From de44cad219b00fe88e1d993c684997b1d3b9e35b Mon Sep 17 00:00:00 2001 From: snsd0805 Date: Sat, 11 May 2024 21:55:58 +0800 Subject: [PATCH] feat: add dataset container's example dockerfile --- dataset/Dockerfile | 16 ++++++++++++++++ dataset/dataset_dir/.gitkeep | 0 2 files changed, 16 insertions(+) create mode 100644 dataset/Dockerfile create mode 100644 dataset/dataset_dir/.gitkeep diff --git a/dataset/Dockerfile b/dataset/Dockerfile new file mode 100644 index 0000000..9f48b53 --- /dev/null +++ b/dataset/Dockerfile @@ -0,0 +1,16 @@ +# we will run `docker run -it --rm -v ./dataset_dir:/dataset YOUR_IMAGE` to run the downloading container. +# The provider will mount their `dataset_dir` to `/dataset` directory in the container. +# So, you should save your dataset into `/dataset` so that our `training container` can access your dataset. + +FROM ubuntu:22.04 + +# This is our example script: +# First, we create the directory named `/dataset` so that it can link to the provider's host. +# Then, we use apt to download `wget` so that we can use wget to download the dataset from our target URL. +RUN mkdir /dataset && apt-get update && apt-get install -y wget + +# And we get the dataset file from the target URL and save it into /dataset +# Then, we unzip it so that the `training container` can access them directly. +WORKDIR /dataset +CMD pwd && wget https://www.cs.toronto.edu/\~kriz/cifar-10-python.tar.gz && tar zxvf cifar-10-python.tar.gz + diff --git a/dataset/dataset_dir/.gitkeep b/dataset/dataset_dir/.gitkeep new file mode 100644 index 0000000..e69de29