Can you please the model structure for yolov6? like I want to know the key difference between yolov5 and yolov6

meituan / YOLOv6

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

GNU General Public License v3.0

5.72k stars 1.04k forks source link

Can you please the model structure for yolov6? like I want to know the key difference between yolov5 and yolov6 #145

Closed noreenanwar closed 2 years ago

meituan-gengyifei commented 2 years ago

Thanks for your suggestion! We will add structure comparison diagrams as soon as possible to help better understand yolov6.

mtjhl commented 2 years ago

Currently, you can use Netron to visualize the onnx model and find the difference.

noreenanwar commented 2 years ago

ok but I am facing issues while training it on my customize dataset(cityscape)I already train it in yolov5 now I am trying with v6

noreenanwar commented 2 years ago

YOLOv6/yolov6/data/datasets.py", line 336, in get_imgs_labels for img_path, info in img_info.items() ValueError: not enough values to unpack (expected 2, got 0)

This is the error.IDK what is the matter as I followed every instruction mentioned.

d5423197 commented 2 years ago

This error means your img_info is empty. You can just debug this. It is easy to fix.