Hugging Face's logo

qualcomm
/
CenterNet-2D

Object Detection
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
0dba4d2
·
verified ·
1 Parent(s): cf87f43

v0.48.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

Files changed (1) hide show
  1. README.md +40 -41
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/quic/ai-hub-models/blob/main/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
 
@@ -27,39 +27,38 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | 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/centernet_2d/releases/v0.47.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
31
- | 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/centernet_2d/releases/v0.47.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
32
- | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.47.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
33
- | 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/centernet_2d/releases/v0.47.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
34
- | 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/centernet_2d/releases/v0.47.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip)
35
- | 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/centernet_2d/releases/v0.47.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
36
- | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.47.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs9075.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/centernet_2d/releases/v0.47.0/centernet_2d-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/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
39
- | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8275_proxy.zip)
40
- | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
41
- | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8775p.zip)
42
- | 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/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
43
- | 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/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.zip)
44
- | 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/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
45
- | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_sa7255p.zip)
46
- | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8295p.zip)
47
- | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs9075.zip)
48
- | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.47.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8450_proxy.zip)
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/quic/ai-hub-models/blob/main/qai_hub_models/models/centernet_2d) Python library to compile and export the model with your own:
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/quic/ai-hub-models/blob/main/qai_hub_models/models/centernet_2d) for usage instructions.
63
 
64
  ## Model Details
65
 
@@ -74,25 +73,25 @@ See our repository for [CenterNet-2D on GitHub](https://github.com/quic/ai-hub-m
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® X Elite | 448.769 ms | 54 - 54 MB | NPU
78
- | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 302.135 ms | 18 - 25 MB | NPU
79
- | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 441.166 ms | 1 - 63 MB | NPU
80
- | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 455.018 ms | 9 - 15 MB | NPU
81
- | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 304.949 ms | 13 - 24 MB | NPU
82
- | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 238.034 ms | 18 - 27 MB | NPU
83
- | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 263.941 ms | 52 - 52 MB | NPU
84
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 431.418 ms | 3 - 3 MB | NPU
85
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 309.637 ms | 3 - 11 MB | NPU
86
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 564.897 ms | 1 - 10 MB | NPU
87
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 432.807 ms | 3 - 7 MB | NPU
88
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 458.264 ms | 0 - 9 MB | NPU
89
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 448.469 ms | 3 - 13 MB | NPU
90
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 650.768 ms | 4 - 12 MB | NPU
91
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 564.897 ms | 1 - 10 MB | NPU
92
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 483.451 ms | 3 - 8 MB | NPU
93
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 303.593 ms | 3 - 12 MB | NPU
94
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 239.145 ms | 3 - 12 MB | NPU
95
- | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 266.592 ms | 3 - 3 MB | NPU
96
 
97
  ## License
98
  * 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/main/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.48.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
31
+ | 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/centernet_2d/releases/v0.48.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
32
+ | 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/centernet_2d/releases/v0.48.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
33
+ | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.48.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.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/centernet_2d/releases/v0.48.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
35
+ | 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/centernet_2d/releases/v0.48.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip)
36
+ | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.48.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
37
+ | 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/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
38
+ | 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/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
39
+ | 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/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
40
+ | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
41
+ | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8775p.zip)
42
+ | 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/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
43
+ | 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/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.zip)
44
+ | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_sa7255p.zip)
45
+ | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8295p.zip)
46
+ | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs9075.zip)
47
+ | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.48.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8450_proxy.zip)
 
48
 
49
  For more device-specific assets and performance metrics, visit **[CenterNet-2D on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/centernet_2d)**.
50
 
51
 
52
  ### Option 2: Export with Custom Configurations
53
 
54
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/centernet_2d) Python library to compile and export the model with your own:
55
  - Custom weights (e.g., fine-tuned checkpoints)
56
  - Custom input shapes
57
  - Target device and runtime configurations
58
 
59
  This option is ideal if you need to customize the model beyond the default configuration provided here.
60
 
61
+ See our repository for [CenterNet-2D on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/centernet_2d) for usage instructions.
62
 
63
  ## Model Details
64
 
 
73
  ## Performance Summary
74
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
75
  |---|---|---|---|---|---|---
76
+ | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 268.771 ms | 52 - 52 MB | NPU
77
+ | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 459.221 ms | 54 - 54 MB | NPU
78
+ | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 306.116 ms | 19 - 26 MB | NPU
79
+ | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 447.524 ms | 1 - 63 MB | NPU
80
+ | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 462.493 ms | 7 - 13 MB | NPU
81
+ | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 310.126 ms | 14 - 21 MB | NPU
82
+ | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 240.099 ms | 17 - 27 MB | NPU
83
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 255.19 ms | 3 - 3 MB | NPU
84
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 443.944 ms | 3 - 3 MB | NPU
85
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 330.538 ms | 3 - 10 MB | NPU
86
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 583.655 ms | 1 - 9 MB | NPU
87
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 445.79 ms | 3 - 5 MB | NPU
88
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 1365.841 ms | 1 - 10 MB | NPU
89
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 467.457 ms | 3 - 13 MB | NPU
90
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 653.56 ms | 3 - 12 MB | NPU
91
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 583.655 ms | 1 - 9 MB | NPU
92
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 501.091 ms | 0 - 5 MB | NPU
93
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 308.595 ms | 3 - 16 MB | NPU
94
+ | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 241.694 ms | 3 - 13 MB | NPU
95
 
96
  ## License
97
  * The license for the original implementation of CenterNet-2D can be found