kentaroy47

vision-transformers-cifar10

Let's train vision transformers (ViT) for cifar 10!

apple-lidar-stream

Stream Apple LiDAR (iPad/iPhone) data with open3d

benchmark-FP32-FP16-INT8-with-TensorRT

Benchmark inference speed of CNNs with various quantization methods in Pytorch+TensorRT with Jetson Nano/Xavier

timm_speed_benchmark

Benchmark Benchmark Benchmark!

ODA-Object-Detection-ttA

ODA is a test-time-augmentation(TTA) tool for 2D object detectors. For use in Kaggle competitions.

Deep-Compression.Pytorch

Unofficial Pytorch implementation of Deep Compression in CIFAR10

youtube-stream-downloader

Download Youtube, Twitch, whatever videos with a Python script.

quantize_models_sandbox

quantize models like vit and mlp-mixer

ADC-Quantization.python

Simulate ADC quantization with python/numpy.

benchmark-mygpu-pytorch

benchmark my gpu, personal note

choka-analysis

釣りビジョンの釣果をスクレイピング→可視化

quantize-huggingface

Quantize Huggingface transformers like BERT :hugs:

benchmark-object-detectors

Benchmarking object detection libraries

ByteTrack

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

citation-tracker

Track your citations on Google Scholar

computer-simulation-numerical-analysis

deep_running

Deep Running

ebook-GPT-translator

Enjoy reading with your favorite style.

FairMOT

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

ffcv-imagenet

Train ImageNet *fast* in 500 lines of code with FFCV

IEICE-TimeBasedCurrentSource

laTex source of the paper: "Time-Based Current Source: A Highly Digital Robust Current Generator for Switched Capacitor Circuits"

kentaroy47

lab-mlbook

lab_startup

研究室のPCのセットアップ資料

laser-gakkai-2023

reinforcement-learning-introduction

Swin-Transformer-Object-Detection

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

test-web

TVLSI-VCO-comparator

tex code base of the paper "VCO-based Comparator: A Fully Adaptive Noise Scaling Comparator for High-Precision and Low-Power SAR ADCs"

UniTrack

Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).