Why deployment serves predictions in PyTorch - Experiment to Prove It

Experiment - Why deployment serves predictions

Problem:You have trained a PyTorch model to classify images, but you want to understand why deploying the model to serve predictions is important for real users.

Current Metrics:Training accuracy: 95%, Validation accuracy: 92%, No deployment yet.

Issue:The model works well during training but is not accessible to users because it is not deployed to serve predictions.

Your Task

Deploy the trained PyTorch model to serve predictions through a simple API so users can send images and get classification results.

Use PyTorch for the model.

Use a lightweight web framework like Flask or FastAPI.

Keep the deployment code simple and clear.

Hint 1

Hint 2

Hint 3

Solution

PyTorch

import torch
from torchvision import transforms
from PIL import Image
from fastapi import FastAPI, File, UploadFile
import io

# Define the model class (example: simple CNN for 10 classes)
import torch.nn as nn
import torch.nn.functional as F

class SimpleCNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 16, 3, 1)
        self.conv2 = nn.Conv2d(16, 32, 3, 1)
        self.fc1 = nn.Linear(32 * 5 * 5, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2)
        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2)
        x = torch.flatten(x, 1)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# Load the trained model weights
model = SimpleCNN()
model.load_state_dict(torch.load('model.pth', map_location=torch.device('cpu')))
model.eval()

# Define image transforms
transform = transforms.Compose([
    transforms.Resize((28, 28)),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

app = FastAPI()

@app.post('/predict')
async def predict(file: UploadFile = File(...)):
    image_bytes = await file.read()
    image = Image.open(io.BytesIO(image_bytes)).convert('RGB')
    img_t = transform(image).unsqueeze(0)  # Add batch dimension

    with torch.no_grad():
        outputs = model(img_t)
        _, predicted = torch.max(outputs, 1)

    return {'predicted_class': int(predicted.item())}

# To run this app, save as app.py and run:
# uvicorn app:app --reload

Created a simple CNN model class matching the trained model.

Loaded the trained model weights with map_location to handle CPU loading and set model to evaluation mode.

Built a FastAPI app with a /predict endpoint to accept image uploads.

Processed uploaded images with transforms before prediction.

Normalized images with 3 channels mean and std instead of 1 channel.

Returned the predicted class as JSON to serve predictions.

Results Interpretation

Before deployment: Model had high accuracy but was not accessible to users.

After deployment: Model serves predictions through an API, making it usable in real applications.

Deploying a trained model to serve predictions is essential to make the model useful for real-world users. It bridges the gap between training and practical use by providing an interface for input and output.

Bonus Experiment

Extend the deployment to accept multiple images at once and return predictions for all.

💡 Hint

Modify the API endpoint to accept a list of files, process each image in a loop, and return a list of predicted classes.

Practice

1. Why do we deploy a trained PyTorch model to serve predictions?

easy

A. To use the learned knowledge on new, unseen data

B. To train the model faster

C. To increase the size of the training dataset

D. To debug the model's training code

Solution

1. Step 1: Understand deployment purpose

   Deployment means making the model ready to use outside training, usually to predict new data.

2. Step 2: Connect deployment to prediction

   Serving predictions means applying the model's learned patterns to new inputs to get useful outputs.

3. Final Answer:

   To use the learned knowledge on new, unseen data -> Option A

4. Quick Check:

   Deployment = use model for new data [OK]

Hint: Deployment means using model on new data, not training [OK]

Common Mistakes:

• Confusing deployment with training
• Thinking deployment increases training speed
• Assuming deployment changes dataset size

2. Which PyTorch code snippet correctly sets the model for prediction during deployment?

easy

A. model.train()

B. model.fit()

C. model.eval()

D. model.backward()

Solution

1. Step 1: Recall model modes in PyTorch

   model.train() sets training mode; model.eval() sets evaluation mode for prediction.

2. Step 2: Identify correct mode for deployment

   During deployment, model.eval() disables dropout and batch norm updates for stable predictions.

3. Final Answer:

   model.eval() -> Option C

4. Quick Check:

   Use model.eval() for prediction mode [OK]

Hint: Use model.eval() to switch to prediction mode [OK]

Common Mistakes:

• Using model.train() during prediction
• Confusing model.eval() with training
• Using non-existent methods like model.fit()

3. What will be the output of the following PyTorch code during deployment?

import torch
model.eval()
with torch.no_grad():
    input_tensor = torch.tensor([[1.0, 2.0]])
    output = model(input_tensor)
print(output)

medium

A. Tensor with prediction values without gradient tracking

B. Tensor with prediction values but gradients are tracked

C. Error because torch.no_grad() is not allowed

D. Empty tensor because model.eval() disables output

Solution

1. Step 1: Understand torch.no_grad() effect

   torch.no_grad() disables gradient tracking to save memory during prediction.

2. Step 2: Analyze model.eval() and output

   model.eval() sets model to evaluation mode; output will be prediction tensor without gradients.

3. Final Answer:

   Tensor with prediction values without gradient tracking -> Option A

4. Quick Check:

   torch.no_grad() disables gradients during prediction [OK]

Hint: torch.no_grad() disables gradients for efficient prediction [OK]

Common Mistakes:

• Expecting gradients during prediction
• Thinking torch.no_grad() causes errors
• Assuming model.eval() disables output

4. Identify the error in this deployment code snippet for serving predictions:

model.train()
with torch.no_grad():
    output = model(input_tensor)
print(output)

medium

A. input_tensor is not defined

B. Missing optimizer step after prediction

C. torch.no_grad() should not be used during prediction

D. Using model.train() instead of model.eval() during prediction

Solution

1. Step 1: Check model mode for prediction

   model.train() enables training mode, which is incorrect for deployment predictions.

2. Step 2: Confirm correct mode and usage

   model.eval() should be used to disable dropout and batch norm updates during prediction.

3. Final Answer:

   Using model.train() instead of model.eval() during prediction -> Option D

4. Quick Check:

   Use model.eval() for prediction, not model.train() [OK]

Hint: Always use model.eval() for deployment predictions [OK]

Common Mistakes:

• Confusing train() and eval() modes
• Thinking optimizer step is needed for prediction
• Believing torch.no_grad() is wrong during prediction

5. You want to deploy a PyTorch model to serve predictions efficiently in a web app. Which combination of steps is best practice?

hard

A. Call model.train(), enable gradients, and skip input preprocessing

B. Call model.eval(), use torch.no_grad(), and preprocess input data before prediction

C. Call model.eval(), enable gradients, and preprocess input data after prediction

D. Call model.train(), use torch.no_grad(), and preprocess input data after prediction

Solution

1. Step 1: Set model to evaluation mode

   model.eval() disables training behaviors like dropout for stable predictions.

2. Step 2: Use torch.no_grad() and preprocess input

   torch.no_grad() saves memory by disabling gradients; preprocessing input ensures correct format.

3. Final Answer:

   Call model.eval(), use torch.no_grad(), and preprocess input data before prediction -> Option B

4. Quick Check:

   Eval mode + no_grad + preprocess input = best deployment [OK]

Hint: Eval mode + no_grad + preprocess input = efficient deployment [OK]

Common Mistakes:

• Using train mode during deployment
• Enabling gradients during prediction
• Skipping input preprocessing