# Phase 2

- Refer phase2_F23.pdf for problem description

## Requirements and dependencies

- Requires MongoDB server (local or otherwise)
- Install packages from requirements.txt

## Environment variables

- `DATASET_PATH` - path to the Caltech101 dataset

## Data files

- Files should be in the same folder as the source code to be accessed properly

## Execution

- For each task, simply run all cells in the corresponding notebook and enter inputs as prompted
- Task 6 requires significant RAM and also takes a lot of time
- Task 11 takes a lot of time if constructing the similarity matrix afresh