INNER CODE UNIT · Python
__init__
wenhaochai/StableVideo · annotator/midas/__init__.py:10
def __init__(self):
self.model = MiDaSInference(model_type="dpt_hybrid").cuda()
def __call__(self, input_image, a=np.pi * 2.0, bg_th=0.1):
assert input_image.ndim == 3
image_depth = input_image
with torch.no_grad():
image_depth = torch.from_numpy(image_depth).float().cuda()
image_depth = image_depth / 127.5 - 1.0
image_depth = rearrange(image_depth, 'h w c -> 1 c h w')
depth = self.model(image_depth)[0]
depth_pt = depth.clone()
depth_pt -= torch.min(depth_pt)
depth_pt /= torch.max(depth_pt)
depth_pt = depth_pt.cpu().numpy()
depth_image = (depth_pt * 255.0).clip(0, 255).astype(np.uint8)