Upload 5 files

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+data/product_data.csv filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,8 @@
+env/
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+*.DS_Store
+data/embeddings.npy
+data/image_urls.pkl

README.md

@@ -1,13 +0,0 @@
----
-title: Product Recommendation
-emoji: 📉
-colorFrom: blue
-colorTo: pink
-sdk: gradio
-sdk_version: 5.34.2
-app_file: app.py
-pinned: false
-short_description: Transformer model with vector embedding and faiss index
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

precompute_embeddings.py

@@ -0,0 +1,31 @@
+import pandas as pd
+import numpy as np
+import pickle
+from tqdm import tqdm
+from model.feature_extractor import FeatureExtractor
+from utils.image_utils import load_image_from_url
+
+def main():
+    df = pd.read_csv("data/product_data.csv")
+    fe = FeatureExtractor()
+    embeddings = []
+    valid_urls = []
+
+    # tqdm wraps the iterable and shows progress bar with description
+    for url in tqdm(df['IMAGE_URL'], desc="Extracting embeddings"):
+        img = load_image_from_url(url)
+        if img is not None:
+            emb = fe.extract(img)
+            embeddings.append(emb)
+            valid_urls.append(url)
+
+    embeddings = np.array(embeddings)
+    np.save("data/embeddings.npy", embeddings)
+
+    with open("data/image_urls.pkl", "wb") as f:
+        pickle.dump(valid_urls, f)
+
+    print(f"Saved {len(valid_urls)} embeddings and URLs.")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,13 @@
+streamlit
+torch
+torchvision
+timm
+faiss-cpu
+pandas
+Pillow
+requests
+tqdm
+numpy
+fastapi
+uvicorn
+openpyxl