remmarp / padim-tf Goto Github PK

Hello, I would like to ask a question. Now I have found that the Gaussian distribution at certain points exhibits a double Gaussian distribution, and there may be deviations when calculating the mean and covariance. I would like to distinguish the channels that conform to the double Gaussian distribution, and then calculate the minimum Mahalanobis distance separately from the two distributions. Do you have any ideas about this?

I'm going to apply an augmentation to my dataset, not Mvtec, to spin several epochs. Since there are many batches, the out of memory phenomenon occurred when out went up to RAM. How can I get a mean, variation?

out = []
    for x, _, _ in train_set:
        l1, l2, l3 = net(x)
        _out = tf.reshape(embedding_concat(embedding_concat(l1, l2), l3), (batch_size, h * w, c))  # (b, h x w, c)
        out.append(_out.numpy())

I'm trying to reproduce this implementation. Although the image level detection works well, I get weird results for the pixel-level localization/mask. Seems like I get a lot of False Positives.
Please see attached photos.
I do not change any code nor requirements. So everything is as recommended in this repo.
Could you please comment if I'm missing anything.

Thanks.