MMXuan

very appreciate my email is [email protected]

@Cadene perfect work, that's what i want, very thanks

try both command as follow has the same error, my tensorflow version is 1.8.0 python predict.py --model_path NYU_ResNet-UpProj.npy --image_paths ~/Downloads/dp/t4.jpg python predict.py --model_path NYU_FCRN-checkpoint/NYU_FCRN.ckpt.data-00000-of-00001 --image_paths ~/Downloads/dp/t4.jpg what the right code...

i use tensorflow ckpt not modify the predict.py code, and error info like i post

but crash at set nnapi provider, even not reach Session create code, as error info: Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_Nnapi(sessionOptions, nnapi_flags)); i can get the right result, but when i use nnapi provider get...

> I don't think NNAPI EP supports LSTM. There is no such op in [its op registration code](https://github.com/microsoft/onnxruntime/blob/03181caeaef9343bd2e8d7999386893562ebb23a/onnxruntime/core/providers/nnapi/nnapi_builtin/builders/op_builder.cc#L2633). as nnapi doc show, it support lstm op,  https://developer.android.com/ndk/reference/group/neural-networks#group___neural_networks_1ggaabbe492c60331b13038e39d4207940e0ad0377e8c305e596fb7f64ff896671fc5

> Seems like your runtime error comes from a vendor extensions issue, which is outside of ORT. https://source.android.com/devices/neural-networks/vendor-extensions > > Currently the ORT NNAPI execution provider does not have support...

@skottmckay do nnapi support armv7a, in my case i compiled nnapi arm64v8a run success, but armv7a crash on create session?

@wangxinxin08 我在导出human det的模型的时候碰到同样的shape问题 python tools/export_model.py -c configs/pphuman/ppyoloe_crn_s_36e_crowdhuman.yml -o weights=output_inference/mot_ppyoloe_s_36e_pipeline/mot_ppyoloe_s_36e_pipeline.pdparams --output_dir export 然后使用paddle2onnx --model_dir . --model_filename model.pdmodel --params_filename model.pdiparams --save_file model.onnx --enable_dev_version True --opset_version 15 --input_shape_dict="{'image': [1,3,640,640], 'scale_factor':[1, 2]}"导出onnx 使用onnxruntime加载时出下面错误，都是使用最新版本代码

@gpleiss will you continue support the new jit feature?