训练过程中，为什么要同时加载所有的图片进入内存？？？

[xing-xing448]

    for idx, frame in tqdm(enumerate(frames)):
        cam_name = os.path.join(path, 'gt_imgs', str(frame["img_id"]) + extension)

        # NeRF 'transform_matrix' is a camera-to-world transform
        c2w = np.array(frame["transform_matrix"])
        # change from OpenGL/Blender camera axes (Y up, Z back) to COLMAP (Y down, Z forward)
        c2w[:3, 1:3] *= -1

        # get the world-to-camera transform and set R, T
        w2c = np.linalg.inv(c2w)
        R = np.transpose(w2c[:3,:3])  # R is stored transposed due to 'glm' in CUDA code
        T = w2c[:3, 3]

        image_path = os.path.join(path, cam_name)
        image_name = Path(cam_name).stem
        image = Image.open(image_path)
        w, h = image.size[0], image.size[1]
        image = np.array(image.convert("RGB"))

        torso_img_path = os.path.join(path, 'torso_imgs', str(frame['img_id']) + '.png')
        torso_img = np.array(Image.open(torso_img_path).convert("RGBA")) * 1.0
        bg = torso_img[..., :3] * torso_img[..., 3:] / 255.0 + bg_img * (1 - torso_img[..., 3:] / 255.0)
        bg = bg.astype(np.uint8)

不能使用的时候在加载吗？？？内存放不下，直接卡死了