ramsonjehu

Hi @Lynazhang , Can you elaborate a little bit on the following? **_Note that you need to implement the followings: (i) set up the device and the connection; (ii) profiling...

Hi @JiahangXu , I have implemented the backend class and detected fusion rules. Currently building kernel latency predictors. I would like to know if any updates on reference code for...

Hi @JiahangXu , Thanks for the update. I'm also curious about quantize predictor, when is it planned to release?

I'm not using any script. Indeed what i did is, To evaluate the model, I have added the posenet_decoder op implementation from here (https://github.com/google-coral/coralmicro/blob/main/libs/tensorflow/posenet_decoder_op.cc) to the tflite micro library and...

I have uploaded the source files in google drive, Here is the [link](https://drive.google.com/file/d/1sSXpEm1RJGPY-q9riSTjAEE-qd97n75E/view?usp=sharing). Please find the build and execution steps in the readme.txt file. The source was built and tested...

I used the PoseNet MobileNet V1 CPU model with input size 353x481x3 in that source which was taken from [https://coral.ai/models/pose-estimation/](https://coral.ai/models/pose-estimation/).

Hi @hjonnala, I think this issue is with the posenet_decoder implementation in [posenet_decoder_op.cc](https://github.com/google-coral/coralmicro/blob/main/libs/tensorflow/posenet_decoder_op.cc). why because, the same model when run using TFLite interpreter. The output is correct. Please checkout this...

hi @hjonnala , Any updates on this? Thanks