-
Notifications
You must be signed in to change notification settings - Fork 123
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
training error #43
Comments
@RaceSu I am having the same error. Did you find the solution? |
hello, I also meet this problem. In my case. I want to train pspnet50 on ADE datasets. But I only need 8 classes in ADE datasets. So I modify the datasets. I found some of the images size is a little different from the original size. So I resize these images by nearest. It work. |
Specificly. I use the python to modify the dataset. The round function is different from that in matlab. This is the problem source. |
#34 Please find the solution to the problem. |
I solved it, the image height and width you set in code is not same as the input image's height and width, and the image need to be cv2.imread in and cv2.imwrite out, it will work, I don't know why. |
I'm having the same error. I'm sure my image size is same. So I want to know what‘s your mean 'the image need to be cv2.imread in and cv2.imwrite out' Thanks. |
I met the error as follow when I train the model.
"OutOfRangeError (see above for traceback): FIFOQueue '_1_create_inputs/batch/fifo_queue' is closed and has insufficient elements (requested 1, current size 0)"
The text was updated successfully, but these errors were encountered: