Upload README.md with huggingface_hub

README.md

@@ -1,89 +1,103 @@
 ---
+---
 tags:
   - image-classification
   - cnn
   - cifar-10
 license: apache-2.0
-library_name: transformers
+library_name: pytorch
 ---
-README.md for tiny-cnn-classifier
-
-Tiny CNN Classifier for Image Classification (CIFAR-10)
-
-This is a custom Convolutional Neural Network (CNN) model trained on the CIFAR-10 dataset. The model classifies images into 10 categories: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck. It was trained using the PyTorch framework.
-
-Model Overview
-
-Type: Convolutional Neural Network (CNN)
-
-Architecture:
-  - 2 convolutional layers
-  - 2 max-pooling layers
-  - 2 fully connected layers
-  - ReLU activation functions
-
-Dataset: CIFAR-10 (10 classes)
-
-Test Accuracy: 69.90%
 
-How the Model Works:
-The model uses two convolutional layers followed by max-pooling and fully connected layers to classify images. The model was trained for 5 epochs on the CIFAR-10 dataset.
+# Tiny CNN Classifier for CIFAR-10
 
-How to Use the Model:
+This is a custom **Convolutional Neural Network (CNN)** trained on the **CIFAR-10 dataset**.  
+It classifies images into 10 categories:  
+`airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck`
 
-To use this model for image classification, you can use the following code snippet:
-
-
-
-```python
+---
 
-from transformers import pipeline
+## 📖 Model Overview
 
+- **Type**: Convolutional Neural Network (CNN)  
+- **Architecture**:
+  - 2 convolutional layers  
+  - 2 max-pooling layers  
+  - 2 fully connected layers  
+  - ReLU activation functions  
+- **Dataset**: CIFAR-10 (10 classes)  
+- **Framework**: PyTorch  
+- **Test Accuracy**: **69.90%**  
+- **Training Epochs**: 5  
 
+The model uses two convolutional layers followed by max-pooling and fully connected layers to classify images. It was trained using Adam optimizer and Cross-Entropy loss.  
 
-# Load the trained model
+---
 
-classifier = pipeline('image-classification', model='Udayan012/tiny-cnn-classifier')
+## 🚀 How to Use
 
-# Provide an image to classify
+> ⚠️ Note: This is **not a Hugging Face Transformers model**.  
+> You **cannot** use `pipeline()`. Instead, load it directly with **PyTorch**.
 
-image = 'path\_to\_your\_image.jpg'
+### 1. Clone the repository
+```bash
+git clone https://huggingface.co/Udayan012/tiny-cnn-classifier
+cd tiny-cnn-classifier
 
-# Get the classification result
+### 2. Install Dependencies
+```bash
+pip install torch torchvision pillow
 
-result = classifier(image)
+### 3. Load the model
+```python 
+import torch
+from model import CustomCNN
 
-# Print the result
+# Initialize model and load weights
+model = CustomCNN()
+model.load_state_dict(torch.load("cnn_model.pth", map_location="cpu"))
+model.eval()
 
-print(result)
+### 4. Run inference on an image
+```python
+from torchvision import transforms
+from PIL import Image
 
-Steps to classify your own images:-
+# CIFAR-10 preprocessing (32x32 RGB)
+transform = transforms.Compose([
+    transforms.Resize((32, 32)),
+    transforms.ToTensor(),
+])
 
-1. Install necessary libraries:
+# Load an image
+img = Image.open("test.jpg").convert("RGB")
+x = transform(img).unsqueeze(0)
 
-pip install transformers torch torchvision
+# Predict
+with torch.no_grad():
+    output = model(x)
+    pred_class = output.argmax(1).item()
 
-2. Use the pipeline() function to load the model and classify images.
+classes = ['airplane','automobile','bird','cat','deer','dog','frog','horse','ship','truck']
+print("Predicted class:", classes[pred_class])
 
 
-Training Information:
+### Training Information
 
 Dataset: CIFAR-10
 Optimizer: Adam
 Loss Function: Cross-Entropy Loss
-Training Epochs: 5
+Epochs: 5
 Batch Size: 32
 Learning Rate: 0.001
 
-Model Limitations:
-
-The model is trained on the CIFAR-10 dataset and performs well on images similar to the CIFAR-10 test set.
-The model may not generalize well to high-resolution images or images with complex backgrounds.
-It performs best on 32x32 pixel images with simple backgrounds, similar to those in the CIFAR-10 dataset.
 
+### Model Limitations
 
+Trained only on CIFAR-10 → works best on 32x32 images with simple backgrounds.
+May not generalize well to high-resolution or real-world images.
 
-License:
 
-This model is released under the Apache 2.0 License. You can freely use, modify, and distribute this model.
+### License
 
+This model is released under the Apache 2.0 License.
+You can freely use, modify, and distribute this model.