Feature/byol dataset setup

Deeplens_Self_Supervised_Learning_Yashwardhan_Deshmukh/README.md

@@ -38,3 +38,15 @@ All results were calculated on a **separate test set**.
 ## Conclusion and Future Goals
 So far, we can see that the results for self-supervised learning seem superior to their ResNet50 Baseline. 
 Future goals consist of testing models for regression, implementing vision transformers (twin networks) and testing some more self-supervised learning methods.
+
+
+
+## BYOL Dataset Setup
+
+The BYOL self-supervised learning notebooks require the `Model_I` dataset
+from the DeepLenseSim repository.
+
+Before running the BYOL notebooks, download the dataset using:
+
+```bash
+python scripts/setup_byol_dataset.py

Deeplens_Self_Supervised_Learning_Yashwardhan_Deshmukh/requirements.txt

@@ -0,0 +1,9 @@
+imageio
+numpy
+pandas
+tensorflow
+keras
+matplotlib
+tqdm
+pillow
+scikit-learn

Deeplens_Self_Supervised_Learning_Yashwardhan_Deshmukh/scripts/setup_byol_dataset.py

@@ -0,0 +1,36 @@
+import os
+import zipfile
+import urllib.request
+import shutil
+
+ZIP_URL = "https://github.com/mwt5345/DeepLenseSim/archive/refs/heads/main.zip"
+ZIP_NAME = "DeepLenseSim.zip"
+EXTRACTED_DIR = "DeepLenseSim-main"
+TARGET_DIR = "Model_I"
+
+def setup_data():
+    if os.path.exists(TARGET_DIR):
+        print("[INFO] Model_I dataset already exists.")
+        return
+
+    print("[INFO] Downloading DeepLenseSim dataset...")
+    urllib.request.urlretrieve(ZIP_URL, ZIP_NAME)
+
+    print("[INFO] Extracting archive...")
+    with zipfile.ZipFile(ZIP_NAME, "r") as zip_ref:
+        zip_ref.extractall()
+
+    src = os.path.join(EXTRACTED_DIR, "Model_I")
+    if not os.path.exists(src):
+        raise RuntimeError("Model_I not found in DeepLenseSim archive")
+
+    shutil.move(src, TARGET_DIR)
+
+    # Cleanup
+    shutil.rmtree(EXTRACTED_DIR)
+    os.remove(ZIP_NAME)
+
+    print("[SUCCESS] Model_I dataset setup complete.")
+
+if __name__ == "__main__":
+    setup_data()