ONNX export in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to export a PyTorch model to ONNX format.

PyTorch

import torch
import torch.nn as nn

model = nn.Linear(10, 5)
dummy_input = torch.randn(1, 10)
torch.onnx.export(model, dummy_input, [1])

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

A"model.onnx"

Bmodel.onnx

Cdummy_input

Dtorch.onnx

Attempts:

3 left

💡 Hint

Common Mistakes

Not providing the file path as a string.

Passing the model or dummy input as the file path.

The second argument to torch.onnx.export is the dummy input, and the third argument is the file path as a string where the ONNX model will be saved.

2fill in blank

medium

Complete the code to specify the input names when exporting to ONNX.

PyTorch

torch.onnx.export(model, dummy_input, "model.onnx", input_names=[[1]])

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

Ainput1

B["input1"]

C"input1"

D'input1'

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the input name without quotes.

Passing a list inside the blank when brackets are already present.

The input_names argument expects a list of strings. Since the list brackets are already in the code, just provide the string name with quotes.

3fill in blank

hard

Fix the error in the code to export the model with dynamic axes for variable batch size.

PyTorch

torch.onnx.export(model, dummy_input, "model.onnx", dynamic_axes={"input": [1])

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

A{"batch_size": "0"}

B{"0": "batch_size"}

C{"batch_size": 0}

D{"0": 0}

Attempts:

3 left

💡 Hint

Common Mistakes

Using integers instead of strings as keys.

Swapping keys and values in the dictionary.

The dynamic_axes argument expects a dictionary mapping input names to dictionaries that map axis indices (as strings) to axis names.

4fill in blank

hard

Fill both blanks to export the model with verbose output and specifying output names.

PyTorch

torch.onnx.export(model, dummy_input, "model.onnx", verbose=[1], output_names=[[2]])

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

ATrue

BFalse

C"output1"

Doutput1

Attempts:

3 left

💡 Hint

Common Mistakes

Passing output names without quotes.

Passing verbose as a string instead of boolean.

verbose expects a boolean value, so True or False. output_names expects a list of strings, so the string name with quotes is correct.

5fill in blank

hard

Fill all three blanks to export the model with opset version 11, enable constant folding, and set training mode to evaluation.

PyTorch

torch.onnx.export(model, dummy_input, "model.onnx", opset_version=[1], do_constant_folding=[2], training=[3])

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

A10

B11

CTrue

DFalse

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong opset version.

Not enabling constant folding.

Setting training to True instead of evaluation mode.

opset_version should be 11 for compatibility, do_constant_folding is a boolean to optimize constants, and training should be set to torch.onnx.TrainingMode.EVAL which is represented here as False for no training.