aa2020unlp-covid-19-xray's Introduction

aa2020unlp-covid-19-xray

Kaggle Challenge to Classify Covid Pneumonia Xray

Content

aa2020unlp-covid-19-xray
- Content
- Quickstart
  - Tags
  - Variants
- Datasets

Quickstart

To start the docker container execute the following command

$ ./bin/docker [-n <string>] [-t <tag-name>] [--sudo] [--build] [-d] [-c <command>]

Variants

Each base tag has variants that add or change functionality:

<tag>-gpu The specified tag release with GPU support. (See below)
<tag>-py3 The specified tag release with Python 3 support.
<tag>-jupyter The specified tag release with Jupyter (includes TensorFlow tutorial notebooks)

You can use multiple variants at once. For example, the following downloads TensorFlow release images to your machine. For example:

$ ./bin/docker -n myContainer --build  # latest stable release
$ ./bin/docker -n myContainer --build -t devel-gpu # nightly dev release w/ GPU support
$ ./bin/docker -n myContainer --build -t latest-gpu-jupyter # latest release w/ GPU support and Jupyter

Once the docker container is running it will execute the contents of the /bin/execute file.

You can execute

$ docker exec -it <container-id> /bin/sh -c "[ -e /bin/bash ] && /bin/bash || /bin/sh"

to access the running container's shell.

Datasets

You will need the other datasets to use localted at data/<dataset_name>/data in order to generate the new dataset. Then, you can just run the following command in order to generate the new dataset.

$ pip install -e .
$ python src/datasets/datagen/cli.py \
    --dataset aa2020 \
    --splits_dir ./data/aa2020/splits \
    --split v1 \
    --train_size 0.80 \
    --test_size 0.20 \
    --seed 40 \
    --gs \
    -w

Recommend Projects