tonyskypc

Question about INT8 quantization Slower

7

## Description yolov5s base pytorch-quantization reference https://github.com/maggiez0138/yolov5_quant_sample onnx->fp16 3ms qat->onnx->int8 4ms why? please tell me，thanks. [onnx file download](https://drive.google.com/file/d/1Q1u81E0yLVrwHgazTN-l38ZyEFL78ggz/view) ## Environment **TensorRT Version**:8.2 **NVIDIA GPU**: geforce 3060ti **NVIDIA Driver Version**: 510...

Quantization: MQBench 加载出错了

2

@Gumpest 大佬，在使用MQBench,加载网络就出错了，能帮忙看看原因吗？ 加载到第3层出现如下错误 index 0 is out of bounds for dimension 0 with size 0 关闭量化参数quantize，就正常，请教

yolo-pose custom train question

3

git code about yolo-pose,use coco 2017 data train,detect result keypoint out of range. 

## ❔Question base coco 2017 dataset trian, this is [pretrained_weights]: http://software-dl.ti.com/jacinto7/esd/modelzoo/gplv3/08_02_00_11/edgeai-yolov5/pretrained_models/checkpoints/keypoint/coco/edgeai-yolov5/other/person_detector/yolov5s6_960_71p6_93p1/weights/last.pt but trained,detect keypoints result out of range ,please tell me,Thanks. ## Additional context

helper