ValueError: too many values to unpack (expected 2) in File "/content/PaddleOCR/ppocr/modeling/heads/proposal_local_graph.py"

[Grula]

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：

( Using on google colab)

• Ubuntu 20.04.6 LTS \n \l

• 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components：

• Cloned from github refhead : fac0387

• paddle version: 2.5.0

• 运行指令/Command Code：

• python tools/export_model.py -c configs/det/det_r50_drrg_ctw.yml -o Global.pretrained_model="./output/det_drrg/best_accuracy" Global.save_inference_dir="./output/det_drrg_inference/"
  ( obtained from https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_en/algorithm_det_drrg_en.md model & config)

• 完整报错/Complete Error Message：

W0718 17:44:47.579499 17274 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 7.5, Driver API Version: 12.0, Runtime API Version: 11.8
W0718 17:44:47.580794 17274 gpu_resources.cc:149] device: 0, cuDNN Version: 8.9.
Compiling user custom op, it will cost a few seconds.....
[2023-07-18 17:44:51,591] [ INFO] dist.py:985 - running build
[2023-07-18 17:44:51,592] [ INFO] dist.py:985 - running build_ext
2023-07-18 17:44:51,787 - INFO - using custom operator only
[2023-07-18 17:44:51,787] [ INFO] extension_utils.py:1475 - using custom operator only
[2023/07/18 17:44:52] ppocr INFO: load pretrain successful from ./output/det_drrg/best_accuracy
Traceback (most recent call last):
File "/content/PaddleOCR/tools/export_model.py", line 269, in
main()
File "/content/PaddleOCR/tools/export_model.py", line 264, in main
export_single_model(
File "/content/PaddleOCR/tools/export_model.py", line 185, in export_single_model
paddle.jit.save(model, save_path)
File "", line 2, in save
File "/usr/local/lib/python3.10/dist-packages/paddle/fluid/wrapped_decorator.py", line 25, in impl
return wrapped_func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/paddle/jit/api.py", line 752, in wrapper
func(layer, path, input_spec, **configs)
File "", line 2, in save
File "/usr/local/lib/python3.10/dist-packages/paddle/fluid/wrapped_decorator.py", line 25, in impl
return wrapped_func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/paddle/fluid/dygraph/base.py", line 75, in impl
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/paddle/jit/api.py", line 1043, in save
static_func.concrete_program_specify_input_spec(
File "/usr/local/lib/python3.10/dist-packages/paddle/jit/dy2static/program_translator.py", line 709, in concrete_program_specify_input_spec
concrete_program, _ = self.get_concrete_program(
File "/usr/local/lib/python3.10/dist-packages/paddle/jit/dy2static/program_translator.py", line 589, in get_concrete_program
concrete_program, partial_program_layer = self._program_cache[
File "/usr/local/lib/python3.10/dist-packages/paddle/jit/dy2static/program_translator.py", line 1249, in getitem
self._caches[item_id] = self._build_once(item)
File "/usr/local/lib/python3.10/dist-packages/paddle/jit/dy2static/program_translator.py", line 1193, in _build_once
concrete_program = ConcreteProgram.from_func_spec(
File "", line 2, in from_func_spec
File "/usr/local/lib/python3.10/dist-packages/paddle/fluid/wrapped_decorator.py", line 25, in impl
return wrapped_func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/paddle/fluid/dygraph/base.py", line 75, in impl
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/paddle/jit/dy2static/program_translator.py", line 1070, in from_func_spec
error_data.raise_new_exception()
File "/usr/local/lib/python3.10/dist-packages/paddle/jit/dy2static/error.py", line 452, in raise_new_exception
raise new_exception from None
ValueError: In transformed code:
File "/content/PaddleOCR/ppocr/modeling/architectures/base_model.py", line 99, in forward
if self.use_head:
File "/content/PaddleOCR/ppocr/modeling/architectures/base_model.py", line 100, in forward
x = self.head(x, targets=data)
File "/content/PaddleOCR/ppocr/modeling/heads/det_drrg_head.py", line 131, in forward
if self.training:
File "/content/PaddleOCR/ppocr/modeling/heads/det_drrg_head.py", line 143, in forward
return self.single_test(inputs)
File "/content/PaddleOCR/ppocr/modeling/heads/det_drrg_head.py", line 165, in single_test
none_flag, graph_data = self.graph_test(pred_maps, feat_maps)
File "/content/PaddleOCR/ppocr/modeling/heads/proposal_local_graph.py", line 382, in call
comp_attribs, text_comps = self.propose_comps_and_attribs(
File "/content/PaddleOCR/ppocr/modeling/heads/proposal_local_graph.py", line 173, in propose_comps_and_attribs
center_region_mask = fill_hole(center_region_mask)
File "/content/PaddleOCR/ppocr/modeling/heads/proposal_local_graph.py", line 36, in fill_hole
def fill_hole(input_mask):
h, w = input_mask.shape
~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
canvas = np.zeros((h + 2, w + 2), np.uint8)
ValueError: too many values to unpack (expected 2)

[Grula]

Since the model needs to be converted to Numpy data for many times in the forward, DRRG dynamic graph to static graph is not supported.

i missed this

[nguyengiaphuc1992]

I encountered a similar error, please help me fix it.

[Grula]

I encountered a similar error, please help me fix it.

Inference of this model is not possible, https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_en/algorithm_det_drrg_en.md#4-4