-
Notifications
You must be signed in to change notification settings - Fork 167
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
The visualization of the segmentation results. #47
Comments
@chenyzh28 you can use the cityscapes colormap, this code uses a different color map. see get_palette() |
Refer to here |
hi,i have a question about why your results are just 76.42%,you have 4 GPU,but your results are not the same as paper 79 or 78.x |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I trained the model with 4 GPUs (GTX 2080) with batchsize 4, and the PSPNet achieves the mIOU of 76.42%. But I found the visualization results are not correct. Here is an example.
.
But the ground-truth label is like:
So how can i modify the program to make it right?
The text was updated successfully, but these errors were encountered: