readme

README.md

@@ -9,4 +9,67 @@ app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Image Reverse Search Web App
+
+## Description
+
+### A very fast reverse image search webapp in streamlit using NVIDIA's EfficientNet and Spotify's Annoy library over atleast 7000 images.
+
+Upload a picture, and AI powered by deep learning will instantly show you visually related matches. Explore and discover connections through the magic of image recognition.
+
+## Demo
+
+Experience the app in action right in your browser: https://huggingface.co/spaces/Instantaneous1/search-by-image
+
+![Demo](UI.png)
+
+## Key Features
+
+- Upload a query image to find visually similar images in the dataset.
+- Explore retrieved images to discover related content.
+- Adjust the number of matches displayed for visual comparisons.
+- Utilizes a pre-trained image feature extractor model (EfficientNet-b0) for accurate image similarity.
+- Employs Annoy index for fast approximate nearest neighbor search.
+- Offers a user-friendly interface powered by Streamlit.
+
+## Getting Started
+
+1. Clone this repository:
+
+```bash
+git clone [[email protected]:sayan1999/search-by-image.git]([email protected]:sayan1999/search-by-image.git)
+```
+
+2. Install required libraries:
+
+```bash
+pip install -r requirements.txt
+```
+
+3. Run the Streamlit app:
+
+```bash
+streamlit run app.py
+```
+
+4. Access the app in your web browser (usually at http://localhost:8501).
+
+## Technology Stack
+
+Streamlit: Framework for building and deploying web apps in Python.
+Torch: Powerful deep learning framework.
+OpenDatasets: Library for convenient dataset downloading.
+Annoy: Library for fast approximate nearest neighbor search.
+NVIDIA EfficientNet-b0: Pre-trained image classification model for feature extraction.
+
+## Usage
+
+1. Access the app in your web browser at the provided link (usually http://localhost:8501).
+2. Click the "Upload Image" button and select an image from your computer.
+3. Optionally, adjust the number of matches using the slider.
+4. Click the "Search" button to initiate the reverse image search.
+5. The app will display the query image along with the retrieved similar images.
+
+## Dataset
+
+[https://www.kaggle.com/datasets/kkhandekar/image-dataset](https://www.kaggle.com/datasets/kkhandekar/image-dataset)

app.py

@@ -15,6 +15,7 @@ ImageFile.LOAD_TRUNCATED_IMAGES = True
 FOLDER = "images/"
 NUM_TREES = 100
 FEATURES = 1000
+FILETYPES = [".png", ".jpg", ".jpeg", ".tiff", ".bmp"]
 
 
 @st.cache_resource
@@ -53,12 +54,11 @@ def get_all_file_paths(folder_path):
     file_paths = []
     for root, _, files in os.walk(folder_path):
         for file in files:
-            if not file.lower().endswith(
-                (".png", ".jpg", ".jpeg", ".tiff", ".bmp", ".gif")
-            ):
+            if not file.lower().endswith(tuple(FILETYPES)):
                 continue
             file_path = os.path.join(root, file)
             file_paths.append(file_path)
+    print(f"Total {len(file_paths)} image files present")
     return file_paths
 
 
@@ -172,7 +172,8 @@ if __name__ == "__main__":
 
         # File uploader
         uploaded_file = st.file_uploader(
-            "Choose an image like a car, cat, dog, flower, fruits, bike, aeroplane, person"
+            "Choose an image like a car, cat, dog, flower, fruits, bike, aeroplane, person",
+            type=FILETYPES,
         )
 
         n_matches = st.slider(