Couldn't find x2paddle_52_p0 in previous layers, the layers should be make by topological sort

[duorouputao]

感谢您参与 X2Paddle 社区！ 问题模版为了 X2Paddle 能更好的迭代，例如新功能发布、 RoadMaps 和错误跟踪. :smile_cat:

问题描述

• 错误信息
• 错误截图

具体信息

• 转换模型后用处
  • [ ] 使用 Paddle 框架/ PaddleInference 推理预测
  • [√] 使用 Paddle-Lite 做移动端推理
  • [ ] 转换预训练参数，再使用 Paddle 进行模型开发
• 模型来源 lstm
• 应用场景 用于移动端业务下的摔倒检测
• 版本信息 PaddlePaddle => :grey_question: X2Paddle => :grey_question:1.0.1 来源框架版本(PyTorch/TF/ONNX/Caffe) =>onnx
• 您的联系方式(邮箱/微信/电话) [email protected]

[wjj19950828]

@duorouputao 我看你X2Paddle版本信息1.0.1，建议升级到最新版本1.3.6再试试

[duorouputao]

更新了还是不行 C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\urllib3\util\selectors.py:14: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working from collections import namedtuple, Mapping C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\urllib3_collections.py:2: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working from collections import Mapping, MutableMapping paddle.version = 2.2.2 Now translating model from onnx to paddle. model ir_version: 6, op version: 9 shape inferencing ... shape inferenced. Now, onnx2paddle support convert onnx model opset_verison [9],opset_verison of your onnx model is 9, automatically treated as op_set: 9. Total nodes: 23 Nodes converting ... Converting node 28 ... ['lstm0.weight_ih_l0', 'lstm0.weight_hh_l0', 'lstm0.bias_ih_l0', 'lstm0.bias_hh_l0'] Converting node 30 ... ['lstm1.weight_ih_l0', 'lstm1.weight_hh_l0', 'lstm1.bias_ih_l0', 'lstm1.bias_hh_l0'] Converting node 37 ... Nodes converted. Traceback (most recent call last): File "d:\programdata\miniconda3\envs\py37\lib\runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "d:\programdata\miniconda3\envs\py37\lib\runpy.py", line 85, in run_code exec(code, run_globals) File "D:\ProgramData\Miniconda3\envs\py37\Scripts\x2paddle.exe_main.py", line 7, in File "D:\Gitprj\fall\X2Paddle-develop\x2paddle\convert.py", line 264, in main onnx2paddle(args.model, args.save_dir, args.paddle_type) File "D:\Gitprj\fall\X2Paddle-develop\x2paddle\convert.py", line 173, in onnx2paddle mapper.paddle_graph.build() File "D:\Gitprj\fall\X2Paddle-develop\x2paddle\core\program.py", line 181, in build v) AssertionError: Couldn't find x2paddle_52_p0 in previous layers, the layers should be make by topological sort

[wjj19950828]

@duorouputao 麻烦把ONNX模型上传到百度云吧，这边排期看一下

另外这是个什么模型呢，这有一份问卷也麻烦填一下吧：https://iwenjuan.baidu.com/?code=npyd51

[duorouputao]

okok,是个带lstm的 https://pan.baidu.com/s/1igMqqxF5gDWQVFWd3emZfA 提取码：4988 麻烦大佬们看下