2025-01-11 22:46:13 +08:00
2024-12-31 17:40:42 +08:00
2025-01-03 16:25:42 +08:00
2025-01-04 16:16:26 +08:00
2025-01-11 21:53:59 +08:00
2025-01-03 16:25:42 +08:00
2025-01-07 12:02:08 +08:00
2025-01-11 21:53:59 +08:00
2025-01-11 21:53:59 +08:00
2025-01-07 12:02:08 +08:00
2025-01-11 21:53:59 +08:00
2025-01-11 22:46:13 +08:00
2025-01-11 21:59:57 +08:00
2025-01-11 21:53:59 +08:00
2025-01-04 16:16:26 +08:00
2025-01-04 16:16:26 +08:00

Installation

Set Up Environment

Clone the repository.

git clone https://github.com/IDGallagher/MotionVideoSearch
cd MotionVideoSearch

Install dependencies

[Optional] Create a conda environment.

conda create -n mvs python=3.9
conda activate mvs

Install the PyTorch and TorchVision versions that are compatible with your CUDA configuration.

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

Install ffmpeg 6.x

conda install -c conda-forge ffmpeg=6.*

Install other dependencies.

pip install tqdm matplotlib einops einshape scipy timm lmdb av mediapy typer imageio imageio-ffmpeg requests opencv-python

Install faiss https://github.com/facebookresearch/faiss

conda install -c pytorch faiss-cpu=1.9.0

[Optional] Download watermark removal repo

git clone https://github.com/l-comm/WatermarkRemoval.git
S
Description
No description provided
Readme
4.7 MiB
Languages
Python 75.1%
Cuda 15.9%
C++ 8.2%
C 0.8%