From 392e402c2eece87ab3d4dad220366ccbdb4f99c3 Mon Sep 17 00:00:00 2001
From: Craig <cdmacfadyen@gmail.com>
Date: Sat, 12 Apr 2025 10:14:46 +0100
Subject: [PATCH] chore: Update .gitignore to include custom ignores and remove
 outdated hint from prompt_plan.md

---
 .gitignore               |  8 +++++++-
 prompt_plan.md           |  1 -
 scripts/download_data.sh | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 41 insertions(+), 2 deletions(-)
 create mode 100755 scripts/download_data.sh

diff --git a/.gitignore b/.gitignore
index 1800114..bf6241f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -171,4 +171,10 @@ cython_debug/
 .ruff_cache/
 
 # PyPI configuration file
-.pypirc
\ No newline at end of file
+.pypirc
+
+# Custom Ignores
+data/
+outputs/
+logs/
+*.pth
\ No newline at end of file
diff --git a/prompt_plan.md b/prompt_plan.md
index d9ef64e..85e0994 100644
--- a/prompt_plan.md
+++ b/prompt_plan.md
@@ -101,7 +101,6 @@ Implement the core dataset loading logic in `utils/data_utils.py`:
     *   In `__len__(self)`:
         *   Return the total number of images.
 
-*(Hint: Refer to the Torchvision Object Detection Finetuning Tutorial for guidance on parsing masks and structuring the target dictionary: https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html)*
 ```
 
 ## Prompt 5: Data Utilities (Transforms and Collate)
diff --git a/scripts/download_data.sh b/scripts/download_data.sh
new file mode 100755
index 0000000..e3da710
--- /dev/null
+++ b/scripts/download_data.sh
@@ -0,0 +1,34 @@
+#!/bin/bash
+
+set -e # Exit immediately if a command exits with a non-zero status.
+
+DATA_DIR="data"
+TARGET_DIR="$DATA_DIR/PennFudanPed"
+ZIP_FILE="$DATA_DIR/PennFudanPed.zip"
+URL="https://www.cis.upenn.edu/~jshi/ped_html/PennFudanPed.zip"
+
+# 1. Check if the target directory already exists
+if [ -d "$TARGET_DIR" ]; then
+    echo "Dataset already exists at $TARGET_DIR. Skipping download."
+    exit 0
+fi
+
+# 2. Create the data directory if it doesn't exist
+mkdir -p "$DATA_DIR"
+echo "Created directory $DATA_DIR (if it didn't exist)."
+
+# 3. Download the dataset
+echo "Downloading dataset from $URL..."
+wget -O "$ZIP_FILE" "$URL"
+echo "Download complete."
+
+# 4. Extract the dataset
+echo "Extracting $ZIP_FILE to $DATA_DIR..."
+unzip -q "$ZIP_FILE" -d "$DATA_DIR" # -q for quiet mode
+echo "Extraction complete."
+
+# 5. Remove the zip file
+rm "$ZIP_FILE"
+echo "Removed $ZIP_FILE."
+
+echo "Dataset setup complete in $TARGET_DIR." 
\ No newline at end of file