Kentaro Yoshioka
kentaroy47
4-year old Ph.D researcher interested in efficient and fast systems.
Languages
Top Repositories
Let's train vision transformers (ViT) for cifar 10 / cifar 100!
:collision:Faster R-CNN from scratch written with Keras
Stream Apple LiDAR (iPad/iPhone) data with open3d
1st place solution for the Kaggle PANDA Challenge
:neckbeard:Unofficial implementation of EfficientDet
Benchmark inference speed of CNNs with various quantization methods in Pytorch+TensorRT with Jetson Nano/Xavier
Repositories
125Let's train vision transformers (ViT) for cifar 10 / cifar 100!
No description provided.
No description provided.
Stream Apple LiDAR (iPad/iPhone) data with open3d
This is a collection of works on neural networks and neural accelerators.
No description provided.
No description provided.
ODA is a test-time-augmentation(TTA) tool for 2D object detectors. For use in Kaggle competitions.
Unofficial Pytorch implementation of :fire:BlazeFace:fire:
1st place solution for the Kaggle PANDA Challenge
釣りビジョンの釣果をスクレイピング→可視化
No description provided.
visualize the depth anything results as pointclouds (open3d)
:collision:Faster R-CNN from scratch written with Keras
Startup some anomaly detection with pytorch!
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
Let's train CIFAR 10 Pytorch with Half-Precision!
Benchmark inference speed of CNNs with various quantization methods in Pytorch+TensorRT with Jetson Nano/Xavier
:neckbeard:Unofficial implementation of EfficientDet
Train cifar10 networks and inference with tensorrt.
NLP2025の著者ネットワーク可視化
Unofficial Pytorch implementation of Deep Compression in CIFAR10
Download Youtube, Twitch, whatever videos with a Python script.
Pytorch Pretrained Resnet18, 34, 50 backbone of faster-rcnn
MOT tracking using deepsort and faster-rcnn
Unofficial implementation of textsnake. Mostly to practice code reading.
Simulate ADC quantization with python/numpy.
Labelme modified to output voc-like datasets
No description provided.