392781 / faceoff Goto Github PK

Rewrite the current api as it stands.

Your codes are full of bugs. Could you please fix them? I don't think your examples can run successfully.

Create a new function in adversarial_face_recognition.py for dataloading. Could potentially done inside the Attack class or as a standalone function.

I have noticed in the generation of the mask, the values used are in the range of (-1,1) seen both in:

adversarial_face_recognition.py ln 187:
self.mask_list[i].data.clamp_(-1, 1)

and alogorithm.py ln 74:
delta.data.clamp_(-1, 1)

I believe the range is to be in (0,1) as when imagize(adver.detach().cpu()) is called the values are normalised to fit in to the range (0,255). Howveer, when we try to read this image back into resnet by calling tensorize() the valuse (0,255) is fitted into the range of (0,1) instead of (-1,1). The resultant tensor is significantly different from the apply(input_tensor, delta) tensor. To prevent the data lost, the mask should be generated in the range of (0,1) instead.

Title

Hi
How can I replace main face with adversarial face in the main whole picture?

I mean the I just want to change face -> into adversarial face in the main big image

Create a notebook with clean usage of library outlined.

Doesn't reuse code currently and does a lot of costly calculations multiple times.

Epoch 28:
Loss = -0.5512599
Dist. to Image = 0.9096553
Dist. to Target = 0.3583954
Face detection = True
Epoch 29:
Loss = -0.5638140
Dist. to Image = 0.9396414
Dist. to Target = 0.3758273
Face detection = True
Epoch 30:
Loss = -0.5764654
Dist. to Image = 0.9016970
Dist. to Target = 0.3252316
Face detection = True

I feel like the end result is blending the perturbation on the original face image instead of masking it directly. And I found that as the epoch increases, the perturbations appear more and more sparse.