TorchScript for production in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of TorchScript tracing with control flow

Consider the following PyTorch model and its TorchScript tracing. What will be the output when running scripted_model(torch.tensor(3))?

PyTorch

import torch
import torch.nn as nn

class MyModel(nn.Module):
    def forward(self, x):
        if x.item() > 2:
            return x * 2
        else:
            return x + 2

model = MyModel()
scripted_model = torch.jit.trace(model, torch.tensor(1))
output = scripted_model(torch.tensor(3))
print(output.item())

A 4

B 5

C 3

D 6

💡 Hint

Tracing records operations for the example input. Think about what happens when input changes.

Tracing records the operations executed with the example input (1). Since 1 <= 2, the else branch (x + 2) is recorded. When input 3 is passed, the traced model still executes x + 2, returning 5.

❓ Model Choice

intermediate

Choosing between tracing and scripting for dynamic control flow

You have a PyTorch model with dynamic control flow depending on input values. Which TorchScript method should you use to correctly convert the model for production?

A torch.jit.trace

B torch.jit.optimize_for_inference

C torch.jit.freeze

D torch.jit.script

💡 Hint

Tracing records operations for fixed inputs, scripting analyzes code.

Tracing records operations executed for example inputs and cannot capture dynamic control flow. Scripting analyzes the model code and supports dynamic control flow, making it suitable for such models.

❓ Hyperparameter

advanced

Optimizing TorchScript model for inference speed

Which of the following options is the best practice to improve inference speed of a TorchScript model in production?

A Use torch.jit.freeze on the scripted model

B Use torch.jit.trace with multiple example inputs

C Increase batch size during training

D Add dropout layers before scripting

💡 Hint

Freezing removes unnecessary parts and optimizes the graph.

torch.jit.freeze optimizes the scripted model by removing unused attributes and enabling further graph optimizations, improving inference speed. Increasing batch size or adding dropout does not affect TorchScript inference speed. Tracing with multiple inputs is not supported.

🔧 Debug

advanced

Identifying error in TorchScript scripted model

Given this scripted model code, what error will it raise when running scripted_model(torch.tensor([1,2,3]))?

PyTorch

import torch
import torch.nn as nn

class Model(nn.Module):
    def forward(self, x):
        return x[0] + x[3]

model = Model()
scripted_model = torch.jit.script(model)
output = scripted_model(torch.tensor([1,2,3]))

A IndexError: index 3 is out of bounds for dimension 0 with size 3

B No error, output is 4

C RuntimeError: TorchScript does not support list indexing

D TypeError: unsupported operand type(s) for +: 'Tensor' and 'int'

💡 Hint

Check the tensor size and indexing carefully.

The input tensor has size 3, so index 3 is out of bounds causing IndexError. TorchScript supports tensor indexing, and the addition is valid, so other errors do not occur.

🧠 Conceptual

expert

Understanding TorchScript serialization and deployment

Which statement about TorchScript models saved with torch.jit.save and loaded with torch.jit.load is TRUE?

A The saved model cannot be used without the original Python source code

B The loaded model can only run on the same device type it was saved from

C The saved model includes both the model code and its parameters in a single file

D The saved model loses all optimizations applied during scripting

💡 Hint

Think about portability and self-containment of TorchScript files.

TorchScript saves the model code and parameters together, allowing loading and running without Python source code. The model can be loaded on different devices, and optimizations are preserved.

Practice

1. What is the main purpose of using TorchScript in PyTorch?

easy

A. To increase the size of the model for better accuracy

B. To visualize model training progress

C. To convert PyTorch models into a format optimized for production use

D. To automatically generate training data

Solution

1. Step 1: Understand TorchScript's role

   TorchScript is designed to convert PyTorch models into a form that can run faster and be deployed easily in production environments.

2. Step 2: Compare options

   Options A, B, and D describe unrelated tasks like visualization, model size increase, or data generation, which are not the purpose of TorchScript.

3. Final Answer:

   To convert PyTorch models into a format optimized for production use -> Option C

4. Quick Check:

   TorchScript purpose = convert for production [OK]

Hint: TorchScript = production-ready model format [OK]

Common Mistakes:

• Confusing TorchScript with visualization tools
• Thinking TorchScript generates data
• Assuming TorchScript increases model size

2. Which of the following is the correct way to save a TorchScript model after scripting?

easy

A. torch.save(model, 'model.pt')

B. torchscript.save_model(model, 'model.pt')

C. model.save('model.pt')

D. scripted_model.save('model.pt')

Solution

1. Step 1: Recall TorchScript saving method

   After scripting a model, the resulting scripted model object has a save() method to save it to disk.

2. Step 2: Evaluate options

   torch.save(model, 'model.pt') uses torch.save which is for regular PyTorch models, not scripted ones. model.save('model.pt') is invalid as model.save() does not exist. torchscript.save_model(model, 'model.pt') is not a valid PyTorch API.

3. Final Answer:

   scripted_model.save('model.pt') -> Option D

4. Quick Check:

   Use scripted_model.save() to save TorchScript [OK]

Hint: Use scripted_model.save() to save TorchScript models [OK]

Common Mistakes:

• Using torch.save() instead of scripted_model.save()
• Calling save() on the original model
• Assuming torchscript.save_model() exists

3. Given the code below, what will be the output printed?

import torch
class MyModule(torch.nn.Module):
    def forward(self, x):
        return x * 2

model = MyModule()
scripted = torch.jit.script(model)
print(scripted(torch.tensor(3)))

medium

A. tensor(6)

B. tensor(3)

C. 6

D. Error: scripting failed

Solution

1. Step 1: Understand the model's forward method

   The model multiplies input by 2, so input 3 becomes 6.

2. Step 2: Check scripting and output

   The model is scripted successfully, so calling scripted(torch.tensor(3)) returns tensor(6).

3. Final Answer:

   tensor(6) -> Option A

4. Quick Check:

   Input 3 * 2 = tensor(6) [OK]

Hint: Model doubles input; output = input * 2 [OK]

Common Mistakes:

• Confusing tensor(6) with integer 6
• Expecting error from scripting simple model
• Ignoring tensor wrapper in output

4. What is the error in the following code snippet when trying to trace a model?

import torch
class MyModel(torch.nn.Module):
    def forward(self, x):
        if x.sum() > 0:
            return x * 2
        else:
            return x - 2

model = MyModel()
example_input = torch.tensor([1.0, -1.0])
traced = torch.jit.trace(model, example_input)

medium

A. Syntax error in model definition

B. Tracing fails because the model has data-dependent control flow

C. example_input must be a scalar tensor

D. No error, tracing works fine

Solution

1. Step 1: Identify model control flow

   The model uses an if-statement depending on input data (x.sum() > 0), which is data-dependent control flow.

2. Step 2: Understand tracing limitation

   Tracing records operations from example input but cannot capture data-dependent branches, so it will not handle this correctly.

3. Final Answer:

   Tracing fails because the model has data-dependent control flow -> Option B

4. Quick Check:

   Tracing can't handle data-dependent control flow [OK]

Hint: Tracing fails if model has if/else based on input data [OK]

Common Mistakes:

• Assuming tracing works with all control flow
• Thinking example_input shape causes error
• Ignoring data-dependent branching

5. You want to deploy a PyTorch model with dynamic control flow and save it for production. Which approach is best to create a TorchScript model that handles this correctly?

hard

A. Use torch.jit.script() to convert the model

B. Rewrite the model to remove all control flow before tracing

C. Save the original PyTorch model with torch.save()

D. Use torch.jit.trace() with a fixed example input

Solution

1. Step 1: Identify model characteristics

   The model has dynamic control flow, meaning decisions depend on input data during execution.

2. Step 2: Choose correct TorchScript method

   torch.jit.script() analyzes the model code and supports dynamic control flow, unlike tracing which only records fixed operations.

3. Step 3: Evaluate other options

   Use torch.jit.trace() with a fixed example input (tracing) fails with dynamic control flow. Save the original PyTorch model with torch.save() saves the model but not in optimized TorchScript form. Rewrite the model to remove all control flow before tracing is impractical and changes model logic.

4. Final Answer:

   Use torch.jit.script() to convert the model -> Option A

5. Quick Check:

   Dynamic control flow needs scripting, not tracing [OK]

Hint: Use scripting for models with dynamic control flow [OK]

Common Mistakes:

• Using tracing for dynamic control flow models
• Saving without TorchScript conversion
• Trying to remove control flow instead of scripting