ONNX Runtime in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load an ONNX model using ONNX Runtime.

Computer Vision

import onnxruntime as ort

session = ort.InferenceSession([1])

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

A"model.onnx"

Bmodel.onnx

Cload_model("model.onnx")

Donnx.load("model.onnx")

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the model filename without quotes causes a NameError.

Trying to use onnx.load instead of passing the file path.

The InferenceSession expects the model file path as a string.

2fill in blank

medium

Complete the code to prepare input data for ONNX Runtime inference.

Computer Vision

import numpy as np

input_name = session.get_inputs()[0].name
input_data = np.random.rand(1, 3, 224, 224).astype([1])

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

A"int32"

B"float64"

C"uint8"

D"float32"

Attempts:

3 left

💡 Hint

Common Mistakes

Using float64 causes type mismatch errors.

Using integer types when the model expects floats.

ONNX models usually expect input data as 32-bit floats (float32).

3fill in blank

hard

Fix the error in the code to run inference and get the output.

Computer Vision

outputs = session.run(None, [1])
print(outputs[0])

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

A(input_name, input_data)

B{input_name: input_data}

Cinput_data

D[input_name, input_data]

Attempts:

3 left

💡 Hint

Common Mistakes

Passing inputs as a list or tuple causes runtime errors.

Passing only the input data without the input name.

The run method expects a dictionary mapping input names to input data.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps input names to numpy arrays.

Computer Vision

inputs = { [1]: np.array(value) for [2], value in input_data.items() }

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

Aname

Bkey

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variable names for the key and the iteration variable.

Not using a colon between key and value.

Dictionary comprehension syntax: {key: value for key, value in dict.items()}.

5fill in blank

hard

Fill all three blanks to extract output names, run inference, and print the first output.

Computer Vision

output_names = [output.name for output in session.get_outputs()]
results = session.run([1], [2])
print(results[3])

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

Aoutput_names

B{input_name: input_data}

C[0]

Dinput_data

Attempts:

3 left

💡 Hint

Common Mistakes

Passing inputs as a list instead of a dictionary.

Not specifying output names in the run method.

Trying to print results without indexing.

Use output_names to specify outputs, input dictionary for inputs, and index [0] to print first output.