0
  model_name_list:
  • Student
    key: head_out
    multi_head: true
• DistillationNRTRLoss:
  weight: 1.0
  smoothing: false
  model_name_list:
  • Student
    key: head_out
    multi_head: true
• DistillCTCLogits:
  weight: 1.0
  reduction: mean
  model_name_pairs:
  • • Student
    • Teacher
      key: head_out
      PostProcess:
      name: DistillationCTCLabelDecode
      model_name:
• Student
  key: head_out
  multi_head: true
  Metric:
  name: DistillationMetric
  base_metric_name: RecMetric
  main_indicator: acc
  key: Student
  ignore_space: false
  Train:
  dataset:
  name: SimpleDataSet
  data_dir: ./train_data/lpd_rec
  label_file_list:

  • ./train_data/lpd_rec/train.txt
    ratio_list:

  • 1.0
    transforms:

  • DecodeImage:
    img_mode: BGR
    channel_first: false

  • RecAug:

  • MultiLabelEncode:
    gtc_encode: NRTRLabelEncode

  • RecResizeImg:
    image_shape: [3, 48, 320]

  • KeepKeys:
    keep_keys:

    • image
    • label_ctc
    • label_gtc
    • length
    • valid_ratio
      loader:
      shuffle: true
      batch_size_per_card: 8
      drop_last: true
      num_workers: 2
      use_shared_memory: true
      Eval:
      dataset:
      name: SimpleDataSet
      data_dir: ./train_data/lpd_rec
      label_file_list:

  • ./train_data/lpd_rec/test.txt
    transforms:

  • DecodeImage:
    img_mode: BGR
    channel_first: false

  • MultiLabelEncode:
    gtc_encode: NRTRLabelEncode

  • RecResizeImg:
    image_shape: [3, 48, 320]

  • KeepKeys:
    keep_keys:

    • image
    • label_ctc
    • label_gtc
    • length
    • valid_ratio
      loader:
      shuffle: false
      drop_last: false
      batch_size_per_card: 8
      num_workers: 2
      profiler_options: null

请问我要如何修改呢？

[704572066]

很多人都遇到这个问题

[lizhq]

yes , 此预训练模型对应下面配置文件

Global:
debug: false
use_gpu: true
epoch_num: 20
log_smooth_window: 20
print_batch_step: 1
save_model_dir: /home/aistudio/output/Student/pt
save_epoch_step: 20
eval_batch_step:

• 0
• 2000
  cal_metric_during_train: true
  pretrained_model: https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_rec_train/student.pdparams
  checkpoints: ''
  save_inference_dir: null
  use_visualdl: true
  infer_img: doc/imgs_words/ch/word_1.jpg
  character_dict_path: /home/aistudio/paddleXdata/dict.txt
  max_text_length: 25
  infer_mode: false
  use_space_char: true
  distributed: true
  save_res_path: ./output/rec/predicts_ppocrv3.txt
  eval_batch_epoch: 5
  use_xpu: false
  use_npu: false
  use_mlu: false
  to_static: false
  use_amp: false
  amp_level: 'OFF'
  Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
  name: Cosine
  learning_rate: 0.0001
  warmup_epoch: 3
  regularizer:
  name: L2
  factor: 3.0e-05
  Architecture:
  model_type: rec
  algorithm: SVTR_LCNet
  Transform: null
  Backbone:
  name: PPLCNetV3
  scale: 0.95
  Head:
  name: MultiHead
  head_list:
  • CTCHead:
    Neck:
    name: svtr
    dims: 120
    depth: 2
    hidden_dims: 120
    kernel_size:
    - 1
    - 3
    use_guide: true
    Head:
    fc_decay: 1.0e-05
  • NRTRHead:
    nrtr_dim: 384
    max_text_length: 25
    Loss:
    name: MultiLoss
    loss_config_list:
• CTCLoss: null
• NRTRLoss: null
  PostProcess:
  name: CTCLabelDecode
  Metric:
  name: RecMetric
  main_indicator: acc
  Train:
  dataset:
  name: MSTextRecDataset
  ds_width: false
  data_dir: /home/aistudio/paddleXdata
  ext_op_transform_idx: 1
  label_file_list:
  • /home/aistudio/output/Teacher/teacher_best/merged_label.txt
    transforms:
  • DecodeImage:
    img_mode: BGR
    channel_first: false
  • RecConAug:
    prob: 0.5
    ext_data_num: 2
    image_shape:
    • 48
    • 320
    • 3
      max_text_length: 25
  • RecAug: null
  • MultiLabelEncode:
    gtc_encode: NRTRLabelEncode
  • KeepKeys:
    keep_keys:
    • image
    • label_ctc
    • label_gtc
    • length
    • valid_ratio
      sampler:
      name: MultiScaleSampler
      scales:
  • • 320
    • 32
  • • 320
    • 48
  • • 320
    • 64
      first_bs: 64
      fix_bs: false
      divided_factor:
  • 8
  • 16
    is_training: true
    loader:
    shuffle: true
    batch_size_per_card: 64
    drop_last: true
    num_workers: 8
    Eval:
    dataset:
    name: TextRecDataset
    data_dir: /home/aistudio/paddleXdata
    label_file_list:
  • /home/aistudio/paddleXdata/val.txt
    transforms:
  • DecodeImage:
    img_mode: BGR
    channel_first: false
  • MultiLabelEncode:
    gtc_encode: NRTRLabelEncode
  • RecResizeImg:
    image_shape:
    • 3
    • 48
    • 320
  • KeepKeys:
    keep_keys:
    • image
    • label_ctc
    • label_gtc
    • length
    • valid_ratio
      loader:
      shuffle: false
      drop_last: false
      batch_size_per_card: 64
      num_workers: 4
      profiler_options: null

[fxfxfxfxfxfxfxfx]

请问这个·问题解决了吗

[leduy-it]

@tink2123 can you take a look of this issue?

[github-actions]

This issue is stale because it has been open for 90 days with no activity.

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.