Motoki Kimura's repositories
spacenet_building_detection
Project to train/test convolutional neural networks to extract buildings from SpaceNet satellite imageries.
PyTorch_Gaussian_YOLOv3
PyTorch implementation of Gaussian YOLOv3 (including training code for COCO dataset)
yolo_v1_pytorch
PyTorch implementation of YOLO-v1 including training
kalman_filter_with_kitti
Applying extended Kalman filter to KITTI GPS/IMU data for vehicle localization
yolox-ti-lite_tflite
YOLOX-ti-lite models exportable to TFLite
kits19_3d_segmentation
PyTorch implementation of 3D U-Net for kidney and tumor segmentation from KiTS19 CT scans.
pytorch_quantization_fx
An example to quantize MobileNetV2 trained on CIFAR-10 dataset with PyTorch
solafune_vehicle_detection_solution
motokimura's solution for Solafune "Vehicle Detection in Multi-Resolution Images" competition
spacenet8_solution_5th-place
5th-place solution for SpaceNet-8: Flood Detection Challenge Using Multiclass Segmentation
ultralytics
NEW - YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
paddleseg_playground
Provides Docker environment with which you can play around with PaddleSeg framework.
spacenet7_solution
motokimura's Solution for SpaceNet 7
high-res-stereo-1
Hierarchical Deep Stereo Matching on High Resolution Images, CVPR 2019.
mmdetection
OpenMMLab Detection Toolbox and Benchmark
motokimura.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
pytorch-fid
Compute FID scores with PyTorch.
UniverseNet
Object detection. EfficientDet-D5 level COCO AP in 20 epochs. SOTA single-stage detector on Waymo Open Dataset.