video_features
video_features copied to clipboard
v-iashin
Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.
CLIP is an interesting model with features that have achieved excellent results in several downstream tasks. So I think adding this model will make this repo better. [paper](https://arxiv.org/abs/2103.00020), [code](https://github.com/openai/CLIP) In...
Would you consider adding the ability to extract video features using slowfast model
Hi , this is a greate work for my stduy ,But I had a problem running the demo. ``` (torch_zoo) czy@PT6630W:/data1/czy/affectivevideo/video_features$ /home/czy/anaconda3/envs/torch_zoo/bin/python3.8 main.py feature_type=r21d device_ids="[0]" video_paths="[./sample/v_ZNVhz7ctTq0.mp4, ./sample/v_GGSY1Qvo990.mp4]" Traceback (most recent...
I have installed your library and use `PWC` conda env, but it will throw `pytorch CUDNN_STATUS_MAPPING_ERROR` and `CUDA error: invalid texture reference` errors, I run this code on RTX 3090...
Hello, thank you for your work. I want try to use this code to extract the i3d feature and vggish feature in the BMT branch. But the environment is hard...
I found that the code will only processing one video on each GPU, and used about 2.5G memory, the memory usage is slow for GPUs which have lager memory. I...
Now the project inherits `GPL-3.0 License` from [PWC](https://v-iashin.github.io/video_features/models/pwc/) which prevents adaptation of the library for some use-cases. Probably will have to drop PWC support to make it `MIT` 😞
It is not ready to be merged for now. But I have finished a preliminary version that supports batch read, overlap and so on. The test code: ```python from utils.io...