Description
有算子不支持要怎么修改，文档不是说x2paddle1.6.0支持onnx17吗
问题描述
root@autodl-container-bdf4448313-53c1871e:~/autodl-tmp# x2paddle --framework=onnx --model=./model/superpoint_lightglue_pipeline.onnx --save_dir=pd_model --to_lite=True --lite_valid_places=arm --lite_model_type=naive_buffer
/root/miniconda3/lib/python3.8/site-packages/paddle/utils/cpp_extension/extension_utils.py:711: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
warnings.warn(warning_message)
WARNING: OMP_NUM_THREADS set to 18, not 1. The computation speed will not be optimized if you use data parallel. It will fail if this PaddlePaddle binary is compiled with OpenBlas since OpenBlas does not support multi-threads.
PLEASE USE OMP_NUM_THREADS WISELY.
onnx2paddle ...
Now translating model from onnx to paddle.
model ir_version: 8, op version: 17
Shape inferencing ...
[WARNING] Incomplete symbolic shape inference
Shape inferenced.
Now, onnx2paddle support convert onnx model opset_verison [7, 8, 9, 10, 11, 12, 13, 14, 15], opset_verison of your onnx model is 17.
========= 2 OPs are not supported yet ===========
========== LayerNormalization ============
========== GridSample ============
Traceback (most recent call last):
File "/root/miniconda3/bin/x2paddle", line 8, in
sys.exit(main())
File "/root/miniconda3/lib/python3.8/site-packages/x2paddle/convert.py", line 504, in main
onnx2paddle(args.model,
File "/root/miniconda3/lib/python3.8/site-packages/x2paddle/convert.py", line 324, in onnx2paddle
mapper = ONNXOpMapper(model)
File "/root/miniconda3/lib/python3.8/site-packages/x2paddle/op_mapper/onnx2paddle/onnx_op_mapper.py", line 39, in init
raise Exception("Model is not supported yet.")
Exception: Model is not supported yet.
具体信息
-
转换模型后用处
使用 Paddle-Lite 做移动端推理
-
模型来源
lightglue：https://github.com/fabio-sim/LightGlue-ONNX.git -
应用场景
用于移动端业务下的图像匹配 -
版本信息
PaddlePaddle => :PaddlePaddle 3.0.0, compiled with
with_avx: ON
with_gpu: OFF
with_mkl: ON
with_mkldnn: ON
with_python: ON
X2Paddle => :1.6.0
来源框架版本(ONNX) => :opset_version=17
[email protected]