DNNLibrary
DNNLibrary copied to clipboard
JDAI-CV
Daquexian's NNAPI Library. ONNX + Android NNAPI
https://github.com/JDAI-CV/DNNLibrary/blob/e17f11e966b2cce7d747799b76bb9843813d4b01/quant.py#L269 Name of input tensor `data` is presumed which is not appropriate for most other model. https://github.com/JDAI-CV/DNNLibrary/blob/e17f11e966b2cce7d747799b76bb9843813d4b01/quant.py#L216 Also there shouldn't be any presume that model needs normalization with mean/dev.
Error while converting ONNX model opset 9 and opset 11 to daq using onnx2daq: libc++abi.dylib: terminating with uncaught exception of type std::out_of_range: unordered_map::at: key not found Platform is MacOSX. Mac...
After running the command `./onnx2daq.AppImage model.onnx mobile_model.daq` , I'm getting this error: ``` terminate called after throwing an instance of 'std::out_of_range' what(): _Map_base::at Aborted (core dumped) ``` I'm obviously working...
Hi, Thanks for this great library! Anyway I failed when trying to build source to create onnx2daq executable in Windows. Below is the error. Please advise. Thanks 
``` terminate called after throwing an instance of 'std::out_of_range' what(): _Map_base::at ``` this is the error while trying to convert https://github.com/onnx/models/tree/master/vision/object_detection_segmentation/yolov3
Hi, Try to convert onnx to daq in Ubuntu but error thrown.  Then I tried to simplify onnx model in https://convertmodel.com/ but error persist. Please advise....
This issue is to summarize all operators which needed to be supported. If you want an operator to be supported, please feel free to post it here. - [x] LRN(#16,...
Without using high level ML framework, and using only Android NNAPI improves the performance of DNN classification? Do you see accelerated response on the same hardware with only Android NNAPI?
When quant8 is true: ModelBuilder.cpp:108, function name: AddNewOperanderror, ret: Bad data When quant8 is false: Model.cpp:88, function name: PredictAfterSetInputBuffererror, ret: Op failed
### Problem Per [README](https://github.com/JDAI-CV/DNNLibrary#if-you-are-an-c-developer-and-dont-care-about-android-app): > ... you need Android NDK, **r17b or higher NDK is necessary** But in fact, in code used definition which available only in r19 https://github.com/JDAI-CV/DNNLibrary/blob/master/dnnlibrary/ModelBuilder.cpp#L358 ###...
