RAFT
Pointnet_Pointnet2_pytorch
Our great sponsors
RAFT | Pointnet_Pointnet2_pytorch | |
---|---|---|
3 | 3 | |
2,985 | 3,187 | |
3.4% | - | |
3.2 | 0.0 | |
5 months ago | 4 days ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
RAFT
-
SD-CN-Animation updated to v0.9. Many of the major issues were fixed, better vid2vid quality, ControlNet in txt2vid mode and more! Here is an example of how txt2vid with CN looks like.
Learning something new. Recently learned to use temporal kit, i.e. merge multiple frames into the same image to achieve consistency. You are using " 'RAFT' optical flow estimation algorithm to create an occlusion mask that is used to generate the next frame". Curious, how is it used?
-
Optical flow installation for a Stable Diffusion extension
The command "conda install pytorch=1.6.0 torchvision=0.7.0 cudatoolkit=10.1 matplotlib tensorboard scipy opencv -c pytorch" is asking to install Google Authenticator in an environment, as part of a package install. Trying to install this https://github.com/princeton-vl/RAFT to run this https://github.com/volotat/SD-CN-Animation
-
Are the New M1 Macbooks Any Good for Deep Learning? Let’s Find Out
https://github.com/princeton-vl/RAFT#optional-efficent-imple...
It's "optional" in the sense that things still calculate correctly on CPU without it, but at a 1000x performance penalty. Or you could skip it if you had 64GB of GPU RAM, which you cannot buy (yet).
So if you actually want to work with this on GPUs that are commercially available, you need it.
Pointnet_Pointnet2_pytorch
-
Help me understand how to use this PointNet implementation (pytorch, point cloud classification)
here is a sample from one of these log files
I am trying to use this implementation of PointNet (GitHub repo)
-
Are the New M1 Macbooks Any Good for Deep Learning? Let’s Find Out
Here you go: https://github.com/yanx27/Pointnet_Pointnet2_pytorch - no need for any custom cuda code.
Note the cuda kernels in the original repo were added in August 2017. It might have been the case at the time they needed them, but again, if you need to do something like that today, you're probably an outlier. Modern DL library have a pretty vast assortment of ops. There have been a few cases in the last couple of years when I thought I'd need write a custom op in cuda (e.g. np.unpackbits) but every time I found a way to implement it with native Pytorch ops.
If you're doing DL/CV research, can you give an example from your own work where you really need to run custom cuda code today?
What are some alternatives?
SD-CN-Animation - This script allows to automate video stylization task using StableDiffusion and ControlNet.
tensorflow_macos - TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.
pointnet2 - PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
ROCm - AMD ROCm™ Software - GitHub Home [Moved to: https://github.com/ROCm/ROCm]
segmentation_models.pytorch - Segmentation models with pretrained backbones. PyTorch.
Pix2Vox - The official implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images". (Xie et al., ICCV 2019)
SimpleView - Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"
mmrazor - OpenMMLab Model Compression Toolbox and Benchmark.
DeepViewAgg - [CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in "Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation"