Image scaling issues

1- Currently, I believe the images are not scaled to a [0-1] range when we run the tfrecords generation followed by model training. This is OK for efficientnet models, because [preprocessing is done by the model itself](https://keras.io/api/applications/efficientnet/#efficientnetb0-function). That said, other models, like [inception](https://keras.io/api/applications/inceptionv3/) expect a scaled input.

2- I might we wrong, but I believe the `scale` variable, used for data augmentation and created [here](https://github.com/Decathlon/decavision/blob/master/decavision/model_training/tfrecords_image_classifier.py#L110), should be the opposite. It should be `1` for models of the efficientnet family (because the model expect a tensor of [0-255] floats), while it should be 255 for the other models.