Hardik Dava

Is there any update on this issue? It will be interesting to see the performance on edgetpu.

@keesschollaart81 @Baael I have tried the mentioned workflow. I was able to convert model into tflite but not int8 quantize model which is needed by coral edgetpu. I would still...

We need to perform full integer quantization by using tflite converter on tensorflow saved_model and save int8 tflite model. Then we have to compile the model using edgecompiler which generates...

@glenn-jocher @AyushExel Is this feature available in near future? Is there any branch or PR which is designated for this?

@AyushExel @glenn-jocher I was able to make layers of Ghost model in tensorflow keras. But I got this error ` Exception encountered when calling layer "tf_conv_37" (type TFConv). It has...

@glenn-jocher Thanks for quick reply. Is it possible toc= change grid size of detection layer? I think the bounding box will reduce by decreasing detection grid i.e. from (10,10) to...

@glenn-jocher I was able to run YoloV5s model with input image resolution of 288x288 pixels with 3 anchors at 75 fps by only considering top-k objects rather than all confident...

Thanks for the reply @glenn-jocher

@glenn-jocher I was able to use onnx2tf for tensorflow saved_model, tflite and keras model successfully. But I will test it with every models and submit PR soon.

@jkulhanek can you provide the notebook? Thanks