Canelo_
Canelo_
If you just need the result of anomaly detection but not localizaition, the ground truth is not required, you can just prepare some black image as the fake ground truth...
you just need to change the "export_mode" in config.yaml about fastflow model.
And I also want to know how to improve the inference speed.
Hi, I had the same bug with you when I wanted to get the predicted image. but I think the code should be: `if predictions.pred_label == "Normal": pred_image = add_normal_label(predictions.image,...
碰到了同样的问题，请问您解决了吗？而且作者已经删除了他们的cfp权重文件，我不知道该如何复现结果
Do you address the problem? I also meet this question.
请问你解决这个问题了吗？我在使用单卡训练和测试Real-iadD时也碰到了相同的问题