def pre_init_with_sift(trainPhotoTourDataset):
patch_size = 65
ON_GPU = True
SIFT = SIFTNet(patch_size=patch_size, do_cuda=ON_GPU)
SIFT.eval()
if ON_GPU:
SIFT.cuda()
transformed = []
for img in trainPhotoTourDataset.data:
transformed.append(
np.expand_dims(cv2.resize(img.cpu().numpy(), (65, 65)), axis=0))
phototour_loader = data_utils.DataLoader(
PhototourTrainingData(transformed), batch_size=256, shuffle=False)
descriptors = []
pbar = tqdm(enumerate(phototour_loader))
for batch_idx, data_a in pbar:
if ON_GPU:
torch_patches = Variable(data_a.type(torch.FloatTensor).cuda(),
volatile=True)
else:
torch_patches = Variable(data_a.type(torch.FloatTensor),
volatile=True)
res = SIFT(torch_patches)
sift = np.round(512. * res.data.cpu().numpy()).astype(np.float32)
descriptors.extend(sift)
return np.array(descriptors)
patches = []
current_patch_idx = start_patch_idx
for y in range(0, height, patch_h):
patch_idxs.append([])
for x in range(0, width, patch_w):
patch = np.array(img.crop(
(x, y, x + patch_w, y + patch_h))).astype(np.uint8)
patches.append(patch)
patch_idxs[-1].append(current_patch_idx)
current_patch_idx += 1
return np2torch(np.array(patches)), patch_idxs, patch_idxs[-1][-1]
model = SIFTNet(patch_size=41)
model.cuda()
model.eval()
try:
input_img_fname = sys.argv[1]
output_fname = sys.argv[2]
except:
print "Wrong input format. Try ./rank_scale_patches.py imgs/ref.png out.txt"
sys.exit(1)
patches, idxs, max_idx = read_patch_file(input_img_fname,
patch_w=73,
patch_h=41)
bw_patches = patches.float().mean(dim=1, keepdim=True)
print bw_patches.shape
n_patches = bw_patches.size(0)