Update README.md

README.md

@@ -1,4 +1,10 @@
 ---
+title: Hindi Character Classifier
+emoji: 🖼️
+colorFrom: red
+colorTo: blue
+sdk: streamlit
+sdk_version: "1.25.0"
 library_name: torch
 pipeline_tag: image-classification
 ---
@@ -9,16 +15,49 @@ This model is a Convolutional Neural Network (CNN) for Hindi character image cla
 
 ## Usage
 
-(Provide instructions on how to load and use your model. Include code snippets.)
+This model is designed to classify images of Hindi characters. It takes a 32x32 pixel RGB image as input and outputs the predicted Hindi character class.
 
-Example:
+**To use this model within a Hugging Face Space (Streamlit example):**
+
+1.  **Ensure you have the following files in your space:**
+    * `your_model_file.py`: Contains the `HindiCharacterCNN` class definition.
+    * `your_model.safetensors`: The model's weights.
+    * `app.py`: The Streamlit application script.
+    * `requirements.txt`: Lists your dependencies (torch, torchvision, pillow, streamlit).
+2.  **Example `app.py` (Streamlit):**
 
 ```python
+import streamlit as st
 import torch
-from your_model_file import HindiCharacterCNN #replace your_model_file
+from PIL import Image
+import torchvision.transforms as transforms
+from your_model_file import HindiCharacterCNN  # Replace with your model file
 
+# Load model
 model = HindiCharacterCNN(num_labels=36)
-model.load_state_dict(torch.load("your_model.safetensors")) #or .bin
+model.load_state_dict(torch.load("your_model.safetensors", map_location=torch.device('cpu')))
 model.eval()
 
-# ... your inference code ...
+# Preprocessing
+transform = transforms.Compose([
+    transforms.Resize((32, 32)),
+    transforms.ToTensor(),
+])
+
+st.title("Hindi Character Classification")
+
+uploaded_file = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])
+
+if uploaded_file is not None:
+    image = Image.open(uploaded_file).convert('RGB')
+    st.image(image, caption="Uploaded Image.", use_column_width=True)
+    st.write("")
+    st.write("Classifying...")
+
+    image = transform(image).unsqueeze(0)
+
+    with torch.no_grad():
+        output = model(image)
+        probabilities = torch.nn.functional.softmax(output[0], dim=0)
+        _, predicted_class = torch.max(probabilities, 0)
+        st.write(f"Predicted Class: {int(predicted_class)}")