TorchScript export in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to convert a PyTorch model to TorchScript using tracing.

PyTorch

import torch
import torch.nn as nn

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(10, 5)

    def forward(self, x):
        return self.linear(x)

model = SimpleModel()
example_input = torch.randn(1, 10)
scripted_model = torch.jit.[1](model, example_input)

Drag options to blanks, or click blank then click option'

Atrace

Boptimize

Ccompile

Dscript

Attempts:

3 left

💡 Hint

Common Mistakes

Using torch.jit.script instead of torch.jit.trace for models with simple forward passes.

Not providing example inputs to the trace function.

Tracing a model with torch.jit.trace records the operations performed with example inputs, creating a TorchScript version.

2fill in blank

medium

Complete the code to save the TorchScript model to a file.

PyTorch

scripted_model.save([1])

Drag options to blanks, or click blank then click option'

Amodel

B'model.pt'

C'model'

Dmodel.pt

Attempts:

3 left

💡 Hint

Common Mistakes

Not using quotes around the filename string.

Using a filename without an extension.

The save method requires a string filename with quotes to save the model file.

3fill in blank

hard

Fix the error in loading a TorchScript model from a file.

PyTorch

loaded_model = torch.jit.[1]('model.pt')

Drag options to blanks, or click blank then click option'

Aload

Bscript

Ctrace

Dimport

Attempts:

3 left

💡 Hint

Common Mistakes

Using torch.jit.script or torch.jit.trace to load a model file.

Using an incorrect function name like import.

torch.jit.load loads a saved TorchScript model from a file.

4fill in blank

hard

Fill both blanks to create a TorchScript model using scripting and then save it.

PyTorch

scripted_model = torch.jit.[1](model)
scripted_model.[2]('scripted_model.pt')

Drag options to blanks, or click blank then click option'

Ascript

Bsave

Ctrace

Dload

Attempts:

3 left

💡 Hint

Common Mistakes

Using trace instead of script for models with control flow.

Using load instead of save to write the model.

torch.jit.script creates a scripted model, and save writes it to a file.

5fill in blank

hard

Fill all three blanks to load a TorchScript model, run it on input, and print the output shape.

PyTorch

loaded_model = torch.jit.[1]('scripted_model.pt')
input_tensor = torch.randn(2, 10)
output = loaded_model([2])
print(output.[3])

Drag options to blanks, or click blank then click option'

Aload

Binput_tensor

Cshape

Dscript

Attempts:

3 left

💡 Hint

Common Mistakes

Using script instead of load to load the model.

Passing wrong variable to the model call.

Printing output instead of output.shape.

Load the model with torch.jit.load, pass input_tensor to it, and print the output's shape attribute.