Torment123
Torment123
Hi, I'm studying your paper and trying to run the realness DCGAN on CIFAR10 dataset, the parameter setting for CIFAR10 I used is based on run_CelebA.sh, the only changes I...
Hi, I'm very interested in your work. And thanks for the detailed document. Currently I'm trying to train STTR from scratch on the sceneflow dataset. As mentioned in the document,...
Hi, I found that in the training all the batchnorm2d layer are frozen from the very beginning, indicating that these set of parameters are randomly initialized without any learning, I'm...
Hi, thank you for this very interesting work! I'm currently trying to train the vq-gan part on my few-shot dataset (e.g. ~300 dog or cat images) with resolution 256x256. However...
Hi, I've been trying to run the draggan app on a conda environment of a remote server; after setting up the environment as described in the repo, I executed sh...
Hi, I see that the benefits of PTI in principle doesn't depend on the specific architecture of styleGAN generator, is there any observation of whether the same improvement can be...
Hi, I'm studying the code of your pytorch implementation of COCO GAN, and have a small problem which I hope you can help me with: in the appendix of the...
Hi, I'm applying the KITTI pretrained FastACV on a new dataset (KITTI360), and trying to convert the predicted disparity of stereo pair to depth value, and the process I do...
Hi, in the pretrained checkpoint link I saw generalization.ckpt, I wonder what's the different between it and other pretrained model on sceneflow and KITTI? thanks
Hi, I found that in the default test split of shapenet car dataset, there is a sample 876d92ce6a0e4bf399588eee976baae that only contains white backgrounds, I wonder whether in your evaluation code...