Different pre-processing pipelines for different models?

I noticed that there are different image pre-processing pipelines for different models.

For [Inception-BN](https://github.com/dmlc/mxnet-model-gallery/blob/master/imagenet-1k-inception-bn.md), the images should be normalized with the `mean_224.nd`:

```
mean_img = mx.nd.load("Inception/mean_224.nd")["mean_img"]
normed_img = sample - mean_img.asnumpy()
```

For [Inception-V3](https://github.com/dmlc/mxnet-model-gallery/blob/master/imagenet-1k-inception-v3.md), the images should be:

```
normed_img = sample - 128.
normed_img /= 128.
```

For [Inception-BN-21k](https://github.com/dmlc/mxnet-model-gallery/blob/master/imagenet-21k-inception.md), the images should be:

```
normed_img = sample - 117.
```

Am I correct with the above settings?