| --- |
| library_name: pytorch |
| license: other |
| tags: |
| - android |
| pipeline_tag: image-segmentation |
|
|
| --- |
| |
|  |
|
|
| # Mask2Former: Optimized for Qualcomm Devices |
|
|
| Mask2Former is a machine learning model that predicts masks and classes of objects in an image. |
|
|
| This is based on the implementation of Mask2Former found [here](https://github.com/huggingface/transformers/tree/main/src/transformers/models/mask2former). |
| This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/mask2former) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). |
|
|
| Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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 | |
| |---|---|---|---|---| |
| | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip) |
| | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip) |
| | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip) |
| | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip) |
| | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip) |
| | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip) |
| | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip) |
| | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip) |
| | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip) |
| | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip) |
| | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip) |
| | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip) |
| | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip) |
| | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_sa8775p.zip) |
| | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_qcs9075.zip) |
| | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_sa7255p.zip) |
| | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_sa8295p.zip) |
| | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip) |
| | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.59.0/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip) |
|
|
| For more device-specific assets and performance metrics, visit **[Mask2Former on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mask2former)**. |
|
|
|
|
| ### Option 2: Export with Custom Configurations |
|
|
| Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/mask2former) 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 [Mask2Former on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/mask2former) for usage instructions. |
|
|
| ## Model Details |
|
|
| **Model Type:** Model_use_case.semantic_segmentation |
| |
| **Model Stats:** |
| - Model checkpoint: facebook/mask2former-swin-tiny-coco-panoptic |
| - Input resolution: 384x384 |
| - Number of output classes: 100 |
| |
| ## Performance Summary |
| | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
| |---|---|---|---|---|---|--- |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 67.94 ms | 9 - 9 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 142.293 ms | 109 - 109 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 104.618 ms | 9 - 22 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 234.001 ms | 9 - 23 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 142.039 ms | 0 - 112 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 234.001 ms | 9 - 23 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 201.948 ms | 7 - 12 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 142.293 ms | 109 - 109 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 89.094 ms | 10 - 20 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 89.094 ms | 10 - 20 MB | NPU |
| | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 70.678 ms | 9 - 21 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 68.148 ms | 2 - 2 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 142.765 ms | 2 - 2 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 104.6 ms | 4 - 11 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | 233.681 ms | 1 - 10 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8275 | 289.752 ms | 2 - 11 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 141.664 ms | 2 - 4 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 147.41 ms | 2 - 11 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 147.41 ms | 2 - 11 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 147.41 ms | 2 - 11 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 | 233.681 ms | 1 - 10 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 146.388 ms | 4 - 10 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 142.765 ms | 2 - 2 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 88.976 ms | 2 - 14 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 289.752 ms | 2 - 11 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 182.756 ms | 2 - 7 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | 88.976 ms | 2 - 14 MB | NPU |
| | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 70.882 ms | 2 - 12 MB | NPU |
| |
| ## License |
| * The license for the original implementation of Mask2Former can be found |
| [here](https://github.com/huggingface/transformers/blob/main/LICENSE). |
| |
| ## References |
| * [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) |
| * [Source Model Implementation](https://github.com/huggingface/transformers/tree/main/src/transformers/models/mask2former) |
| |
| ## Community |
| * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. |
| * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com). |
| |
