edgeai-yolov5
edgeai-yolov5 copied to clipboard
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
## ❔Question The prediction result of the network after flipping up and down is quite different, how can we improve it?(the picture originates from the internet) ## Additional context ![R-C...
## ❔Question this code define 17 and some other num, but I want get another keypoint num, and how do I need to modify the model part? ## Additional context...
## ❔Question In the prediction result of multiple people in a picture, the box of the human frame does not correspond to the key point kpts, and the matrix here...
## ❔Question **This [repository] was used with required changes to generate the dataset in the required format. Please download the processed labels from [here]** How to convert the labels? is...
## ❔Question The COCO dataset's annotation is not complete, for example, when there are crowd persons, the key-points will be not annotated and a segment mask annotate the persons are...
## When training the dataset, Nan appears ## When I started trying to train the COCO2017 dataset, first it was normal, but then there was Nan, which I thought might...
Why are the official yolopose-m6 and yolopose-l6 parameters and GMACS so different from those reported in the paper? In paper:  actual model parameter: yolopose-s6:  yolopose-m6:  yolopose-l6: 
## ❔Question In regular yolo label format there will be CLASS+xywh(normalized) 5 columns in total,and I used to train on yolov5-face which add 8 coordinates(normalized) in the end of the...
Before submitting a bug report, please be aware that your issue **must be reproducible** with all of the following, otherwise it is non-actionable, and we can not help you: -...
## ❔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