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

Creative Applications of Deep Learning w/ Tensorflow

A selection of State Of The Art research papers (and code) on human locomotion (pose + trajectory) prediction (forecasting)

Repo for the paper Extrapolating from a Single Image to a Thousand Classes using Distillation

[IEEE Transactions on Computational Imaging] Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting

Readings for "A Unified View of Relational Deep Learning for Polypharmacy Side Effect, Combination Therapy, and Drug-Drug Interaction Prediction."

QICK: Quantum Instrumentation Control Kit

We will release the code of "ConTNet: Why not use convolution and transformer at the same time?" in this repo

Embracing Single Stride 3D Object Detector with Sparse Transformer

IDA file loader for UF2, created for the DEFCON 29 hardware badge

unet for image segmentation

Code for the head detector (HeadHunter) proposed in our CVPR 2021 paper Tracking Pedestrian Heads in Dense Crowd.

Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

GAN-based 3D human pose estimation model for 3DV'17 paper

A template repository for submitting a job to the Slurm Cluster installed at the DISI - University of Bologna

Semi-supervised semantic segmentation needs strong, varied perturbations

Lenia - Mathematical Life Forms

Automatically replace ONNX's RandomNormal node with Constant node.

First-Order Probabilistic Programming Language

Code and data of the ACL 2021 paper: Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision