The shape of tensor obtained by nvidia.dali reads the image is rotated

The shape of tensor obtained by nvidia.dali reads the image is rotated, because the rotated jpeg file has orientation info, dali considers the rotation head information of the jpeg file, but opencv does not consider it。
code:
dali：

class ImageDecoderPipeline(Pipeline):
    def __init__(self, image_dir, batch_size, num_threads, device_id):
        super(ImageDecoderPipeline, self).__init__(batch_size, num_threads, device_id, seed = seed)
        self.input = ops.FileReader(file_root = image_dir)
        if torch.cuda.is_available():
            self.decode = ops.ImageDecoder(device = 'mixed', output_type = types.RGB)  #mixed
            # self.rotate = ops.Rotate(device="gpu", angle = 0.0)
        else:
            self.decode = ops.ImageDecoder(device='cpu', output_type=types.RGB)  # mixed

    def define_graph(self):
        jpegs, labels = self.input()
        images = self.decode(jpegs)
        return (images, labels)

opencv：
input = cv2.imread(file_path)

the jpeg file:

the head info:
{"size":2534018,"format":"jpeg","width":3000,"height":4000,"colorModel":"ycbcr","orientation":"Right-top"}

obtain by dali and opencv：
dali:
opencv:

Start with the provided ImageDecoderPipeline and ops.ImageDecoder example, then reproduce the report with the linked JPEG and compare its tensor shape with cv2.imread. Trace how JPEG orientation metadata is handled and verify the resulting behavior against the reported DALI and OpenCV outputs; done means the discrepancy is resolved or covered by a regression test.