inference.py

import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision.transforms as transforms
from PIL import Image
import numpy as np

class CNNModel(nn.Module):
    def __init__(self, num_classes=10, dropout_rate=0.5):
        super(CNNModel, self).__init__()

        # First convolutional block
        self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=3, padding=1)
        self.bn1 = nn.BatchNorm2d(32)
        self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)

        # Second convolutional block
        self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, padding=1)
        self.bn2 = nn.BatchNorm2d(64)
        self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)

        # Third convolutional block
        self.conv3 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, padding=1)
        self.bn3 = nn.BatchNorm2d(128)
        self.pool3 = nn.MaxPool2d(kernel_size=2, stride=2)

        self.flattened_size = 128 * 3 * 3

        # Fully connected layers with dropout
        self.fc1 = nn.Linear(self.flattened_size, 512)
        self.dropout1 = nn.Dropout(dropout_rate)
        self.fc2 = nn.Linear(512, 256)
        self.dropout2 = nn.Dropout(dropout_rate)
        self.fc3 = nn.Linear(256, num_classes)

    def forward(self, x):
        # First conv block
        x = self.conv1(x)
        x = self.bn1(x)
        x = F.relu(x)
        x = self.pool1(x)

        # Second conv block
        x = self.conv2(x)
        x = self.bn2(x)
        x = F.relu(x)
        x = self.pool2(x)

        # Third conv block
        x = self.conv3(x)
        x = self.bn3(x)
        x = F.relu(x)
        x = self.pool3(x)

        # Flatten for FC layers
        x = x.view(x.size(0), -1)

        # Fully connected layers with dropout
        x = F.relu(self.fc1(x))
        x = self.dropout1(x)
        x = F.relu(self.fc2(x))
        x = self.dropout2(x)
        x = self.fc3(x)

        return x

def load_model(model_path):
    """Load the trained model"""
    model = CNNModel()
    model.load_state_dict(torch.load(model_path, map_location='cpu'))
    model.eval()
    return model

def predict_image(model, image_path):
    """Predict digit from image"""
    # Load and preprocess image
    transform = transforms.Compose([
        transforms.Grayscale(),
        transforms.Resize((28, 28)),
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
    ])

    image = Image.open(image_path)
    image_tensor = transform(image).unsqueeze(0)

    # Make prediction
    with torch.no_grad():
        outputs = model(image_tensor)
        _, predicted = torch.max(outputs, 1)
        shifted_prediction = predicted.item()

        # Convert back to original digit
        original_digit = 9 - shifted_prediction

    return original_digit, shifted_prediction

# Example usage:
# model = load_model('pytorch_model.bin')
# original, shifted = predict_image(model, 'your_image.png')
# print(f"Original digit: {original}, Shifted prediction: {shifted}")