Hugging Face's logo

qualcomm
/
CenterPoint

Other
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
c22b1ba
·
verified ·
1 Parent(s): d422630

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +20 -20
README.md CHANGED
@@ -13,7 +13,7 @@ pipeline_tag: other
13
 
14
  CenterPoint is a LiDAR-based 3D object detection model that detects objects by predicting their centers and regressing other attributes. It is designed for high accuracy and real-time performance in autonomous driving applications.
15
 
16
- 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/centerpoint) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
17
 
18
  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.
19
 
@@ -26,22 +26,22 @@ Below are pre-exported model assets ready for deployment.
26
 
27
  | Runtime | Precision | Chipset | SDK Versions | Download |
28
  |---|---|---|---|---|
29
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.48.0/centerpoint-qnn_dlc-float.zip)
30
- | TFLITE | float | Universal | TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.48.0/centerpoint-tflite-float.zip)
31
 
32
  For more device-specific assets and performance metrics, visit **[CenterPoint on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/centerpoint)**.
33
 
34
 
35
  ### Option 2: Export with Custom Configurations
36
 
37
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/centerpoint) Python library to compile and export the model with your own:
38
  - Custom weights (e.g., fine-tuned checkpoints)
39
  - Custom input shapes
40
  - Target device and runtime configurations
41
 
42
  This option is ideal if you need to customize the model beyond the default configuration provided here.
43
 
44
- See our repository for [CenterPoint on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/centerpoint) for usage instructions.
45
 
46
  ## Model Details
47
 
@@ -56,21 +56,21 @@ See our repository for [CenterPoint on GitHub](https://github.com/qualcomm/ai-hu
56
  ## Performance Summary
57
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
58
  |---|---|---|---|---|---|---
59
- | CenterPoint | QNN_DLC | float | Snapdragon® X2 Elite | 180.87 ms | 2 - 2 MB | NPU
60
- | CenterPoint | QNN_DLC | float | Snapdragon® X Elite | 312.052 ms | 2 - 2 MB | NPU
61
- | CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 244.881 ms | 0 - 752 MB | NPU
62
- | CenterPoint | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 909.147 ms | 1 - 452 MB | NPU
63
- | CenterPoint | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 323.63 ms | 2 - 366 MB | NPU
64
- | CenterPoint | QNN_DLC | float | Qualcomm® QCS9075 | 397.079 ms | 2 - 11 MB | NPU
65
- | CenterPoint | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 510.792 ms | 1 - 1067 MB | NPU
66
- | CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 201.763 ms | 0 - 449 MB | NPU
67
- | CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 171.022 ms | 2 - 444 MB | NPU
68
- | CenterPoint | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3953.577 ms | 2652 - 2660 MB | CPU
69
- | CenterPoint | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 6321.638 ms | 2607 - 2615 MB | CPU
70
- | CenterPoint | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 5057.038 ms | 2568 - 2595 MB | CPU
71
- | CenterPoint | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5831.27 ms | 2625 - 2635 MB | CPU
72
- | CenterPoint | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3022.673 ms | 2620 - 2629 MB | CPU
73
- | CenterPoint | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2542.905 ms | 2652 - 2662 MB | CPU
74
 
75
  ## License
76
  * The license for the original implementation of CenterPoint can be found
 
13
 
14
  CenterPoint is a LiDAR-based 3D object detection model that detects objects by predicting their centers and regressing other attributes. It is designed for high accuracy and real-time performance in autonomous driving applications.
15
 
16
+ 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/centerpoint) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
17
 
18
  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.
19
 
 
26
 
27
  | Runtime | Precision | Chipset | SDK Versions | Download |
28
  |---|---|---|---|---|
29
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.49.1/centerpoint-qnn_dlc-float.zip)
30
+ | TFLITE | float | Universal | TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.49.1/centerpoint-tflite-float.zip)
31
 
32
  For more device-specific assets and performance metrics, visit **[CenterPoint on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/centerpoint)**.
33
 
34
 
35
  ### Option 2: Export with Custom Configurations
36
 
37
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/centerpoint) Python library to compile and export the model with your own:
38
  - Custom weights (e.g., fine-tuned checkpoints)
39
  - Custom input shapes
40
  - Target device and runtime configurations
41
 
42
  This option is ideal if you need to customize the model beyond the default configuration provided here.
43
 
44
+ See our repository for [CenterPoint on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/centerpoint) for usage instructions.
45
 
46
  ## Model Details
47
 
 
56
  ## Performance Summary
57
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
58
  |---|---|---|---|---|---|---
59
+ | CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 168.806 ms | 2 - 443 MB | NPU
60
+ | CenterPoint | QNN_DLC | float | Snapdragon® X2 Elite | 292.794 ms | 2 - 2 MB | NPU
61
+ | CenterPoint | QNN_DLC | float | Snapdragon® X Elite | 312.248 ms | 2 - 2 MB | NPU
62
+ | CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 240.53 ms | 0 - 753 MB | NPU
63
+ | CenterPoint | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 909.559 ms | 1 - 452 MB | NPU
64
+ | CenterPoint | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 317.529 ms | 2 - 5 MB | NPU
65
+ | CenterPoint | QNN_DLC | float | Qualcomm® QCS9075 | 396.618 ms | 2 - 11 MB | NPU
66
+ | CenterPoint | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 516.508 ms | 2 - 1070 MB | NPU
67
+ | CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 201.55 ms | 0 - 448 MB | NPU
68
+ | CenterPoint | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2561.328 ms | 2582 - 2592 MB | CPU
69
+ | CenterPoint | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4070.789 ms | 2619 - 2628 MB | CPU
70
+ | CenterPoint | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 6335.211 ms | 2597 - 2605 MB | CPU
71
+ | CenterPoint | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4776.619 ms | 2619 - 2622 MB | CPU
72
+ | CenterPoint | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5590.249 ms | 2591 - 2600 MB | CPU
73
+ | CenterPoint | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2992.93 ms | 2594 - 2606 MB | CPU
74
 
75
  ## License
76
  * The license for the original implementation of CenterPoint can be found