v0.49.1
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.
README.md
CHANGED
|
@@ -14,7 +14,7 @@ pipeline_tag: other
|
|
| 14 |
BeVFusion is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle.
|
| 15 |
|
| 16 |
This is based on the implementation of BEVFusion found [here](https://github.com/mit-han-lab/bevfusion).
|
| 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/
|
| 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 |
|
|
@@ -27,32 +27,31 @@ Below are pre-exported model assets ready for deployment.
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 31 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 32 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 33 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8
|
| 34 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite
|
| 35 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 36 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 37 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 38 |
-
| QNN_CONTEXT_BINARY | float |
|
| 39 |
-
| QNN_CONTEXT_BINARY | float |
|
| 40 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite
|
| 41 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.48.0/bevfusion_det-qnn_context_binary-float-qualcomm_sa7255p.zip)
|
| 42 |
|
| 43 |
For more device-specific assets and performance metrics, visit **[BEVFusion on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/bevfusion_det)**.
|
| 44 |
|
| 45 |
|
| 46 |
### Option 2: Export with Custom Configurations
|
| 47 |
|
| 48 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/
|
| 49 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 50 |
- Custom input shapes
|
| 51 |
- Target device and runtime configurations
|
| 52 |
|
| 53 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 54 |
|
| 55 |
-
See our repository for [BEVFusion on GitHub](https://github.com/qualcomm/ai-hub-models/
|
| 56 |
|
| 57 |
## Model Details
|
| 58 |
|
|
@@ -67,61 +66,56 @@ See our repository for [BEVFusion on GitHub](https://github.com/qualcomm/ai-hub-
|
|
| 67 |
## Performance Summary
|
| 68 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 69 |
|---|---|---|---|---|---|---
|
| 70 |
-
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 71 |
-
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 72 |
-
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 73 |
-
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8
|
| 74 |
-
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite
|
| 75 |
-
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 76 |
-
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 77 |
-
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 78 |
-
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float |
|
| 79 |
-
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.
|
| 80 |
-
|
|
| 81 |
-
| BEVFusionEncoder1 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 381.
|
| 82 |
-
| BEVFusionEncoder1 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite |
|
| 83 |
-
| BEVFusionEncoder1 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile |
|
| 84 |
-
| BEVFusionEncoder1 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile |
|
| 85 |
-
| BEVFusionEncoder1 |
|
| 86 |
-
| BEVFusionEncoder1 | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite |
|
| 87 |
-
| BEVFusionEncoder1 | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite |
|
| 88 |
-
| BEVFusionEncoder1 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile |
|
| 89 |
-
| BEVFusionEncoder1 | QNN_CONTEXT_BINARY | float |
|
| 90 |
-
|
|
| 91 |
-
|
|
| 92 |
-
| BEVFusionEncoder2 | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 93 |
-
| BEVFusionEncoder2 | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 94 |
-
| BEVFusionEncoder2 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8
|
| 95 |
-
| BEVFusionEncoder2 |
|
| 96 |
-
| BEVFusionEncoder2 |
|
| 97 |
-
| BEVFusionEncoder2 | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 98 |
-
| BEVFusionEncoder2 | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 99 |
-
| BEVFusionEncoder2 | QNN_CONTEXT_BINARY | float | Snapdragon® 8
|
| 100 |
-
|
|
| 101 |
-
|
|
| 102 |
-
|
|
| 103 |
-
| BEVFusionEncoder3 | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 104 |
-
| BEVFusionEncoder3 | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 105 |
-
| BEVFusionEncoder3 |
|
| 106 |
-
| BEVFusionEncoder3 |
|
| 107 |
-
| BEVFusionEncoder3 |
|
| 108 |
-
| BEVFusionEncoder3 | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 109 |
-
| BEVFusionEncoder3 | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 110 |
-
|
|
| 111 |
-
|
|
| 112 |
-
|
|
| 113 |
-
|
|
| 114 |
-
| BEVFusionEncoder4 | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 115 |
-
| BEVFusionEncoder4 |
|
| 116 |
-
| BEVFusionEncoder4 |
|
| 117 |
-
| BEVFusionEncoder4 |
|
| 118 |
-
| BEVFusionEncoder4 |
|
| 119 |
-
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 120 |
-
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 12.05 ms | 19 - 19 MB | NPU
|
| 121 |
-
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 9.156 ms | 19 - 26 MB | NPU
|
| 122 |
-
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 25.214 ms | 18 - 26 MB | NPU
|
| 123 |
-
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.846 ms | 18 - 27 MB | NPU
|
| 124 |
-
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.809 ms | 18 - 28 MB | NPU
|
| 125 |
|
| 126 |
## License
|
| 127 |
* The license for the original implementation of BEVFusion can be found
|
|
|
|
| 14 |
BeVFusion is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle.
|
| 15 |
|
| 16 |
This is based on the implementation of BEVFusion found [here](https://github.com/mit-han-lab/bevfusion).
|
| 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/tree/v0.49.1/qai_hub_models/models/bevfusion_det) 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® 8 Elite Gen 5 Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip)
|
| 31 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
|
| 32 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
|
| 33 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
|
| 34 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 35 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.zip)
|
| 36 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
|
| 37 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
|
| 38 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
|
| 39 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-qnn_context_binary-float-qualcomm_sa8775p.zip)
|
| 40 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/bevfusion_det/releases/v0.49.1/bevfusion_det-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
|
|
|
| 41 |
|
| 42 |
For more device-specific assets and performance metrics, visit **[BEVFusion on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/bevfusion_det)**.
|
| 43 |
|
| 44 |
|
| 45 |
### Option 2: Export with Custom Configurations
|
| 46 |
|
| 47 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/bevfusion_det) Python library to compile and export the model with your own:
|
| 48 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 49 |
- Custom input shapes
|
| 50 |
- Target device and runtime configurations
|
| 51 |
|
| 52 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 53 |
|
| 54 |
+
See our repository for [BEVFusion on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/bevfusion_det) for usage instructions.
|
| 55 |
|
| 56 |
## Model Details
|
| 57 |
|
|
|
|
| 66 |
## Performance Summary
|
| 67 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 68 |
|---|---|---|---|---|---|---
|
| 69 |
+
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.743 ms | 16 - 26 MB | NPU
|
| 70 |
+
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 7.013 ms | 24 - 24 MB | NPU
|
| 71 |
+
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 13.117 ms | 23 - 23 MB | NPU
|
| 72 |
+
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.851 ms | 16 - 22 MB | NPU
|
| 73 |
+
| BEVFusionDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.71 ms | 12 - 19 MB | NPU
|
| 74 |
+
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.714 ms | 5 - 14 MB | NPU
|
| 75 |
+
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 7.395 ms | 5 - 5 MB | NPU
|
| 76 |
+
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 13.106 ms | 5 - 5 MB | NPU
|
| 77 |
+
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 9.876 ms | 5 - 12 MB | NPU
|
| 78 |
+
| BEVFusionDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.757 ms | 0 - 9 MB | NPU
|
| 79 |
+
| BEVFusionEncoder1 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 350.947 ms | 51 - 61 MB | NPU
|
| 80 |
+
| BEVFusionEncoder1 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 381.36 ms | 102 - 102 MB | NPU
|
| 81 |
+
| BEVFusionEncoder1 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 687.105 ms | 101 - 101 MB | NPU
|
| 82 |
+
| BEVFusionEncoder1 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 523.216 ms | 32 - 44 MB | NPU
|
| 83 |
+
| BEVFusionEncoder1 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 419.255 ms | 37 - 49 MB | NPU
|
| 84 |
+
| BEVFusionEncoder1 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 349.118 ms | 13 - 22 MB | NPU
|
| 85 |
+
| BEVFusionEncoder1 | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 381.759 ms | 12 - 12 MB | NPU
|
| 86 |
+
| BEVFusionEncoder1 | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 686.801 ms | 12 - 12 MB | NPU
|
| 87 |
+
| BEVFusionEncoder1 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 521.41 ms | 13 - 20 MB | NPU
|
| 88 |
+
| BEVFusionEncoder1 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 420.68 ms | 12 - 21 MB | NPU
|
| 89 |
+
| BEVFusionEncoder2 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2171.536 ms | 293 - 303 MB | NPU
|
| 90 |
+
| BEVFusionEncoder2 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 2354.007 ms | 1058 - 1058 MB | NPU
|
| 91 |
+
| BEVFusionEncoder2 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 3430.112 ms | 1058 - 1058 MB | NPU
|
| 92 |
+
| BEVFusionEncoder2 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2747.846 ms | 538 - 545 MB | NPU
|
| 93 |
+
| BEVFusionEncoder2 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2464.98 ms | 512 - 519 MB | NPU
|
| 94 |
+
| BEVFusionEncoder2 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 2172.187 ms | 16 - 26 MB | NPU
|
| 95 |
+
| BEVFusionEncoder2 | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 2429.811 ms | 17 - 17 MB | NPU
|
| 96 |
+
| BEVFusionEncoder2 | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 3530.924 ms | 17 - 17 MB | NPU
|
| 97 |
+
| BEVFusionEncoder2 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 2734.547 ms | 17 - 27 MB | NPU
|
| 98 |
+
| BEVFusionEncoder2 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 2451.822 ms | 17 - 30 MB | NPU
|
| 99 |
+
| BEVFusionEncoder3 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 369.72 ms | 508 - 518 MB | NPU
|
| 100 |
+
| BEVFusionEncoder3 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 355.989 ms | 610 - 610 MB | NPU
|
| 101 |
+
| BEVFusionEncoder3 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 700.88 ms | 610 - 610 MB | NPU
|
| 102 |
+
| BEVFusionEncoder3 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 582.578 ms | 572 - 582 MB | NPU
|
| 103 |
+
| BEVFusionEncoder3 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 499.155 ms | 571 - 583 MB | NPU
|
| 104 |
+
| BEVFusionEncoder3 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 368.343 ms | 609 - 619 MB | NPU
|
| 105 |
+
| BEVFusionEncoder3 | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 356.194 ms | 610 - 610 MB | NPU
|
| 106 |
+
| BEVFusionEncoder3 | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 700.168 ms | 610 - 610 MB | NPU
|
| 107 |
+
| BEVFusionEncoder3 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 591.853 ms | 623 - 635 MB | NPU
|
| 108 |
+
| BEVFusionEncoder3 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 500.811 ms | 608 - 623 MB | NPU
|
| 109 |
+
| BEVFusionEncoder4 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.771 ms | 30 - 40 MB | NPU
|
| 110 |
+
| BEVFusionEncoder4 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 7.929 ms | 14 - 14 MB | NPU
|
| 111 |
+
| BEVFusionEncoder4 | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 12.165 ms | 18 - 18 MB | NPU
|
| 112 |
+
| BEVFusionEncoder4 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.159 ms | 31 - 38 MB | NPU
|
| 113 |
+
| BEVFusionEncoder4 | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.707 ms | 14 - 21 MB | NPU
|
| 114 |
+
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.783 ms | 18 - 28 MB | NPU
|
| 115 |
+
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 8.702 ms | 19 - 19 MB | NPU
|
| 116 |
+
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 11.936 ms | 19 - 19 MB | NPU
|
| 117 |
+
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 9.085 ms | 19 - 26 MB | NPU
|
| 118 |
+
| BEVFusionEncoder4 | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.826 ms | 18 - 27 MB | NPU
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
|
| 120 |
## License
|
| 121 |
* The license for the original implementation of BEVFusion can be found
|