Ask questionsSupport image transformations
Training DNNs uses random resize, crop, rotation, etc. for data augmentation. How do you do this with jpeg2dct?
Answer questions saitarslanboun
Speeding up training is relevant, and that's what I personally care about.
Dear @dreamflasher, encoding/decoding is not the part of the process speeding up the inference. DCT is already a compressed form. In order to compress the given image to an equivalent size that DCT has, you have to use a reasonable amount of convolutional layers which require heavy computational need. The main idea of this work is using already compressed image form to avoid 1st and 2nd blocks in ResNet which involves lots of Convolutional layers.
Related questionsNo questions were found.