Changelog for the video-sampler
.
- added GPUVideoSampler
- added
use-gpu-decoder
option to thevideo-sampler
command which allows to use a GPU decoder. - major code refactoring
- added support for streaming and RTSP
- tests added
- added
start-time
andend-time
options to thevideo-sampler
command which allows to specify the start and end time of the video segment to be processed. - fixed optional imports
- minimal docker builds added
- added multiprocessing over multiple videos in the folder
- new cli command & support reading from
.yaml
config files
- added summary creation from sampled frames
- keyword yt-dlp extraction
- added yt-dlp integration
- extra yt-dlp options are supported
- added blur gating
- adding CLIP-based gating for sampling
- added docker build image
- fixed some bugs in requirements and setup scripts
- adding gif creation from sampled frames
- added a notebook in
notebooks
to show the distribution shift of the sampled frames - added some basic tests (really basic)
- added a short explanation and usage of guided sampling in README.md.
- added grid hash sampling
- fixed a major bug in the hashing buffer
- added entropy and gzip methods for the sliding top-k buffer
- improved build process