Refactor training loop from script to class

src/api.py

@@ -1,28 +1,28 @@
-from fastapi import FastAPI, UploadFile, File
-from PIL import Image
 import torch
+from fastapi import FastAPI, File, UploadFile
+from PIL import Image
 from torchvision import transforms
-from main import Net  # Importing Net class from main.py
 
-# Load the model
-model = Net()
-model.load_state_dict(torch.load("mnist_model.pth"))
-model.eval()
+from main import MNISTTrainer  # Importing MNISTTrainer class from main.py
+
+trainer = MNISTTrainer()
+model = trainer.load_model("mnist_model.pth")
 
 # Transform used for preprocessing the image
-transform = transforms.Compose([
-    transforms.ToTensor(),
-    transforms.Normalize((0.5,), (0.5,))
-])
+transform = transforms.Compose(
+    [transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]
+)
 
 app = FastAPI()
 
+
 @app.post("/predict/")
 async def predict(file: UploadFile = File(...)):
+    """Predict the digit in the uploaded image using the loaded model."""
     image = Image.open(file.file).convert("L")
     image = transform(image)
     image = image.unsqueeze(0)  # Add batch dimension
     with torch.no_grad():
-        output = model(image)
+        output = trainer.predict(image)  # Use the predict method of the trainer
         _, predicted = torch.max(output.data, 1)
     return {"prediction": int(predicted[0])}

src/main.py

@@ -1,48 +1,58 @@
-from PIL import Image
 import torch
 import torch.nn as nn
 import torch.optim as optim
-from torchvision import datasets, transforms
 from torch.utils.data import DataLoader
-import numpy as np
-
-# Step 1: Load MNIST Data and Preprocess
-transform = transforms.Compose([
-    transforms.ToTensor(),
-    transforms.Normalize((0.5,), (0.5,))
-])
+from torchvision import datasets, transforms
 
-trainset = datasets.MNIST('.', download=True, train=True, transform=transform)
-trainloader = DataLoader(trainset, batch_size=64, shuffle=True)
 
-# Step 2: Define the PyTorch Model
-class Net(nn.Module):
+class MNISTTrainer:
     def __init__(self):
-        super().__init__()
-        self.fc1 = nn.Linear(28 * 28, 128)
-        self.fc2 = nn.Linear(128, 64)
-        self.fc3 = nn.Linear(64, 10)
-
-    def forward(self, x):
-        x = x.view(-1, 28 * 28)
-        x = nn.functional.relu(self.fc1(x))
-        x = nn.functional.relu(self.fc2(x))
-        x = self.fc3(x)
-        return nn.functional.log_softmax(x, dim=1)
-
-# Step 3: Train the Model
-model = Net()
-optimizer = optim.SGD(model.parameters(), lr=0.01)
-criterion = nn.NLLLoss()
-
-# Training loop
-epochs = 3
-for epoch in range(epochs):
-    for images, labels in trainloader:
-        optimizer.zero_grad()
-        output = model(images)
-        loss = criterion(output, labels)
-        loss.backward()
-        optimizer.step()
-
-torch.save(model.state_dict(), "mnist_model.pth")
+        self.transform = transforms.Compose(
+            [transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]
+        )
+        self.optimizer = None
+        self.criterion = nn.NLLLoss()
+
+    def load_data(self):
+        trainset = datasets.MNIST(
+            ".", download=True, train=True, transform=self.transform
+        )
+        return DataLoader(trainset, batch_size=64, shuffle=True)
+
+    class Net(nn.Module):
+        def __init__(self):
+            super().__init__()
+            self.fc1 = nn.Linear(28 * 28, 128)
+            self.fc2 = nn.Linear(128, 64)
+            self.fc3 = nn.Linear(64, 10)
+
+        def forward(self, x):
+            x = x.view(-1, 28 * 28)
+            x = nn.functional.relu(self.fc1(x))
+            x = nn.functional.relu(self.fc2(x))
+            x = self.fc3(x)
+            return nn.functional.log_softmax(x, dim=1)
+
+    def define_model(self):
+        model = self.Net()
+        self.optimizer = optim.SGD(model.parameters(), lr=0.01)
+        return model
+
+    def train_model(self, model, trainloader):
+        epochs = 3
+        for _epoch in range(epochs):
+            for images, labels in trainloader:
+                self.optimizer.zero_grad()
+                output = model(images)
+                loss = self.criterion(output, labels)
+                loss.backward()
+                self.optimizer.step()
+
+    def save_model(self, model):
+        torch.save(model.state_dict(), "mnist_model.pth")
+
+    def load_model(self, model_path):
+        model = self.define_model()
+        model.load_state_dict(torch.load(model_path))
+        model.eval()
+        return model