Laurent Chauvin

Hello, In v2, before the input of the coarse generator, you concatenate 3 images on the depth channel: `x = tf.concat([x, ones_x, ones_x*mask], axis=3)` but in gen_conv() you only split...

Hello, Why did you remove the patch-based computation of l1_loss in v2 ? Thank you.

Based on your work, I found this nice implementation of DeepFill v2 for PyTorch, I thought it might be useful to others: https://github.com/nipponjo/deepfillv2-pytorch

I tried to download a video that I paid for, but it only downloads the trailer of the video. I pasted the cookie, but nothing.

Hello, I trained the model and images generated looked nice, but during inference, it's pretty bad. I even try to infer using training data (just to test), and even then,...

Modify number and upgrades of estus

1

It would be nice to be able to add or remove some flask of Crimson Tears, and change their upgrades. Maybe same with the shadow blessings, although it's probably a...

Cannot run voxelmorph with synthmorph model

3

Hello, I'm trying to run synthmorph, but I'm having this issue: ``` python ./scripts/tf/register.py --moved tmp.nii --moving /scratch/02/lchauvin/datasets/SynthMorph/img1_half_fov.nii --fixed /scratch/02/lchauvin/datasets/SynthMorph/img2_half_fov.nii --model models/synthmorph.deform.3.h5 2024-09-20 19:09:45.209404: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN...