holocron
PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief, PolyLoss, MobileOne). Other additions: AdEMAMix
File Explorer
Download Latest Version (.zip)- bug_report.yml
- config.yml
- feature_request.yml
- backend.yml
- demo.yml
- docs.yml
- package.yml
- page-build.yml
- pr-edited.yml
- pr-merged.yml
- quality.yml
- scripts.yml
- triage.yml
- CODEOWNERS
- collect_env.py
- dependabot.yml
- FUNDING.yml
- labeler.yml
- pull-labels.yml
- PULL_REQUEST_TEMPLATE.md
- release.yml
- SECURITY.md
- verify_deps_sync.py
- verify_labels.py
- extensions.json
- settings.json
- config.py
- main.py
- vision.py
- test_classification.py
- conftest.py
- Dockerfile
- pyproject.toml
- README.md
- uv.lock
- app.py
- requirements.txt
- classification.md
- installation.md
- notebooks.md
- box-iou-family.svg
- checkpoint-accuracy-vs-parameters.svg
- classification-transfer.svg
- favicon.svg
- logo.svg
- logo_text.svg
- katex.js
- changelog.md
- convnext.md
- darknet.md
- darknetv2.md
- darknetv3.md
- darknetv4.md
- mobileone.md
- pyconv_resnet.md
- repvgg.md
- repvit.md
- res2net.md
- resnet.md
- resnext.md
- rexnet.md
- sknet.md
- tridentnet.md
- models.md
- nn.md
- ops.md
- optim.md
- trainer.md
- transforms.md
- utils.data.md
- utils.md
- index.md
- mkdocs.yml
- __init__.py
- convnext.py
- darknet.py
- darknetv2.py
- darknetv3.py
- darknetv4.py
- mobileone.py
- pyconv_resnet.py
- repvgg.py
- repvit.py
- res2net.py
- resnet.py
- rexnet.py
- sknet.py
- tridentnet.py
- __init__.py
- yolo.py
- yolov2.py
- yolov4.py
- __init__.py
- unet.py
- unet3p.py
- unetpp.py
- __init__.py
- checkpoints.py
- presets.py
- utils.py
- __init__.py
- activation.py
- attention.py
- conv.py
- downsample.py
- dropblock.py
- lambda_layer.py
- loss.py
- __init__.py
- functional.py
- init.py
- __init__.py
- boxes.py
- __init__.py
- adabelief.py
- adamp.py
- adan.py
- ademamix.py
- lamb.py
- lars.py
- ralars.py
- tadam.py
- wrapper.py
- __init__.py
- classification.py
- core.py
- detection.py
- segmentation.py
- utils.py
- __init__.py
- interpolation.py
- __init__.py
- collate.py
- __init__.py
- fonts.py
- misc.py
- __init__.py
- README.md
- README.md
- train.py
- train_characters.py
- README.md
- train.py
- transforms.py
- latin-starter.json
- README.md
- train.py
- transforms.py
- clean_checkpoint.py
- README.md
- eval_latency.py
- export_to_onnx.py
- prepare_fonts.py
- test_docs.py
- test_models.py
- test_models_classification.py
- test_models_detection.py
- test_models_segmentation.py
- test_nn.py
- test_nn_activation.py
- test_nn_attention.py
- test_nn_conv.py
- test_nn_downsample.py
- test_nn_init.py
- test_nn_loss.py
- test_ops.py
- test_optim.py
- test_optim_wrapper.py
- test_train_characters.py
- test_trainer.py
- test_trainer_utils.py
- test_transforms.py
- test_utils.py
- .gitignore
- .pre-commit-config.yaml
- CITATION.cff
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- LICENSE
- Makefile
- pyproject.toml
- README.md
- uv.lock
# Installation Guide
git clone https://github.com/frgfm/holocron
Downloads the entire project code from GitHub to your computer.
cd holocron
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
pip install pylocron
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.
3. Docker
Easy- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker build -f api/Dockerfile -t holocron .
Builds a runnable image based on the Dockerfile.
docker run -p 8080:80 holocron
Runs the built image as an actual container.
4. Python
Easypip install pylocron
Installs the package published on PyPI directly β no need to clone the source.
pip install -e Holocron/.
Installs the Python libraries listed in requirements.txt (or similar).
Pulled directly from this repo's README.
5. Make
Medium- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
make build-api
Compiles the code based on the generated build configuration to produce an executable.
make start-api
Compiles the code based on the generated build configuration to produce an executable.
Pulled directly from this repo's README.