--- library_name: pytorch license: other tags: - android pipeline_tag: image-segmentation --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/web-assets/model_demo.png) # 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/main/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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip) | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/mask2former-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip) | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/mask2former-precompiled_qnn_onnx-float-qualcomm_qcs9075.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/v0.56.0/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/v0.56.0/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/v0.56.0/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/v0.56.0/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/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/v0.56.0/mask2former-qnn_context_binary-float-qualcomm_sa8775p.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/v0.56.0/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/v0.56.0/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.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/v0.56.0/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/v0.56.0/mask2former-qnn_context_binary-float-qualcomm_sa8295p.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mask2former/releases/v0.56.0/mask2former-qnn_context_binary-float-qualcomm_qcs9075.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/main/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/main/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 | 67.968 ms | 10 - 10 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 142.678 ms | 109 - 109 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 104.58 ms | 12 - 19 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 234.545 ms | 9 - 23 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 141.063 ms | 0 - 113 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 234.545 ms | 9 - 23 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 70.63 ms | 9 - 21 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 147.549 ms | 7 - 12 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 88.646 ms | 10 - 18 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8750 | 88.646 ms | 10 - 18 MB | NPU | Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS7181 | 142.678 ms | 109 - 109 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 68.019 ms | 2 - 2 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 142.573 ms | 2 - 2 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 104.711 ms | 4 - 11 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | 239.722 ms | 2 - 11 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 | 289.576 ms | 2 - 10 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 141.748 ms | 2 - 4 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 | 239.722 ms | 2 - 11 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 70.644 ms | 2 - 11 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 289.576 ms | 2 - 10 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 146.653 ms | 2 - 8 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | 88.654 ms | 2 - 11 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 180.889 ms | 2 - 8 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8750 | 88.654 ms | 2 - 11 MB | NPU | Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® QCS7181 | 142.573 ms | 2 - 2 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).