edgeai-yolov5

edgeai-yolov5 copied to clipboard

![Uploading test.jpg…]() Why do I use detect.py where the key points are all at the edges of the image, and I use pre trained weights ## 🐛 Bug A clear...

Song-Jie-ing

## ❔Question When I used yolov5-sp6.pt weight to predict images, I encountered an error ## Additional context Traceback (most recent call last): File "D:\PycharmProjects\PycharmProjects\edgeai-yolov5-yolo-pose\edgeai-yolov5-yolo-pose\detect.py", line 204, in detect(opt=opt) File "D:\PycharmProjects\PycharmProjects\edgeai-yolov5-yolo-pose\edgeai-yolov5-yolo-pose\detect.py",...

Song-Jie-ing

keypoint prediction error

5

detect by this weight:  result:  I was beginning to think it was a post-process error,but when I print the pred of detect.py,the y of keypoint of the person...

sankexin

## ❔Question I run below command, and it generated the result image, but the bbox and points seem not correct. ``` python yolo_pose_onnx_inference.py --model-path ../weights/yolov5s6_pose_640_ti_lite_54p9_82p2.onnx --img-path "sample_ips.txt" --dst-path "sample_ops_onnxrt" ```...

f1ynng8

Is there Yolov5s (not Yolov5s6) mAP and GFLOPS benchmark? I would like to know the benchmark of Yolov5s to be. Could you provide the results of this?

joyyang1215

labels require 56 columns each

6

## ❔Question Hi! I try to train model for detecting keypoints for one class with 9 keypoints. I have an errors like: `train: WARNING: Ignoring corrupted image and/or label /content/drive/MyDrive/cv_tn/tn_keypoints_dataset/images/train/102_jpg.rf.0f0bf4b6ec94f8a7be6527458b7922f3.jpg:...

akatendra

Loss formula in paper "YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss"

3

Hello, I would like to ask about the keypoint loss issue in YOLOPose, which is crucial for me. From the source code, we can see that in the loss.py file,...

Charmnut1

The pt.link is vacant

2

In directory: edgeai-yolov5/pretrained_models/models/detection/coco/edgeai-yolov5 ## 🐛 Bug The link of pth file .e.g yolov5l6_640_ti_lite_47p1_65p6.pt.link is vacant while the .link for onnx and protext is valid.

hitmachineWu

I was wondering if you guys have plan to add yolov8 for detection?

ammar-deep

## ❔Question how could i get the prototxt file when export yolo-pose model? ## Additional context when i use export.py as below, `python models/export.py --weights runs/train/exp/weights/best.pt --img 640 --batch 1...

happyamyhope