Lemon64 runs on passion — not intrusive ads or paywalls. But keeping the site alive comes with real costs: servers, software, hardware, and ongoing maintenance. Most visitors never donate, but if just a few do today, we can keep everything running smoothly. If Lemon64 has brought you joy, nostalgia, or simply been helpful, please consider a small gift. Your support helps ensure the site stays online for years to come. Thank you.
device = "cuda" if torch.cuda.is_available() else "cpu" model = resnet50(pretrained=True).eval().to(device) preprocess = T.Compose([T.Resize(256), T.CenterCrop(224), T.ToTensor(), T.Normalize(mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225])])
results=[] for path, x in images: x = x.to(device) # get label logits = model((x - torch.tensor([0.485,0.456,0.406],device=device).view(1,3,1,1)) / torch.tensor([0.229,0.224,0.225],device=device).view(1,3,1,1)) orig_label = logits.argmax(dim=1).cpu().item()
# Define atk_hairy_hairy: as PGD but adding a high-frequency "hair" mask def generate_hair_mask(shape, density=0.02): # shape: (1,3,H,W) in [0,1] tensor _,_,H,W = shape mask = torch.zeros(1,1,H,W) rng = torch.Generator().manual_seed(0) num_strands = max(1,int(H*W*density/50)) for _ in range(num_strands): x = torch.randint(0,W,(1,), generator=rng).item() y = torch.randint(0,H,(1,), generator=rng).item() length = torch.randint(int(H*0.05), int(H*0.3),(1,), generator=rng).item() thickness = torch.randint(1,4,(1,), generator=rng).item() for t in range(length): xx = min(W-1, max(0, x + int((t/length-0.5)*10))) yy = min(H-1, max(0, y + t)) mask[0,0,yy:yy+thickness, xx:xx+thickness] = 1.0 return mask.to(device)
