Eval_SCD输入问题

[Jackoldwolf]

Hello! 我在运行Eval_SCD.py时，使用second数据集，输入pred_SCD生成的Inference RGB image（im1_rgb），遇到错误
assert unique_set.issubset(set([0, 1, 2, 3, 4, 5, 6])), "unrecognized label number" AssertionError: unrecognized label number，
请问EVAL（）函数中INFER_DIR1和LABEL_DIR1的输入应该是什么？Thanks！

[DingLei14]

Hi,
try replacing the rgb predictions with index predictions.

[ZhangQuan-wq]

INFER_DIR1 = r'' # Inference path1
INFER_DIR2 = r'' # Inference path2
LABEL_DIR1 = r'' # GroundTruth path
LABEL_DIR2 = r'' # GroundTruth path ,excuse me, I really want to know what should be filled in these four places. And I try something like this:INFER_DIR1 = r'C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\SECOND\Test\im1' # Inference path1
INFER_DIR2 = r'C:\Users\dell\Desktop\Bi_SRNet_main\Bi_SRNet\SECOND\Test\im2' # 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, Is it wrong?and when i try this,the error is like this:ValueError: Harmonic mean only defined if all elements greater than or equal to zero.