将yolox利用onnxruntime推理时模型输出后结果需要利用下面代码映射到原图上，但是直接利用pth进行推理时，没有看到这一步，这个是为什么？

将yolox利用onnxruntime推理时模型输出后结果需要利用下面代码映射到原图上，但是直接利用pth进行推理时，没有看到这一步，这个是为什么？
def demo_postprocess(outputs, img_size, p6=False):
grids = []
expanded_strides = []
if not p6:
strides = [8, 16, 32]
else:
strides = [8, 16, 32, 64]
hsizes = [img_size[0] // stride for stride in strides]
wsizes = [img_size[1] // stride for stride in strides]
for hsize, wsize, stride in zip(hsizes, wsizes, strides):
xv, yv = np.meshgrid(np.arange(wsize), np.arange(hsize))
grid = np.stack((xv, yv), 2).reshape(1, -1, 2)
grids.append(grid)
shape = grid.shape[:2]
expanded_strides.append(np.full((*shape, 1), stride))
grids = np.concatenate(grids, 1)
expanded_strides = np.concatenate(expanded_strides, 1)
outputs[..., :2] = (outputs[..., :2] + grids) * expanded_strides
outputs[..., 2:4] = np.exp(outputs[..., 2:4]) * expanded_strides
return outputs

Start by comparing the ONNXRuntime inference entry point with the .pth inference path, then inspect the supplied demo_postprocess function and how each path decodes model outputs. Determine whether grid and stride decoding is already performed in one path, and document the output format and preprocessing assumptions needed for equivalent results.