Model packaging (.mar files) in PyTorch

Introduction

Model packaging into .mar files helps you bundle your PyTorch model and its code so it can be easily shared and deployed.

You want to deploy a PyTorch model as a web service.

You need to share your trained model with others in a ready-to-use format.

You want to use TorchServe to serve your model for predictions.

You want to keep your model and its code together for easy version control.

Syntax

PyTorch

torch-model-archiver --model-name <model_name> --version <version> --serialized-file <model_file> --handler <handler_file> --extra-files <extra_files> --export-path <export_path>

Replace placeholders like <model_name> with your actual model name.

The --handler is a Python script or a built-in handler that defines how to load and run your model.

Examples

This packages a ResNet18 model saved in resnet18.pt using the built-in image_classifier handler and saves the .mar file in model_store.

PyTorch

torch-model-archiver --model-name resnet18 --version 1.0 --serialized-file resnet18.pt --handler image_classifier --export-path model_store

This packages a custom model with a custom handler and an extra JSON file needed for predictions.

PyTorch

torch-model-archiver --model-name mymodel --version 2.0 --serialized-file model.pt --handler my_handler.py --extra-files index_to_name.json --export-path model_store

Sample Model

This example saves a pretrained ResNet18 model and shows the command to package it into a .mar file for TorchServe deployment.

PyTorch

import torch
from torchvision import models

# Step 1: Save a pretrained model
model = models.resnet18(pretrained=True)
model.eval()

# Save the model as TorchScript for TorchServe
example_input = torch.randn(1, 3, 224, 224)
traced_model = torch.jit.trace(model, example_input)
traced_model.save('resnet18.pt')

# Step 2: Use torch-model-archiver command (run in terminal, not Python)
# torch-model-archiver --model-name resnet18 --version 1.0 --serialized-file resnet18.pt --handler image_classifier --export-path model_store

# Step 3: After packaging, you get resnet18.mar in model_store folder

print('Model saved as resnet18.pt')
print('Run torch-model-archiver command in terminal to create .mar file')

Important Notes

The torch-model-archiver tool is a command-line utility, so you run it outside Python in your terminal.

Make sure to install TorchServe and torch-model-archiver via pip before packaging.

The .mar file contains your model and code, making deployment easier and consistent.

Summary

Packaging models into .mar files bundles model and code for easy deployment.

Use torch-model-archiver command with model file and handler script.

.mar files are used by TorchServe to serve models as APIs.

Practice

1. What is the main purpose of packaging a PyTorch model into a .mar file?

easy

A. To visualize the model architecture

B. To convert the model into a different training format

C. To compress the model for storage only

D. To bundle the model and code for easy deployment with TorchServe

Solution

1. Step 1: Understand what a .mar file contains

   A .mar file bundles the trained model and the handler code needed to serve it.

2. Step 2: Identify the use case of .mar files

   These files are used by TorchServe to deploy models as APIs easily.

3. Final Answer:

   To bundle the model and code for easy deployment with TorchServe -> Option D

4. Quick Check:

   Model packaging = deployment bundle [OK]

Hint: Think deployment: .mar bundles model + code [OK]

Common Mistakes:

• Confusing .mar with just compression
• Thinking .mar changes training format
• Assuming .mar is for visualization

2. Which command correctly creates a .mar file using torch-model-archiver?

easy

A. torch-model-archiver --model-name mymodel --model-file model.pth --handler handler.py --export-path model_store

B. torch-model-archiver --model-name mymodel --model-file model.pth --handler handler.txt --export-path model_store

C. torch-model-archiver --model-name mymodel --model-file model.txt --handler handler.py --export-path model_store

D. torch-model-archiver --model-name mymodel --model-file model.py --handler handler.py --export-path model_store

Solution

1. Step 1: Identify correct model file type

   The model file should be a PyTorch model file like .pth, not a Python script or text file.

2. Step 2: Confirm handler file type

   The handler must be a Python script .py, not a text file.

3. Final Answer:

   torch-model-archiver --model-name mymodel --model-file model.pth --handler handler.py --export-path model_store -> Option A

4. Quick Check:

   Model file = .pth, handler = .py [OK]

Hint: Model file is .pth, handler is .py script [OK]

Common Mistakes:

• Using .py file as model file
• Using .txt as handler file
• Mixing file extensions incorrectly

3. Given this command:

torch-model-archiver --model-name resnet --model-file resnet.pth --handler image_classifier.py --export-path model_store

What will be the output?

medium

A. A Python script named resnet.py created

B. An error because resnet.pth is not a valid model file

C. A file named resnet.mar created in model_store directory

D. A folder named resnet.mar created

Solution

1. Step 1: Understand torch-model-archiver output

   The command packages the model and handler into a single .mar file.

2. Step 2: Check output location and file name

   The .mar file is named after the model name and saved in the export path.

3. Final Answer:

   A file named resnet.mar created in model_store directory -> Option C

4. Quick Check:

   .mar file = model + handler bundle [OK]

Hint: Output is a .mar file named after model [OK]

Common Mistakes:

• Expecting a Python script output
• Thinking .mar is a folder
• Assuming error due to .pth file

4. You ran this command:

torch-model-archiver --model-name mymodel --model-file model.pth --handler handler.py --export-path model_store

But got an error: Handler file not found. What is the likely cause?

medium

A. The handler.py file is missing or path is incorrect

B. The model.pth file is corrupted

C. The export path model_store does not exist

D. The model name contains invalid characters

Solution

1. Step 1: Analyze the error message

   The error says handler file not found, so the problem is with the handler.py file location or name.

2. Step 2: Check other options

   Model file corruption or export path issues would cause different errors, not handler missing.

3. Final Answer:

   The handler.py file is missing or path is incorrect -> Option A

4. Quick Check:

   Error message = handler file missing [OK]

Hint: Check handler file path if 'Handler file not found' error occurs [OK]

Common Mistakes:

• Blaming model file for handler error
• Ignoring file path correctness
• Assuming export path causes handler error

5. You want to package two different PyTorch models with custom handlers into .mar files for TorchServe. Which approach correctly packages both models for deployment?

hard

A. Package one model as .mar and copy the second model file into the model_store folder without packaging

B. Run torch-model-archiver twice, each time with the respective model file, handler, and unique model name, exporting to the same model_store folder

C. Combine both models into one .pth file and use a single handler to package once

D. Use torch-model-archiver once with both model files and handlers listed separated by commas

Solution

1. Step 1: Understand packaging multiple models

   Each model requires its own .mar file with its specific handler and unique model name.

2. Step 2: Confirm correct packaging method

   Running torch-model-archiver twice with different parameters and exporting to the same folder is the correct way.

3. Final Answer:

   Run torch-model-archiver twice, each time with the respective model file, handler, and unique model name, exporting to the same model_store folder -> Option B

4. Quick Check:

   One .mar per model + handler [OK]

Hint: Package each model separately with unique names [OK]

Common Mistakes:

• Trying to combine models in one .mar file
• Copying model files without packaging
• Passing multiple files in one command