xview3-kohei-solution

Usage

This repository assumes that the given data set is stored in the following locations:

$ ls data/input/xview3/*.csv
data/input/xview3/train.csv  data/input/xview3/validation.csv

$ ls data/input/xview3/downloaded
00a035722196ee86t.tar.gz  4455faa0cb4824f4t.tar.gz  85fe34d1aee53a7ft.tar.gz  c07f6ec980c2c149t.tar.gz
014261f774287442t.tar.gz  4518c556b38a5fa4t.tar.gz  864390795b0439b1t.tar.gz  c0831dbd6d7f3c56t.tar.gz
(snip)

In the case of training, create a virtual env as follows:

# Setup: Create the virtual env
$ poetry config virtualenvs.in-project true
$ poetry install
$ poetry run pip install albumentations timm segmentation_models_pytorch torch==1.10.0+cu113 torchvision==0.11.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html

Training

To save storage space, my preprocessing code assumes that the input image file is the original file in .tar.gz format. It does NOT assume pre-extracted files. The batch size and other settings are based on the assumption that two RTX3080 GPU cards are used.

$ bash train.sh

Inference

My containerized inference code follows the xView3 evaluation protocol. The detailed usage of the xview3 evaluation protocol is described in https://iuu.xview.us/verify.

To build the Docker Image, you need the model weights generated by train.sh. The pre-computed files can be downloaded from my Google Drive.

You will also need to download and extract gshhg-shp-2.3.7.zip as external data. GSHHG data can be found at https://www.ngdc.noaa.gov/mgg/shorelines/data/gshhg/latest/

The Docker image containing these model weights and external data has already been uploaded to Docker Hub (smly/kohei-xview3:latest).

## Setup: Build the docker image -----
$ docker build --no-cache -t kohei-xview3 .

## Inference -----
$ docker run \
    --shm-size 16G \
    --gpus=1 \
    --mount type=bind,source=/home/xv3data,target=/on-docker/xv3data \
    kohei-xview3 \
    /on-docker/xv3data/ \
    0157baf3866b2cf9v \
    /on-docker/xv3data/prediction/prediction.csv

Kohei's 5th place solution for xview3 challenge

Related tags

Overview

xview3-kohei-solution

Usage

Training

Inference

Owner

Kohei Ozaki

Code for CMaskTrack R-CNN (proposed in Occluded Video Instance Segmentation)

Use your Philips Hue lights as Racing Flags. Works with Assetto Corsa, Assetto Corsa Competizione and iRacing.

Codes for TIM2021 paper "Anchor-Based Spatio-Temporal Attention 3-D Convolutional Networks for Dynamic 3-D Point Cloud Sequences"

NAACL2021 - COIL Contextualized Lexical Retriever

This repository is for Competition for ML_data class

UniFormer - official implementation of UniFormer

Pytorch implementation of NEGEV method. Paper: "Negative Evidence Matters in Interpretable Histology Image Classification".

This repository contains the reference implementation for our proposed Convolutional CRFs.

PyTorch code for DriveGAN: Towards a Controllable High-Quality Neural Simulation

General Assembly Capstone: NBA Game Predictor

Bayesian Optimization using GPflow

Simulations for Turring patterns on an apically expanding domain. T

Dataset and Source code of paper 'Enhancing Keyphrase Extraction from Academic Articles with their Reference Information'.

Perform zero-order Hankel Transform for an 1D array (float or real valued).

Official repository of the paper "GPR1200: A Benchmark for General-PurposeContent-Based Image Retrieval"

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Unofficial Implementation of MLP-Mixer, Image Classification Model

custom pytorch implementation of MoCo v3

Tensorflow implementation of "Learning Deconvolution Network for Semantic Segmentation"

AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation