ONNX export in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

ONNX export output shape verification

Consider the following PyTorch model and ONNX export code. What will be the shape of the output tensor when running the ONNX model with the given input shape?

PyTorch

import torch
import torch.nn as nn
import onnx

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()
model.eval()
x = torch.randn(3, 10)

# Export to ONNX
onnx_path = "simple_model.onnx"
torch.onnx.export(model, x, onnx_path, input_names=["input"], output_names=["output"], opset_version=11)

# Assume we load and run the ONNX model with input shape (3, 10)
# What is the shape of the output tensor?

A (3, 5)

B (10, 5)

C (3, 10)

D (5, 3)

💡 Hint

Think about how the linear layer transforms the input shape.

The linear layer transforms input of shape (batch_size, 10) to (batch_size, 5). Since input batch size is 3, output shape is (3, 5).

❓ Model Choice

intermediate

Choosing correct opset version for ONNX export

You want to export a PyTorch model using torch.onnx.export. Which opset_version should you choose to ensure compatibility with most ONNX runtimes and support for common operators?

A opset_version=7

B opset_version=11

C opset_version=15

D opset_version=9

💡 Hint

Check the default recommended opset version in PyTorch documentation.

PyTorch recommends opset_version=11 for broad compatibility and support of common operators.

🔧 Debug

advanced

ONNX export error due to dynamic axes

You try to export a PyTorch model to ONNX with dynamic batch size using this code: torch.onnx.export(model, x, "model.onnx", dynamic_axes={"input": {0: "batch_size"}}) But you get an error about missing output dynamic axes. What is the most likely cause?

A You must specify dynamic axes for both input and output tensors.

B The model does not support dynamic batch size.

C You forgot to set opset_version=15.

D You need to convert the model to eval mode before export.

💡 Hint

Dynamic axes must be declared for all tensors that vary in size.

When using dynamic axes, you must specify them for both inputs and outputs if their batch size varies.

❓ Metrics

advanced

Verifying ONNX model correctness with output comparison

After exporting a PyTorch model to ONNX, you want to verify the ONNX model produces the same output as the PyTorch model for the same input. Which metric is best to check this?

A Cross-entropy loss between PyTorch and ONNX outputs

B Accuracy score between PyTorch and ONNX outputs

C Mean squared error (MSE) between PyTorch and ONNX outputs

D Confusion matrix of PyTorch and ONNX outputs

💡 Hint

You want to measure numerical closeness of outputs.

MSE measures the average squared difference between outputs, suitable for regression outputs comparison.

🧠 Conceptual

expert

Understanding ONNX export limitations with control flow

Which of the following statements about exporting PyTorch models with control flow (like loops or conditionals) to ONNX is TRUE?

A Control flow must be removed from the model before exporting to ONNX.

B ONNX export can handle control flow only if it is traced, not scripted.

C ONNX supports all Python control flow constructs natively during export.

D ONNX supports control flow if the model is scripted with torch.jit.script before export.

💡 Hint

Think about how PyTorch JIT scripting helps ONNX export.

ONNX supports control flow when exporting scripted models, as scripting preserves control flow structure.

Practice

1. What is the main purpose of exporting a PyTorch model to ONNX format?

easy

A. To save the model in a universal format for sharing and deployment

B. To train the model faster on GPUs

C. To convert the model into a TensorFlow model automatically

D. To visualize the model architecture in PyTorch

Solution

1. Step 1: Understand ONNX export purpose

   ONNX is designed to save models in a format that can be used across different frameworks and platforms.

2. Step 2: Compare options

   Only To save the model in a universal format for sharing and deployment correctly describes the universal sharing and deployment purpose of ONNX export.

3. Final Answer:

   To save the model in a universal format for sharing and deployment -> Option A

4. Quick Check:

   ONNX export = universal format [OK]

Hint: ONNX = share and deploy models universally [OK]

Common Mistakes:

• Confusing ONNX export with training speedup
• Thinking ONNX converts models to TensorFlow automatically
• Assuming ONNX export is for visualization only

2. Which of the following is the correct way to prepare a PyTorch model for ONNX export?

easy

A. Call model.train() before export

B. Export without setting any input

C. Use a dummy input tensor matching the model input shape

D. Use model.eval() after export

Solution

1. Step 1: Identify preparation steps for ONNX export

   Model should be in evaluation mode and a dummy input tensor matching input shape is needed for tracing.

2. Step 2: Evaluate options

   Use a dummy input tensor matching the model input shape correctly states the use of a dummy input tensor. Call model.train() before export is wrong because model.train() is for training mode. Export without setting any input misses input, and Use model.eval() after export is incorrect order.

3. Final Answer:

   Use a dummy input tensor matching the model input shape -> Option C

4. Quick Check:

   Dummy input needed = Use a dummy input tensor matching the model input shape [OK]

Hint: Always use dummy input tensor before export [OK]

Common Mistakes:

• Forgetting to set model.eval() before export
• Not providing dummy input tensor
• Calling model.train() instead of eval()

3. Given the code below, what will be the output of print(onnx_model.graph.input[0].name) after export?

import torch
import torch.nn as nn

class SimpleModel(nn.Module):
    def forward(self, x):
        return x * 2

model = SimpleModel()
model.eval()
dummy_input = torch.randn(1, 3)
torch.onnx.export(model, dummy_input, "model.onnx", input_names=["input_tensor"])
import onnx
onnx_model = onnx.load("model.onnx")
print(onnx_model.graph.input[0].name)

medium

A. x

B. input_tensor

C. input0

D. data

Solution

1. Step 1: Check input_names parameter in export

   The export call sets input_names=["input_tensor"], so the input name in ONNX graph should be "input_tensor".

2. Step 2: Confirm printed input name

   Loading the ONNX model and printing the first input name will output "input_tensor" as set.

3. Final Answer:

   input_tensor -> Option B

4. Quick Check:

   input_names param = input_tensor [OK]

Hint: input_names param sets ONNX input name [OK]

Common Mistakes:

• Assuming default input name like 'input0'
• Confusing PyTorch variable name with ONNX input name
• Not setting input_names and expecting custom name

4. You try to export a PyTorch model to ONNX but get an error: RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same. What is the best fix?

medium

A. Export without specifying input_names

B. Use model.train() instead of model.eval()

C. Remove dummy input tensor

D. Move both the model and the dummy input to CPU before export

Solution

1. Step 1: Understand the error cause

   The error means model weights are on CPU but input tensor is on GPU (cuda), causing type mismatch.

2. Step 2: Fix by aligning device

   Moving both the model and the dummy input to CPU ensures both are on the same device (CPU), fixing the mismatch.

3. Final Answer:

   Move both the model and the dummy input to CPU before export -> Option D

4. Quick Check:

   Device mismatch fix = move model and input to CPU [OK]

Hint: Ensure model and input are on same device before export [OK]

Common Mistakes:

• Ignoring device mismatch and exporting anyway
• Switching to train mode instead of fixing device
• Removing dummy input tensor causing other errors

5. You want to export a PyTorch model to ONNX with dynamic batch size support. Which argument should you add to torch.onnx.export to enable this?

hard

A. dynamic_axes={'input': {0: 'batch_size'}, 'output': {0: 'batch_size'}}

B. enable_dynamic_batch=True

C. set_dynamic=True

D. dynamic_batch=True

Solution

1. Step 1: Identify how to specify dynamic axes in ONNX export

   PyTorch ONNX export uses the dynamic_axes argument to mark dimensions as dynamic, e.g., batch size dimension 0.

2. Step 2: Check options for dynamic batch size

   Only dynamic_axes={'input': {0: 'batch_size'}, 'output': {0: 'batch_size'}} correctly uses dynamic_axes with dictionary specifying batch dimension 0 for input and output.

3. Final Answer:

   dynamic_axes={'input': {0: 'batch_size'}, 'output': {0: 'batch_size'}} -> Option A

4. Quick Check:

   Dynamic batch size = dynamic_axes param [OK]

Hint: Use dynamic_axes dict to set dynamic batch size [OK]

Common Mistakes:

• Using nonexistent parameters like enable_dynamic_batch
• Forgetting to specify dynamic axes for output
• Assuming batch size is dynamic by default