search

ToshiHayashi / OCITN

One-class classification approach using error of image transformation into one image
3 stars 0 forks source link

Question about a specific part of the code #3

Closed raulsenaferreira closed 2 years ago

raulsenaferreira commented 2 years ago

Hello, I'm reorganizing the code to better understand the method. However, there is a line of the code that I did not understand:

for n in range(len(x_train)): y_train[n]=y2.rotate(rot)

It seems to me that you are putting the rotated image of Leena.png, n times (which n is the number of images in x_train) inside of a vector that should represent the labels of the training data. In your code the y_train is also a matrix because you do hotencoder, ok, However... If it is the case, it seems wrong because it is just adding n times the image of leena.png inside of the train labels, putting RGB values instead of labels.

Maybe you wanted to put this image inside of an X to posteriorly feed the autoencoder, isn't it? and after it, correctly calculate the construction error regarding this image.

Thanks for sharing the code

raulsenaferreira commented 2 years ago

I saw now that you updated a code more accurate, so I will close this issue. Thanks

ToshiHayashi commented 2 years ago

Hello. Thank you for the issue.

Yes, these codes are more accurate. I will remove the old codes to avoid confusion.

If you have other questions, please feel free to let me know. Thank you very much!