happy-Bobo

@sagartesla thank you so much for your help, I will try it.

Hi Manu， thanks for your reply, the accuracy loss just a little when I use the caffe-jacinto to test quantize, but when I use the TIDL do inference on platform...

Hi manu thanks for your reply, it is same with you said, I use the "signed char* " to point the output buffer, so the feature I got is -128...

Hi manu, thank you so much！my net is almost same with imagenet, I just do some fine tune on it for train a face classification model. there are all the...

thanks for your help, the net does have 10575 output classes, but the fully connected layer is not contain in the deploy.prototxt when I do the quantize. does it still...

No, I don't need the output of last fully connected layer, I just need the output of first fully connected layer, this vector represent the feature of my input image,...

thanks so much for your suggestion, I will try to add the output to 1024 and do some test. I know that quantization dose not enable for the first frame....

thank you for your reply！

Hello manu, Thank you for your guidance, I have try my best to modify the file "center_loss_layer.cpp", but there are still a few mistakes when I build the caffe-jacinto, I...