Ninesheng9 opened a new issue, #13555: URL: https://github.com/apache/tvm/issues/13555
### Expected behavior When I used tvmc to convert PaddlePaddle models to C code, although some models can generate final files I need, the following prompts will appear: <img width="1114" alt="image" src="https://user-images.githubusercontent.com/74167626/205804921-074e7431-ef9f-4af1-8b14-4e0dd0cb4b27.png"> I don't know the exactly reason. ### Environment apache-tvm 0.10.0 paddlepaddle 2.3.2 Python 3.9.12 ### Steps to reproduce My code: tvmc compile --target=cmsis-nn,c \ --target-c-mcpu=cortex-m55 \ --runtime=crt \ --executor=aot \ --executor-aot-interface-api=c \ --executor-aot-unpacked-api=1 \ --pass-config tir.usmp.enable=1 \ --pass-config tir.usmp.algorithm=hill_climb \ --pass-config tir.disable_storage_rewrite=1 \ --pass-config tir.disable_vectorize=1 fastscnn_cityscapes_1024x1024_160k/model.pdmodel \ --output-format=mlf \ --model-format=paddle \ --module-name=fastscnn_cityscapes_1024x1024_160k \ --input-shapes "x:[1,3,1024,1024]" \ --output=fastscnn_cityscapes_1024x1024_160k.tar You can find the model at: https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.7/configs/fastscnn -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
