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.