-
Notifications
You must be signed in to change notification settings - Fork 9.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Question about pad_shape #482
Comments
This maybe a problem about |
It still doesn't work, I think the problem is attributed to padding the masks which makes the size mismatch with img |
you are right, it is the problem of shape mismatch between orign-image and mask-image which is generated from the annotation Do you use |
@jichilen I use |
Now the error shows me the above information. |
Do you know why the mmdet need to pad the img size to multiple of 32? |
Maybe you have an image with the shape(A,B,3), but in your annotation it has the shape of (B,A,3) |
If your data is in the form of coco_type, you may print the |
this is because the backbone may downsample the features to the size of [N,C,1/32H,1/32w] by |
@jichilen OK, I see it. On the other hand, I try it and visualize them with error, but it seems to normal. For the same annotation, detectron and maskrcnn benchmark can accept it without any problems. |
@jichilen Could you use QQ or WeChat ? Could I add you to learn from you about this mmdet in detail? |
Here is an example in my dataset
in |
Thank you for your patient reply. I have found the problem, after checking the shape between origin images and train_images. I will close the issue! |
@qq237942920 Hi, could you provide the way you solved this problem? I am having the same error. |
I just check the annotations and images correspondence. |
@qq237942920 ,How to make comments and images correspond? |
I just compare the images['img_shape'] in my annotations with the real images shape. Furthermore, maybe you should find out which images cause the problem in mmdet and then you can check it according the 'file_name' |
I use coco2014 datasets with instances_minival2014.json but I got the same error.
|
This is most probable that the image shape in annotations is not the same as the actual shape of the loaded image. Some images may be taken by mobile devices and have different orientation. You may have a check. |
tks. it just change the datasets like:
to following:
any advice?pls. |
I think you can try with coco2017 which I'm using. If you use the official dataset ,the annotations they open should right for the dataset. And you can try this format as follow:
|
Nihao! Can you please tell me how did you compate img_shape with real image shape? I am not able to correctly tell which image it failing on. Can you please tell me the exact debugging method you tried please? |
Maybe you can set batch size to 1, comment the code of the whole network(only the image processing |
I make a custom datasets and put it into train ,but I got error as following:
Actually, I put my dataset into detectron or maskbenchmark and it works well, but it doesn't work here. I think it's the problem in mask_pad
The text was updated successfully, but these errors were encountered: