Alexey

@trustin77 I would say that saturation issue comes from the different range and precision of INT8 and FLOAT32, since `0` value can be saturated too. F.e. if we have initial...

> How can I get these files: data/obj.data, yolo-obj.cfg, yolo-obj_10000.weights ? You should create `data/obj.data`, `yolo-obj.cfg` and train `yolo-obj_10000.weights` by yourself if you want to use custom model: https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects Or...

@trustin77 There is calibrated only all cfg-files from this directory: https://github.com/AlexeyAB/yolo2_light/tree/master/bin I.e. if `input_calibrate=` parameter is in the cfg-file, then it is calibrated.

Yes, there is some issue with XNOR model for width or height

@jjeong19 Hi, XNOR weights are stored in .weights-file in FP32 format. During loading the XNOR weights are converted to BIN1, so both weights and input are used as BIN1, to...

@Thilanka97 I didn't do this, but yes - it is possible. At first, try to implement maxpool-int32 and divide inputs by `l->output_multipler` (or by `R_MULT / (l.input_quant_multipler * l.weights_quant_multipler` )...

I fixed it. Try to update your code from GitHub and recompile.

@trustin77 Hi, I have not seen step by step instructions on how to do this. I used these documentations: * How Float-32 is converted to the INT-8 in the TensorRT:...

May be I will add it later.

@Thilanka97 Hi, I just tried to reproduce what was done in the TensorRT: http://on-demand.gputechconf.com/gtc/2017/presentation/s7310-8-bit-inference-with-tensorrt.pdf And cuDNN is optimized for INT8 or UINT8. > Also what did you do to the...