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

PyTorch implementation for Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition.

Unofficial pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"

An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).

Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset

Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection

SFD implement with pytorch

Improving 3D Object Detection with Channel-wise Transformer

Intel® Nervana™ reference deep learning framework committed to best performance on all hardware

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models.

Fully Adaptive Bayesian Algorithm for Data Analysis (FABADA) is a new approach of noise reduction methods. In this repository is shown the package developed for this new method based on \citepaper.

Supervised multi-SNE (S-multi-SNE): Multi-view visualisation and classification

Adapter-BERT: Parameter-Efficient Transfer Learning for NLP.

Multi-Task Deep Neural Networks for Natural Language Understanding

本步态识别系统主要基于GaitSet模型进行实现

Updated for TTS(CE) = Also Known as TTN V3. The code requires the first server to be 'ttn' protocol.

Official implementation of NeurIPS'21: Implicit SVD for Graph Representation Learning

Official implementation for paper Knowledge Bridging for Empathetic Dialogue Generation (AAAI 2021).

No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency

KoRean based ELECTRA pre-trained models (KR-ELECTRA) for Tensorflow and PyTorch

Invariant Causal Prediction for Block MDPs