Xavier Soria Poma
Xavier Soria Poma
> Running final test on the rewrite now. > > Will you be able to train the new model on the Titan X? > > If not, I'll look at...
> Will do. Thanks! > > (Finishing up the Keras version now.) Really? finishing the Keras version, wow if you don't mind, I would like to see the script I...
> Running final test on the rewrite now. > > Will you be able to train the new model on the Titan X? > > If not, I'll look at...
> I took a week away from this to let me return with a fresh perspective. > > Does the paper mention why `DexiNed` includes `img = img.transpose((2,0,1))` in `testDataset.transform`...
> Got it. `img.transpose((2,0,1))` just puts the channels first, as required by PyTorch. sorry I did not see this :)
> > Hi good to have you back :) the paper is based on the DexiNed TensorFlow version. By the way, this is not a big deal you know TF...
Hi, sorry for my late response, how you already solved your problem. But at this point I cannot see any possible solution. By the way, I made a video showing...
> Basic Idea: Exposing DexiNed as an API service. Users should be able to make API calls with relevant arguments to mimic CLI operations. > > I am willing to...
Hi @HKLFJS, I am afraid I cannot give you a consistent answer because, I saw that difference more than a year ago but I cannot find an answer. However, In...
Sorry, I did not give you the requirement in the right time