-
您好，想请教一下测试集是怎么设置的呀
-
It's not a problem with R/D ratio, but simply proportion of file size to the quality setting compared to other tables.
``` sh
cjpeg -quant-table 4
```
typically creates files about 20% larger than o…
-
--tune psychovisual is implemented but we need to look at the resulting video and make sure it actually looks better in all cases.
-
Hello, may I ask if I can run the model by adjusting H and W with only V100 32GB, especially when using multiple GPUs?
-
Dear authors,
It is a great efficient network of deep video compression. It seems that there is no motion compensation network and it only uses warping to compensate motion. Will this lead to a dr…
-
Include more Metric Distance algorithms:
- Color cost functions: Jjnd, Jil and Jhl
- DEitp
- CIE Delta-E 2016 (simply an Euclidean of CAM16-UCS)
- PSNR-HSV (in VMAF plugin)
- PSNR-HMA
- IW-PSNR…
-
I'm using the EntropyBottleneck module in a factorized prior network. While training, the aux_loss and bpp_loss are decreasing but when I use the trained network to compress and save the compressed im…
-
Hi,
Thank you for sharing your work and the interesting model you've developed.
I hope that your model becomes the new standard for Dynamic NeRF models.
I trained the K-planes hybrid version u…
-
I load the model "ZoeD_M12_N.pt", and run the general following code with little modification
, to save metrics depth map first.
```
import torch
import os
import datetime
import numpy as np…
suzdl updated
8 months ago
-
Dear Author,I have used the pretrained weights file 'brats_unet_128_1200k.pt' to infer 156 images, and th…