Don't have [AIcrowd CLI](https://pypi.org/project/aicrowd-cli/) installed? 🥺<br>You can install it [here](https://pypi.org/project/aicrowd-cli/) or **[Download Datasets without CLI](https://www.aicrowd.com/challenges/data-purchasing-challenge-2022/dataset_files)**.
## Dataset Distribution
A quick distribution of the dataset is as follows:
The publicaly released dataset is for local experiments and validating your codebases. The private dataset which is used for all the phases during evaluation are different from the publicaly released ones.
## Using this repository
...
...
@@ -96,7 +103,7 @@ This will run all the phases (pre_training, purchase & prediction) locally and s
The participation flow look as follows:
<imgsrc="https://i.imgur.com/4mgcD5N.jpg">
<imgsrc="https://i.imgur.com/XcLF9dF.jpg">
Quick description about all the phases:
...
...
@@ -130,6 +137,8 @@ Quick description about all the phases:
More details for active participation in present in [SUBMISSION.md](/evaluator/SUBMISSION.md)
In Round 1, your code will have access to machine with 4 CPUS, 16 GB RAM, 1 NVIDIA **T4 GPU** and **3 hours of runtime** per submission (`g4dn.xlarge` on AWS). In the Round 2 of this competition, your code will be evaluated across multiple budget-runtime constraints which will be announced later.