AssertionError: Results do not correspond to current coco set about yolov6 HOT 6 CLOSED

i also met issues when training:

i can't understand the reason,why its a invalid directory path?

from yolov6.

The first problem might be due to the annotation's cache file. You can delete previously generated cache files and regenerate them when using a new training set. We will also optimize this part of the settings as soon as possible, and it is expected to be completed next week. At that time, you can check whether the problem still exists.
The second question suggests that you try using absolute paths in coco.yaml to see if the same problem still exists.
Thank you for your attention

from yolov6.

i also met issues when training:

i can't understand the reason,why its a invalid directory path?

I think you can try to modify the root : from "../coco/images/train2017" to "./coco/images/train2017"

from yolov6.

I also met this issues.
This file".\runs\train\exp\predictions.json" may have problem, such as "image_id": 1333", my dataset don't have an image named 1333. How to solve it?

from yolov6.

I use the following code for training python tools/train.py --batch 4 --conf configs/yolov6s.py --data ./data/coco.yaml --device 0 --workers 0 But this mistake happened during the val AssertionError: Results do not correspond to current coco set

I am having the same issue at the moment.I have deleted the generated annotations folder and .train.json and tried again but I got the same error.Also after deleting the annotations folder and json files, even though all the paths are correct, at first I receive invalid directory path issue, then I run the command again without changing anything it trains for one epoch and I get the same 'Results do not correspond to current coco set' error. It feels like a weird loop I cant debug.Thank you for your help.

from yolov6.

#76

from yolov6.