AOT-GAN: Optimized for Qualcomm Devices
AOT-GAN is a machine learning model that allows to erase and in-paint part of given input image.
This is based on the implementation of AOT-GAN found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.
Getting Started
There are two ways to deploy this model on your device:
Option 1: Download Pre-Exported Models
Below are pre-exported model assets ready for deployment.
| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.51, ONNX Runtime 1.30.0 | Download |
| QNN_DLC | float | Universal | QAIRT 2.51 | Download |
| TFLITE | float | Universal | QAIRT 2.51 | Download |
For more device-specific assets and performance metrics, visit AOT-GAN on Qualcomm® AI Hub.
Option 2: Export with Custom Configurations
Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations
This option is ideal if you need to customize the model beyond the default configuration provided here.
See our repository for AOT-GAN on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.image_editing
Model Stats:
- Input resolution: 512x512
- Model checkpoint: CelebAHQ
- Model size (float): 58.0 MB
- Number of parameters: 15.2M
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| AOT-GAN | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 44.083 ms | 5 - 468 MB | NPU |
| AOT-GAN | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 69.616 ms | 9 - 546 MB | NPU |
| AOT-GAN | ONNX | float | Snapdragon® X2 Elite | 47.481 ms | 8 - 8 MB | NPU |
| AOT-GAN | ONNX | float | Snapdragon® X Elite | 124.131 ms | 32 - 32 MB | NPU |
| AOT-GAN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 87.764 ms | 0 - 645 MB | NPU |
| AOT-GAN | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 180.329 ms | 1 - 579 MB | NPU |
| AOT-GAN | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 177.17 ms | 4 - 12 MB | NPU |
| AOT-GAN | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 122.604 ms | 0 - 39 MB | NPU |
| AOT-GAN | ONNX | float | Qualcomm® QCS8450 | 180.329 ms | 1 - 579 MB | NPU |
| AOT-GAN | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 162.448 ms | 4 - 11 MB | NPU |
| AOT-GAN | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 124.131 ms | 32 - 32 MB | NPU |
| AOT-GAN | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 69.616 ms | 9 - 546 MB | NPU |
| AOT-GAN | ONNX | float | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 40.401 ms | 10 - 540 MB | NPU |
| AOT-GAN | ONNX | float | Snapdragon® 8 Elite Gen 6 Mobile | 53.568 ms | 10 - 384 MB | NPU |
| AOT-GAN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 44.27 ms | 1 - 453 MB | NPU |
| AOT-GAN | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 67.121 ms | 0 - 532 MB | NPU |
| AOT-GAN | QNN_DLC | float | Snapdragon® X2 Elite | 45.704 ms | 4 - 4 MB | NPU |
| AOT-GAN | QNN_DLC | float | Snapdragon® X Elite | 120.047 ms | 4 - 4 MB | NPU |
| AOT-GAN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 85.525 ms | 3 - 649 MB | NPU |
| AOT-GAN | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 181.047 ms | 1 - 574 MB | NPU |
| AOT-GAN | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 118.317 ms | 4 - 16 MB | NPU |
| AOT-GAN | QNN_DLC | float | Qualcomm® QCS8450 | 181.047 ms | 1 - 574 MB | NPU |
| AOT-GAN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 158.373 ms | 4 - 13 MB | NPU |
| AOT-GAN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 120.047 ms | 4 - 4 MB | NPU |
| AOT-GAN | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 67.121 ms | 0 - 532 MB | NPU |
| AOT-GAN | QNN_DLC | float | Qualcomm® SA8295P | 181.962 ms | 1 - 443 MB | NPU |
| AOT-GAN | QNN_DLC | float | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 37.341 ms | 4 - 518 MB | NPU |
| AOT-GAN | QNN_DLC | float | Snapdragon® 8 Elite Gen 6 Mobile | 54.287 ms | 4 - 369 MB | NPU |
| AOT-GAN | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 44.757 ms | 2 - 467 MB | NPU |
| AOT-GAN | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 67.43 ms | 1 - 542 MB | NPU |
| AOT-GAN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 85.94 ms | 3 - 677 MB | NPU |
| AOT-GAN | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 180.687 ms | 4 - 611 MB | NPU |
| AOT-GAN | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 172.695 ms | 3 - 48 MB | NPU |
| AOT-GAN | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 117.569 ms | 3 - 6 MB | NPU |
| AOT-GAN | TFLITE | float | Qualcomm® SA8775P | 3232.104 ms | 3 - 36 MB | GPU |
| AOT-GAN | TFLITE | float | Qualcomm® SA8650P | 3232.104 ms | 3 - 36 MB | GPU |
| AOT-GAN | TFLITE | float | Qualcomm® SA8255P | 3232.104 ms | 3 - 36 MB | GPU |
| AOT-GAN | TFLITE | float | Qualcomm® QCS8450 | 180.687 ms | 4 - 611 MB | NPU |
| AOT-GAN | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 157.034 ms | 3 - 48 MB | NPU |
| AOT-GAN | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 67.43 ms | 1 - 542 MB | NPU |
| AOT-GAN | TFLITE | float | Qualcomm® SA7255P | 7498.364 ms | 1 - 34 MB | GPU |
| AOT-GAN | TFLITE | float | Qualcomm® SA8295P | 181.819 ms | 3 - 458 MB | NPU |
| AOT-GAN | TFLITE | float | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 36.125 ms | 3 - 543 MB | NPU |
| AOT-GAN | TFLITE | float | Snapdragon® 8 Elite Gen 6 Mobile | 54.303 ms | 1 - 371 MB | NPU |
License
- The license for the original implementation of AOT-GAN can be found here.
References
- Aggregated Contextual Transformations for High-Resolution Image Inpainting
- Source Model Implementation
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
