X2Paddle icon indicating copy to clipboard operation
X2Paddle copied to clipboard

Deep learning model converter for PaddlePaddle. (『飞桨』深度学习模型转换工具)

Results 232 X2Paddle issues
Sort by recently updated
recently updated
newest added

ckpt格式转pb格式后,然后用x2paddle转换出现以下问题: ![图片](https://user-images.githubusercontent.com/107793491/174709101-424624cf-21b1-4cad-80fc-affa5f8850c3.png) 询问占位符形状然后自己输入None然后转换第22节点出现以下报错 ![图片](https://user-images.githubusercontent.com/107793491/174709356-c6718336-5dd8-4027-83db-316bb4683f24.png) TypeError: 'NoneType' object is not subscriptable 输入 ![图片](https://user-images.githubusercontent.com/107793491/174709915-6528f1ad-82b0-4eae-b6eb-3d2cdc31dc58.png) - 转换模型后用处 模型移植到edgeboard板子 - 应用场景 学生学习用 - 版本信息 PaddlePaddle => 2.3.0 X2Paddle =>1.3.7 tensorflow1.2.1 python3.6

TensorFlow

# Create A Good Pull Request > 下面的文字请保留在PR说明的最后面,并在提完PR后,根据实际情况勾选确认以下情况 Please check the follow step before merging this pull request - [x] Python code style verification - [x] Review all the code...

pytorch转pp模型,提示算子不支持。是否可以先转onnx,在转pp pytorch模型来源:https://github.com/cfzd/Ultra-Fast-Lane-Detection 工具:全部为最新版本 报错信息: INFO 2022-06-22 09:45:43,293 convert.py:333] Now translating model from PyTorch to Paddle. Traceback (most recent call last): File "E:\pythonProject\testLaneDetect\main.py", line 60, in pytorch2paddle(module=torch_model, File "C:\Users\uidq5147\.conda\envs\paddle_dev\lib\site-packages\x2paddle\convert.py", line 343,...

PyTorch

F:\work\CRE-StereoNet\CREStereo-Pytorch-main\weights>x2paddle --framework=onnx --model=cre_new.onnx --save_dir=pd_model F:\software\python\lib\site-packages\setuptools\depends.py:2: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses import imp INFO:root:paddle.__version__ = 2.3.0 INFO:root:Now translating model...

ONNX

# Create A Good Pull Request > 下面的文字请保留在PR说明的最后面,并在提完PR后,根据实际情况勾选确认以下情况 Please check the follow step before merging this pull request - [x] Python code style verification - [x] Review all the code...

各位开发者们,你们好! ## 问题描述 模型来源: onnx 模型说明: bert预训练模型 模型文件:[bert.onnx](https://github.com/kotori-y/my_data/releases/download/v0.1/bert.onnx) ## 报错内容 ```shell (x2paddle-env) [root@DESKTOP-P0RLOPV BERT-pytorch-alpha0.0.1a5]# x2paddle --framework=onnx --model=bert.onnx --save_dir=pd_model WARNING: Logging before InitGoogleLogging() is written to STDERR W0518 13:48:45.141453 3156 default_variables.cpp:429]...

ONNX

========= 3 OPs are not supported yet =========== ========== aten::upsample_nearest1d ============ ========== aten::upsample_nearest3d ============ ========== aten::reciprocal ============

PyTorch

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 lstm onnx 模型转paddle失败,用了onnx-simple也不行,使用x2paddle1.3.5 - 错误信息 - 错误截图 File "C:\Users\admin\anaconda3\envs\py37_tensorflow1_14\lib\site-packages\x2paddle-1.3.5-py3.7.egg\x2paddle\op_mapper\onnx2paddle\opset9\opset.py", line 107, in run_mapping res = func(*args, **kwargs) File "C:\Users\admin\anaconda3\envs\py37_tensorflow1_14\lib\site-packages\x2paddle-1.3.5-py3.7.egg\x2paddle\op_mapper\onnx2paddle\opset9\opset.py",...

ONNX

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 使用onnx2paddle将onnx的BiLSTM模型转换为paddle模型报错,转换失败。 - 错误信息 ### 使用onnx2paddle转化模型报错: 原ONNX模型转化时opset_version=11: ``` In transformed code: File "model\pd_model\x2paddle_code.py", line 78, in forward x2paddle_onnx__LSTM_47 = paddle.reshape(x=x2paddle_onnx__LSTM_47,...

ONNX