Skip to main content

Accelerated deep learning.

Project description

Gradient Mechanics

Benchmarks

HuggingFace Image Dataset

uv run python src/tests/benchmark_huggingface_images.py

Video Dataset

uv run python src/tests/benchmark_video_dataset.py data/humming_bird_1s.mp4

Transcoding

Keyframes Only

ffmpeg -i data/humming_bird_1s.mp4 -c:v libx264 -x264-params keyint=1:scenecut=0 -crf 18 data/humming_bird_1s_keyframes_only.mp4

Inspect Encoding

ffprobe -loglevel error -select_streams v:0 -show_entries frame=pict_type -of default=noprint_wrappers=1 data/humming_bird_1s_keyframes_only.mp4

Terminology:

  • I-frame is a key frame. Decoding a keyframe is not dependent on other frames.
  • P-frame is a predicted frame. It is dependent on an preceding frame.
  • B-frame is a bi-directional predicted frame. It depends on a preceding and a succeeding frame.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gradient_mechanics-0.0.2-py3-none-any.whl (19.1 kB view details)

Uploaded Python 3

File details

Details for the file gradient_mechanics-0.0.2-py3-none-any.whl.

File metadata

File hashes

Hashes for gradient_mechanics-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 c3d19ae3cbd5f4d56c15a301717e481edc4ae5f516a342631a66318abb2fda7b
MD5 6bc4032691ccbbd2ea206974c8e72705
BLAKE2b-256 a52d3dd46fd3505281959555e4bae53ff595f5f2954801552e816bc0e1c004cb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page