Skip to content
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

In Eval_SCD.py #24

Closed
choidaedae opened this issue Jul 10, 2023 · 7 comments
Closed

In Eval_SCD.py #24

choidaedae opened this issue Jul 10, 2023 · 7 comments

Comments

@choidaedae
Copy link

Hello, I read this issue and I'm not going well with it, too:
#21

Can you explain in more detail what parts of the code I should change?

@DingLei14
Copy link
Owner

Hello, I read this issue and I'm not going well with it, too: #21

Can you explain in more detail what parts of the code I should change?

Replace the rgb_dir to index_dir in line 49, 50.

You are also welcome to check our latest work on SCD: link.

@choidaedae
Copy link
Author

Hello! Thank you for reply :)

I solved this problem myself two days ago, and I remember that maybe this solution didn't solve the problem. The dimensions of the image array didn't match, so I kept the rgb directory, while at the same time loading the 'Color2Index' function in RS_ST.py, I used it and solved the problem. Is it okay to pull request for that part?

@DingLei14
Copy link
Owner

The evaluation codes suppose that the input results are index predictions. There are options in 'pred_SCD.py' to control whether to output index predictions or RGB predictions.

@choidaedae
Copy link
Author

I understood, Thx :)

@wangqingl
Copy link

Hello! Thank you for reply :)

I solved this problem myself two days ago, and I remember that maybe this solution didn't solve the problem. The dimensions of the image array didn't match, so I kept the rgb directory, while at the same time loading the 'Color2Index' function in RS_ST.py, I used it and solved the problem. Is it okay to pull request for that part?

hello, how to deal with the question, could you give me some advice? thank you

@Perfuncotry
Copy link

index_dir
Hello, I have tried many times recently but still haven't been able to solve this problem. How should I modify the code? I hope to receive your advice. I would be extremely grateful!
assert unique_set.issubset(set([0, 1, 2, 3, 4, 5, 6])), "unrecognized label number"
AssertionError: unrecognized label number

@ZhangQuan-wq
Copy link

Hello,I have set the four files like this:INFER_DIR1 = r'C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\pred_dir\im1_rgb' # Inference path1
INFER_DIR2 = r'C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\pred_dir\im2_rgb' # Inference path2
LABEL_DIR1 = r'C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\SECOND\Test\label1' # GroundTruth path
LABEL_DIR2 = r'C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\SECOND\Test\label2' # GroundTruth path
the files can be found, but the Lists are empty,why?Glob pattern for INFER_DIR1: C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\pred_dir\im1_rgb*.png
Glob pattern for INFER_DIR2: C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\pred_dir\im2_rgb*.png
Glob pattern for LABEL_DIR1: C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\SECOND\Test\label1*.png
Glob pattern for LABEL_DIR2: C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\SECOND\Test\label2*.png
Infer list1: []
Infer list2: []
Label list1: []
Label list2: []
No accuracy data available.
bn_hist: TP 0, FN 0, FP 0, TN 0
Accuracy = 0.000%
Mean IoU = 0.000
Sek = 0.000
Score = 0.000
0
change_ratio = 0.0000, SC_Precision = 0.0000, SC_Recall = 0.0000, F_scd = 0.0000

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants