v0.60.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.
- README.md +54 -52
- release_assets.json +34 -20
README.md
CHANGED
|
@@ -14,7 +14,7 @@ pipeline_tag: object-detection
|
|
| 14 |
CenterNet-2D is machine learning model that detects objects by finding their center points.
|
| 15 |
|
| 16 |
This is based on the implementation of CenterNet-2D found [here](https://github.com/xingyizhou/CenterNet).
|
| 17 |
-
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.
|
| 18 |
|
| 19 |
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.
|
| 20 |
|
|
@@ -27,81 +27,83 @@ Below are pre-exported model assets ready for deployment.
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
-
| 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/centernet_2d/releases/v0.
|
| 31 |
-
| 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/centernet_2d/releases/v0.
|
| 32 |
-
| 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/centernet_2d/releases/v0.
|
| 33 |
-
| 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/centernet_2d/releases/v0.
|
| 34 |
-
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™
|
| 35 |
-
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™
|
| 36 |
-
| PRECOMPILED_QNN_ONNX | float |
|
| 37 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite
|
| 38 |
-
|
|
| 39 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 40 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 41 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen
|
| 42 |
-
| QNN_CONTEXT_BINARY | float |
|
| 43 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 44 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™
|
| 45 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 46 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 47 |
-
| QNN_CONTEXT_BINARY | float |
|
| 48 |
-
| QNN_CONTEXT_BINARY | float |
|
|
|
|
|
|
|
| 49 |
|
| 50 |
For more device-specific assets and performance metrics, visit **[CenterNet-2D on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/centernet_2d)**.
|
| 51 |
|
| 52 |
|
| 53 |
### Option 2: Export with Custom Configurations
|
| 54 |
|
| 55 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 56 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 57 |
- Custom input shapes
|
| 58 |
- Target device and runtime configurations
|
| 59 |
|
| 60 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 61 |
|
| 62 |
-
See our repository for [CenterNet-2D on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 63 |
|
| 64 |
## Model Details
|
| 65 |
|
| 66 |
**Model Type:** Model_use_case.object_detection
|
| 67 |
|
| 68 |
**Model Stats:**
|
| 69 |
-
- Model checkpoint: ctdet_coco_dla_2x.pth
|
| 70 |
- Input resolution: 1 x 3 x 512 x 512
|
| 71 |
-
-
|
| 72 |
- Model size: 37.6 MB
|
|
|
|
| 73 |
|
| 74 |
## Performance Summary
|
| 75 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 76 |
|---|---|---|---|---|---|---
|
| 77 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite |
|
| 78 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite |
|
| 79 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile |
|
| 80 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile |
|
| 81 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) |
|
| 82 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 |
|
| 83 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 |
|
| 84 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 |
|
| 85 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 |
|
| 86 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile |
|
| 87 |
-
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile |
|
| 88 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite |
|
| 89 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite |
|
| 90 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile |
|
| 91 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile |
|
| 92 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™
|
| 93 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) |
|
| 94 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P |
|
| 95 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P |
|
| 96 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P |
|
| 97 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 |
|
| 98 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 |
|
| 99 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 |
|
| 100 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 |
|
| 101 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P |
|
| 102 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P |
|
| 103 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile |
|
| 104 |
-
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile |
|
| 105 |
|
| 106 |
## License
|
| 107 |
* The license for the original implementation of CenterNet-2D can be found
|
|
|
|
| 14 |
CenterNet-2D is machine learning model that detects objects by finding their center points.
|
| 15 |
|
| 16 |
This is based on the implementation of CenterNet-2D found [here](https://github.com/xingyizhou/CenterNet).
|
| 17 |
+
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/v0.60.0/src/qai_hub_models/models/centernet_2d) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
|
| 18 |
|
| 19 |
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.
|
| 20 |
|
|
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
|
| 31 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
|
| 32 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
|
| 33 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip)
|
| 34 |
+
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs8275.zip)
|
| 35 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
|
| 36 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
|
| 37 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 38 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
|
| 39 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
|
| 40 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
|
| 41 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
|
| 42 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip)
|
| 43 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8275.zip)
|
| 44 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
|
| 45 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8775p.zip)
|
| 46 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs9075.zip)
|
| 47 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_sa7255p.zip)
|
| 48 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8295p.zip)
|
| 49 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 50 |
+
| 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/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
|
| 51 |
|
| 52 |
For more device-specific assets and performance metrics, visit **[CenterNet-2D on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/centernet_2d)**.
|
| 53 |
|
| 54 |
|
| 55 |
### Option 2: Export with Custom Configurations
|
| 56 |
|
| 57 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/centernet_2d) Python library to compile and export the model with your own:
|
| 58 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 59 |
- Custom input shapes
|
| 60 |
- Target device and runtime configurations
|
| 61 |
|
| 62 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 63 |
|
| 64 |
+
See our repository for [CenterNet-2D on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/centernet_2d) for usage instructions.
|
| 65 |
|
| 66 |
## Model Details
|
| 67 |
|
| 68 |
**Model Type:** Model_use_case.object_detection
|
| 69 |
|
| 70 |
**Model Stats:**
|
|
|
|
| 71 |
- Input resolution: 1 x 3 x 512 x 512
|
| 72 |
+
- Model checkpoint: ctdet_coco_dla_2x.pth
|
| 73 |
- Model size: 37.6 MB
|
| 74 |
+
- Number of parameters: 20.2M
|
| 75 |
|
| 76 |
## Performance Summary
|
| 77 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 78 |
|---|---|---|---|---|---|---
|
| 79 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 160.876 ms | 36 - 36 MB | NPU
|
| 80 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 293.258 ms | 51 - 51 MB | NPU
|
| 81 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 198.466 ms | 17 - 24 MB | NPU
|
| 82 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 427.756 ms | 13 - 21 MB | NPU
|
| 83 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 305.308 ms | 1 - 54 MB | NPU
|
| 84 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 427.756 ms | 13 - 21 MB | NPU
|
| 85 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 277.744 ms | 8 - 13 MB | NPU
|
| 86 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 293.258 ms | 51 - 51 MB | NPU
|
| 87 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 172.484 ms | 13 - 19 MB | NPU
|
| 88 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 172.484 ms | 13 - 19 MB | NPU
|
| 89 |
+
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 165.84 ms | 16 - 23 MB | NPU
|
| 90 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 161.253 ms | 3 - 3 MB | NPU
|
| 91 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 295.769 ms | 3 - 3 MB | NPU
|
| 92 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 198.566 ms | 4 - 10 MB | NPU
|
| 93 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | 417.791 ms | 3 - 17 MB | NPU
|
| 94 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | 477.367 ms | 0 - 10 MB | NPU
|
| 95 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 302.824 ms | 4 - 6 MB | NPU
|
| 96 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 280.17 ms | 0 - 10 MB | NPU
|
| 97 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 280.17 ms | 0 - 10 MB | NPU
|
| 98 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 280.17 ms | 0 - 10 MB | NPU
|
| 99 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 | 417.791 ms | 3 - 17 MB | NPU
|
| 100 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 277.85 ms | 5 - 15 MB | NPU
|
| 101 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 295.769 ms | 3 - 3 MB | NPU
|
| 102 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 172.39 ms | 1 - 9 MB | NPU
|
| 103 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 477.367 ms | 0 - 10 MB | NPU
|
| 104 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 355.233 ms | 0 - 6 MB | NPU
|
| 105 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | 172.39 ms | 1 - 9 MB | NPU
|
| 106 |
+
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 165.665 ms | 2 - 11 MB | NPU
|
| 107 |
|
| 108 |
## License
|
| 109 |
* The license for the original implementation of CenterNet-2D can be found
|
release_assets.json
CHANGED
|
@@ -1,21 +1,35 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"chipset_assets": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"qualcomm-qcs8550-proxy": {
|
| 7 |
"precompiled_qnn_onnx": {
|
| 8 |
"tool_versions": {
|
| 9 |
"qairt": "2.45.0.260326154327",
|
| 10 |
"onnx_runtime": "1.27.1"
|
| 11 |
},
|
| 12 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 13 |
},
|
| 14 |
"qnn_context_binary": {
|
| 15 |
"tool_versions": {
|
| 16 |
"qairt": "2.45.0.260326154327"
|
| 17 |
},
|
| 18 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 19 |
}
|
| 20 |
},
|
| 21 |
"qualcomm-qcs9075": {
|
|
@@ -24,13 +38,13 @@
|
|
| 24 |
"qairt": "2.45.0.260326154327",
|
| 25 |
"onnx_runtime": "1.27.1"
|
| 26 |
},
|
| 27 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 28 |
},
|
| 29 |
"qnn_context_binary": {
|
| 30 |
"tool_versions": {
|
| 31 |
"qairt": "2.45.0.260326154327"
|
| 32 |
},
|
| 33 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 34 |
}
|
| 35 |
},
|
| 36 |
"qualcomm-sa7255p": {
|
|
@@ -38,7 +52,7 @@
|
|
| 38 |
"tool_versions": {
|
| 39 |
"qairt": "2.45.0.260326154327"
|
| 40 |
},
|
| 41 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"qualcomm-sa8295p": {
|
|
@@ -46,7 +60,7 @@
|
|
| 46 |
"tool_versions": {
|
| 47 |
"qairt": "2.45.0.260326154327"
|
| 48 |
},
|
| 49 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 50 |
}
|
| 51 |
},
|
| 52 |
"qualcomm-sa8775p": {
|
|
@@ -54,7 +68,7 @@
|
|
| 54 |
"tool_versions": {
|
| 55 |
"qairt": "2.45.0.260326154327"
|
| 56 |
},
|
| 57 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 58 |
}
|
| 59 |
},
|
| 60 |
"qualcomm-snapdragon-8-elite-for-galaxy": {
|
|
@@ -63,13 +77,13 @@
|
|
| 63 |
"qairt": "2.45.0.260326154327",
|
| 64 |
"onnx_runtime": "1.27.1"
|
| 65 |
},
|
| 66 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 67 |
},
|
| 68 |
"qnn_context_binary": {
|
| 69 |
"tool_versions": {
|
| 70 |
"qairt": "2.45.0.260326154327"
|
| 71 |
},
|
| 72 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 73 |
}
|
| 74 |
},
|
| 75 |
"qualcomm-snapdragon-8-elite-gen5-for-galaxy": {
|
|
@@ -78,13 +92,13 @@
|
|
| 78 |
"qairt": "2.45.0.260326154327",
|
| 79 |
"onnx_runtime": "1.27.1"
|
| 80 |
},
|
| 81 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 82 |
},
|
| 83 |
"qnn_context_binary": {
|
| 84 |
"tool_versions": {
|
| 85 |
"qairt": "2.45.0.260326154327"
|
| 86 |
},
|
| 87 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 88 |
}
|
| 89 |
},
|
| 90 |
"qualcomm-snapdragon-8gen1": {
|
|
@@ -93,13 +107,13 @@
|
|
| 93 |
"qairt": "2.45.0.260326154327",
|
| 94 |
"onnx_runtime": "1.27.1"
|
| 95 |
},
|
| 96 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 97 |
},
|
| 98 |
"qnn_context_binary": {
|
| 99 |
"tool_versions": {
|
| 100 |
"qairt": "2.45.0.260326154327"
|
| 101 |
},
|
| 102 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 103 |
}
|
| 104 |
},
|
| 105 |
"qualcomm-snapdragon-8gen3": {
|
|
@@ -108,13 +122,13 @@
|
|
| 108 |
"qairt": "2.45.0.260326154327",
|
| 109 |
"onnx_runtime": "1.27.1"
|
| 110 |
},
|
| 111 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 112 |
},
|
| 113 |
"qnn_context_binary": {
|
| 114 |
"tool_versions": {
|
| 115 |
"qairt": "2.45.0.260326154327"
|
| 116 |
},
|
| 117 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 118 |
}
|
| 119 |
},
|
| 120 |
"qualcomm-snapdragon-x-elite": {
|
|
@@ -123,13 +137,13 @@
|
|
| 123 |
"qairt": "2.45.0.260326154327",
|
| 124 |
"onnx_runtime": "1.27.1"
|
| 125 |
},
|
| 126 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 127 |
},
|
| 128 |
"qnn_context_binary": {
|
| 129 |
"tool_versions": {
|
| 130 |
"qairt": "2.45.0.260326154327"
|
| 131 |
},
|
| 132 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 133 |
}
|
| 134 |
},
|
| 135 |
"qualcomm-snapdragon-x2-elite": {
|
|
@@ -138,13 +152,13 @@
|
|
| 138 |
"qairt": "2.45.0.260326154327",
|
| 139 |
"onnx_runtime": "1.27.1"
|
| 140 |
},
|
| 141 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 142 |
},
|
| 143 |
"qnn_context_binary": {
|
| 144 |
"tool_versions": {
|
| 145 |
"qairt": "2.45.0.260326154327"
|
| 146 |
},
|
| 147 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.
|
| 148 |
}
|
| 149 |
}
|
| 150 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.60.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"chipset_assets": {
|
| 6 |
+
"qualcomm-qcs8275": {
|
| 7 |
+
"precompiled_qnn_onnx": {
|
| 8 |
+
"tool_versions": {
|
| 9 |
+
"qairt": "2.45.0.260326154327"
|
| 10 |
+
},
|
| 11 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs8275.zip"
|
| 12 |
+
},
|
| 13 |
+
"qnn_context_binary": {
|
| 14 |
+
"tool_versions": {
|
| 15 |
+
"qairt": "2.45.0.260326154327"
|
| 16 |
+
},
|
| 17 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8275.zip"
|
| 18 |
+
}
|
| 19 |
+
},
|
| 20 |
"qualcomm-qcs8550-proxy": {
|
| 21 |
"precompiled_qnn_onnx": {
|
| 22 |
"tool_versions": {
|
| 23 |
"qairt": "2.45.0.260326154327",
|
| 24 |
"onnx_runtime": "1.27.1"
|
| 25 |
},
|
| 26 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip"
|
| 27 |
},
|
| 28 |
"qnn_context_binary": {
|
| 29 |
"tool_versions": {
|
| 30 |
"qairt": "2.45.0.260326154327"
|
| 31 |
},
|
| 32 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip"
|
| 33 |
}
|
| 34 |
},
|
| 35 |
"qualcomm-qcs9075": {
|
|
|
|
| 38 |
"qairt": "2.45.0.260326154327",
|
| 39 |
"onnx_runtime": "1.27.1"
|
| 40 |
},
|
| 41 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip"
|
| 42 |
},
|
| 43 |
"qnn_context_binary": {
|
| 44 |
"tool_versions": {
|
| 45 |
"qairt": "2.45.0.260326154327"
|
| 46 |
},
|
| 47 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs9075.zip"
|
| 48 |
}
|
| 49 |
},
|
| 50 |
"qualcomm-sa7255p": {
|
|
|
|
| 52 |
"tool_versions": {
|
| 53 |
"qairt": "2.45.0.260326154327"
|
| 54 |
},
|
| 55 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_sa7255p.zip"
|
| 56 |
}
|
| 57 |
},
|
| 58 |
"qualcomm-sa8295p": {
|
|
|
|
| 60 |
"tool_versions": {
|
| 61 |
"qairt": "2.45.0.260326154327"
|
| 62 |
},
|
| 63 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8295p.zip"
|
| 64 |
}
|
| 65 |
},
|
| 66 |
"qualcomm-sa8775p": {
|
|
|
|
| 68 |
"tool_versions": {
|
| 69 |
"qairt": "2.45.0.260326154327"
|
| 70 |
},
|
| 71 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8775p.zip"
|
| 72 |
}
|
| 73 |
},
|
| 74 |
"qualcomm-snapdragon-8-elite-for-galaxy": {
|
|
|
|
| 77 |
"qairt": "2.45.0.260326154327",
|
| 78 |
"onnx_runtime": "1.27.1"
|
| 79 |
},
|
| 80 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
|
| 81 |
},
|
| 82 |
"qnn_context_binary": {
|
| 83 |
"tool_versions": {
|
| 84 |
"qairt": "2.45.0.260326154327"
|
| 85 |
},
|
| 86 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
|
| 87 |
}
|
| 88 |
},
|
| 89 |
"qualcomm-snapdragon-8-elite-gen5-for-galaxy": {
|
|
|
|
| 92 |
"qairt": "2.45.0.260326154327",
|
| 93 |
"onnx_runtime": "1.27.1"
|
| 94 |
},
|
| 95 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
|
| 96 |
},
|
| 97 |
"qnn_context_binary": {
|
| 98 |
"tool_versions": {
|
| 99 |
"qairt": "2.45.0.260326154327"
|
| 100 |
},
|
| 101 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
|
| 102 |
}
|
| 103 |
},
|
| 104 |
"qualcomm-snapdragon-8gen1": {
|
|
|
|
| 107 |
"qairt": "2.45.0.260326154327",
|
| 108 |
"onnx_runtime": "1.27.1"
|
| 109 |
},
|
| 110 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip"
|
| 111 |
},
|
| 112 |
"qnn_context_binary": {
|
| 113 |
"tool_versions": {
|
| 114 |
"qairt": "2.45.0.260326154327"
|
| 115 |
},
|
| 116 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip"
|
| 117 |
}
|
| 118 |
},
|
| 119 |
"qualcomm-snapdragon-8gen3": {
|
|
|
|
| 122 |
"qairt": "2.45.0.260326154327",
|
| 123 |
"onnx_runtime": "1.27.1"
|
| 124 |
},
|
| 125 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip"
|
| 126 |
},
|
| 127 |
"qnn_context_binary": {
|
| 128 |
"tool_versions": {
|
| 129 |
"qairt": "2.45.0.260326154327"
|
| 130 |
},
|
| 131 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip"
|
| 132 |
}
|
| 133 |
},
|
| 134 |
"qualcomm-snapdragon-x-elite": {
|
|
|
|
| 137 |
"qairt": "2.45.0.260326154327",
|
| 138 |
"onnx_runtime": "1.27.1"
|
| 139 |
},
|
| 140 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip"
|
| 141 |
},
|
| 142 |
"qnn_context_binary": {
|
| 143 |
"tool_versions": {
|
| 144 |
"qairt": "2.45.0.260326154327"
|
| 145 |
},
|
| 146 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip"
|
| 147 |
}
|
| 148 |
},
|
| 149 |
"qualcomm-snapdragon-x2-elite": {
|
|
|
|
| 152 |
"qairt": "2.45.0.260326154327",
|
| 153 |
"onnx_runtime": "1.27.1"
|
| 154 |
},
|
| 155 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip"
|
| 156 |
},
|
| 157 |
"qnn_context_binary": {
|
| 158 |
"tool_versions": {
|
| 159 |
"qairt": "2.45.0.260326154327"
|
| 160 |
},
|
| 161 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.60.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip"
|
| 162 |
}
|
| 163 |
}
|
| 164 |
}
|