def load_images()

in threestudio/data/image.py [0:0]
57 lines of code
3 McCabe index (conditional complexity)

    def load_images(self):
        # load image
        assert os.path.exists(
            self.cfg.image_path
        ), f"Could not find image {self.cfg.image_path}!"
        rgba = cv2.cvtColor(
            cv2.imread(self.cfg.image_path, cv2.IMREAD_UNCHANGED), cv2.COLOR_BGRA2RGBA
        )
        rgba = (
            cv2.resize(
                rgba, (self.width, self.height), interpolation=cv2.INTER_AREA
            ).astype(np.float32)
            / 255.0
        )
        rgb = rgba[..., :3]
        self.rgb: Float[Tensor, "1 H W 3"] = (
            torch.from_numpy(rgb).unsqueeze(0).contiguous().to(self.rank)
        )
        self.mask: Float[Tensor, "1 H W 1"] = (
            torch.from_numpy(rgba[..., 3:] > 0.5).unsqueeze(0).to(self.rank)
        )
        print(
            f"[INFO] single image dataset: load image {self.cfg.image_path} {self.rgb.shape}"
        )

        # load depth
        if self.cfg.requires_depth:
            depth_path = self.cfg.image_path.replace("_rgba.png", "_depth.png")
            assert os.path.exists(depth_path)
            depth = cv2.imread(depth_path, cv2.IMREAD_UNCHANGED)
            depth = cv2.resize(
                depth, (self.width, self.height), interpolation=cv2.INTER_AREA
            )
            self.depth: Float[Tensor, "1 H W 1"] = (
                torch.from_numpy(depth.astype(np.float32) / 255.0)
                .unsqueeze(0)
                .to(self.rank)
            )
            print(
                f"[INFO] single image dataset: load depth {depth_path} {self.depth.shape}"
            )
        else:
            self.depth = None

        # load normal
        if self.cfg.requires_normal:
            normal_path = self.cfg.image_path.replace("_rgba.png", "_normal.png")
            assert os.path.exists(normal_path)
            normal = cv2.imread(normal_path, cv2.IMREAD_UNCHANGED)
            normal = cv2.resize(
                normal, (self.width, self.height), interpolation=cv2.INTER_AREA
            )
            self.normal: Float[Tensor, "1 H W 3"] = (
                torch.from_numpy(normal.astype(np.float32) / 255.0)
                .unsqueeze(0)
                .to(self.rank)
            )
            print(
                f"[INFO] single image dataset: load normal {normal_path} {self.normal.shape}"
            )
        else:
            self.normal = None