Andrés Romero
Andrés Romero
Is there any update for the pretrained models (edges and yosemite)?
Ok. I just did it and it works quite good for Yosemite and edges to shoes|handbags, but it literally outputs nothing from handbags|shoes to edges in most cases, look an...
Thank you for your reply. Ok. It works with MNIST+LeNet in TF. Nevertheless, Training the model for MNIST+GAN, I get this error: ```bash I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcublas.so...
Hello, when you run on python, it should have the form: `main.py --args`, but on ipython: `main.py -- --args`. As my interpreter was ipython (I did this a while ago)...
Hello, it seems a problem with your memory system. I used Ubuntu 16 as well. Were you able to solve it?
Mmhh, it is hard to say because it is been a while, but my best guess would be 8.0. However, it does not seem to be the case of a...
It is weird, as long as you have the models loaded in the GPU, you should not have such CPU RAM consumption. I ran these experiments in a server with...
Hello, I am sorry for the late reply. Exactly, you are right, either the first frame or the last frame can be ignored, or in order to not to lose...
@homerjed did you continue in this direction? 3D-DWT would indeed be very useful.
Hello, I have encountered a similar problem. When using it for 128x128 it works well, but when the lr input is 32x32 or so, the output is quite blurry. Here...