Shunta Saito's repositories
burn-captions
Burn captions (.srt) into videos
openmpi-cuda-bins
Pre-built binaries of OpenMPI w/ CUDA & verbs options
consistency_models
Official repo for consistency models.
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
jupyterlab
JupyterLab computational environment.
kornia
Open Source Differentiable Computer Vision Library for PyTorch
mallet
TCP tunnel that works like VPN
mlx-examples
Examples in the MLX framework
mmdetection
OpenMMLab Detection Toolbox and Benchmark
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
pfio
IO library to access various filesystems with unified API
ragas
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
s3fs
S3 Filesystem
tfrecord-viewer
TFRecord Viewer for browsing contents of TFRecords with object detection/classification annotations.
UniverseNet
Object detection. EfficientDet-D5 level COCO AP in 20 epochs. SOTA single-stage detector on Waymo Open Dataset.
vision
Datasets, Transforms and Models specific to Computer Vision
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/