Hugging Face's logo

qualcomm
/
CenterPoint

Other
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
533a6d3
·
verified ·
1 Parent(s): 0812f89

v0.63.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.

Files changed (2) hide show
  1. README.md +40 -42
  2. release_assets.json +6 -6
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/v0.62.2/src/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
 
@@ -26,23 +26,23 @@ Below are pre-exported model assets ready for deployment.
26
 
27
  | Runtime | Precision | Chipset | SDK Versions | Download |
28
  |---|---|---|---|---|
29
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.62.2/centerpoint-onnx-float.zip)
30
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.62.2/centerpoint-qnn_dlc-float.zip)
31
- | TFLITE | float | Universal | | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.62.2/centerpoint-tflite-float.zip)
32
 
33
  For more device-specific assets and performance metrics, visit **[CenterPoint on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/centerpoint)**.
34
 
35
 
36
  ### Option 2: Export with Custom Configurations
37
 
38
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/centerpoint) Python library to compile and export the model with your own:
39
  - Custom weights (e.g., fine-tuned checkpoints)
40
  - Custom input shapes
41
  - Target device and runtime configurations
42
 
43
  This option is ideal if you need to customize the model beyond the default configuration provided here.
44
 
45
- See our repository for [CenterPoint on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/centerpoint) for usage instructions.
46
 
47
  ## Model Details
48
 
@@ -57,42 +57,40 @@ See our repository for [CenterPoint on GitHub](https://github.com/qualcomm/ai-hu
57
  ## Performance Summary
58
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
59
  |---|---|---|---|---|---|---
60
- | CenterPoint | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 318.743 ms | 1057 - 1953 MB | NPU
61
- | CenterPoint | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 409.496 ms | 1049 - 1069 MB | NPU
62
- | CenterPoint | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 299.933 ms | 1044 - 1417 MB | NPU
63
- | CenterPoint | ONNX | float | Snapdragon® 8 Elite Mobile | 299.933 ms | 1044 - 1417 MB | NPU
64
- | CenterPoint | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 251.197 ms | 1056 - 1446 MB | NPU
65
- | CenterPoint | QNN_DLC | float | Snapdragon® X2 Elite | 280.558 ms | 2 - 2 MB | NPU
66
- | CenterPoint | QNN_DLC | float | Snapdragon® X Elite | 416.365 ms | 2 - 2 MB | NPU
67
- | CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 308.26 ms | 0 - 690 MB | NPU
68
- | CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 885.617 ms | 1 - 552 MB | NPU
69
- | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 455.059 ms | 2 - 11 MB | NPU
70
- | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 421.579 ms | 3 - 5 MB | NPU
71
- | CenterPoint | QNN_DLC | float | Qualcomm® SA8775P | 480.156 ms | 1 - 407 MB | NPU
72
- | CenterPoint | QNN_DLC | float | Qualcomm® SA8650P | 480.156 ms | 1 - 407 MB | NPU
73
- | CenterPoint | QNN_DLC | float | Qualcomm® SA8255P | 480.156 ms | 1 - 407 MB | NPU
74
- | CenterPoint | QNN_DLC | float | Qualcomm® QCS8450 | 885.617 ms | 1 - 552 MB | NPU
75
- | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 472.537 ms | 2 - 11 MB | NPU
76
- | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 416.365 ms | 2 - 2 MB | NPU
77
- | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 297.13 ms | 0 - 419 MB | NPU
78
- | CenterPoint | QNN_DLC | float | Qualcomm® SA7255P | 1025.144 ms | 2 - 412 MB | NPU
79
- | CenterPoint | QNN_DLC | float | Qualcomm® SA8295P | 530.742 ms | 0 - 403 MB | NPU
80
- | CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 297.13 ms | 0 - 419 MB | NPU
81
- | CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 253.537 ms | 2 - 413 MB | NPU
82
- | CenterPoint | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4314.218 ms | 1859 - 1868 MB | CPU
83
- | CenterPoint | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5485.207 ms | 1840 - 1851 MB | CPU
84
- | CenterPoint | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 6081.167 ms | 2361 - 2383 MB | CPU
85
- | CenterPoint | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4674.031 ms | 1877 - 1879 MB | CPU
86
- | CenterPoint | TFLITE | float | Qualcomm® SA8775P | 5497.631 ms | 1809 - 1815 MB | CPU
87
- | CenterPoint | TFLITE | float | Qualcomm® SA8650P | 5497.631 ms | 1809 - 1815 MB | CPU
88
- | CenterPoint | TFLITE | float | Qualcomm® SA8255P | 5497.631 ms | 1809 - 1815 MB | CPU
89
- | CenterPoint | TFLITE | float | Qualcomm® QCS8450 | 5485.207 ms | 1840 - 1851 MB | CPU
90
- | CenterPoint | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 5241.517 ms | 2363 - 2385 MB | CPU
91
- | CenterPoint | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2767.298 ms | 1809 - 1818 MB | CPU
92
- | CenterPoint | TFLITE | float | Qualcomm® SA7255P | 6339.224 ms | 1847 - 1856 MB | CPU
93
- | CenterPoint | TFLITE | float | Qualcomm® SA8295P | 3650.458 ms | 1805 - 1811 MB | CPU
94
- | CenterPoint | TFLITE | float | Snapdragon® 8 Elite Mobile | 2767.298 ms | 1809 - 1818 MB | CPU
95
- | CenterPoint | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 884.006 ms | 1941 - 1949 MB | CPU
96
 
97
  ## License
98
  * 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/blob/v0.63.0/src/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
+ | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.63.0/centerpoint-onnx-float.zip)
30
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.63.0/centerpoint-qnn_dlc-float.zip)
31
+ | TFLITE | float | Universal | | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.63.0/centerpoint-tflite-float.zip)
32
 
33
  For more device-specific assets and performance metrics, visit **[CenterPoint on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/centerpoint)**.
34
 
35
 
36
  ### Option 2: Export with Custom Configurations
37
 
38
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/centerpoint) Python library to compile and export the model with your own:
39
  - Custom weights (e.g., fine-tuned checkpoints)
40
  - Custom input shapes
41
  - Target device and runtime configurations
42
 
43
  This option is ideal if you need to customize the model beyond the default configuration provided here.
44
 
45
+ See our repository for [CenterPoint on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/centerpoint) for usage instructions.
46
 
47
  ## Model Details
48
 
 
57
  ## Performance Summary
58
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
59
  |---|---|---|---|---|---|---
60
+ | CenterPoint | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 167.16 ms | 1056 - 1516 MB | NPU
61
+ | CenterPoint | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 198.473 ms | 1056 - 1532 MB | NPU
62
+ | CenterPoint | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 235.887 ms | 1057 - 1836 MB | NPU
63
+ | CenterPoint | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 424.968 ms | 1052 - 1811 MB | NPU
64
+ | CenterPoint | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 304.761 ms | 1017 - 1115 MB | NPU
65
+ | CenterPoint | ONNX | float | Qualcomm® QCS8450 | 424.968 ms | 1052 - 1811 MB | NPU
66
+ | CenterPoint | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 198.473 ms | 1056 - 1532 MB | NPU
67
+ | CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 127.153 ms | 0 - 362 MB | NPU
68
+ | CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 147.115 ms | 0 - 361 MB | NPU
69
+ | CenterPoint | QNN_DLC | float | Snapdragon® X2 Elite | 121.005 ms | 2 - 2 MB | NPU
70
+ | CenterPoint | QNN_DLC | float | Snapdragon® X Elite | 201.411 ms | 2 - 2 MB | NPU
71
+ | CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 160.482 ms | 2 - 605 MB | NPU
72
+ | CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 283.124 ms | 1 - 580 MB | NPU
73
+ | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 277.106 ms | 2 - 12 MB | NPU
74
+ | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 214.063 ms | 2 - 6 MB | NPU
75
+ | CenterPoint | QNN_DLC | float | Qualcomm® QCS8450 | 283.124 ms | 1 - 580 MB | NPU
76
+ | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 269.711 ms | 2 - 11 MB | NPU
77
+ | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 201.411 ms | 2 - 2 MB | NPU
78
+ | CenterPoint | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 147.115 ms | 0 - 361 MB | NPU
79
+ | CenterPoint | QNN_DLC | float | Qualcomm® SA8295P | 293.796 ms | 1 - 338 MB | NPU
80
+ | CenterPoint | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 859.757 ms | 1808 - 1816 MB | CPU
81
+ | CenterPoint | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2832.77 ms | 1838 - 1849 MB | CPU
82
+ | CenterPoint | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4217.244 ms | 1847 - 1855 MB | CPU
83
+ | CenterPoint | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5424.656 ms | 1838 - 1848 MB | CPU
84
+ | CenterPoint | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 6081.133 ms | 1855 - 1877 MB | CPU
85
+ | CenterPoint | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4752.043 ms | 1813 - 1839 MB | CPU
86
+ | CenterPoint | TFLITE | float | Qualcomm® SA8775P | 5474.985 ms | 1810 - 1815 MB | CPU
87
+ | CenterPoint | TFLITE | float | Qualcomm® SA8650P | 5474.985 ms | 1810 - 1815 MB | CPU
88
+ | CenterPoint | TFLITE | float | Qualcomm® SA8255P | 5474.985 ms | 1810 - 1815 MB | CPU
89
+ | CenterPoint | TFLITE | float | Qualcomm® QCS8450 | 5424.656 ms | 1838 - 1848 MB | CPU
90
+ | CenterPoint | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 5218.529 ms | 1857 - 1879 MB | CPU
91
+ | CenterPoint | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2832.77 ms | 1838 - 1849 MB | CPU
92
+ | CenterPoint | TFLITE | float | Qualcomm® SA7255P | 6373.846 ms | 1848 - 1857 MB | CPU
93
+ | CenterPoint | TFLITE | float | Qualcomm® SA8295P | 3674.743 ms | 1808 - 1813 MB | CPU
 
 
94
 
95
  ## License
96
  * The license for the original implementation of CenterPoint can be found
release_assets.json CHANGED
@@ -1,24 +1,24 @@
1
  {
2
- "version": "0.62.2",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
- "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.62.2/centerpoint-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
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/centerpoint/releases/v0.62.2/centerpoint-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {},
21
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.62.2/centerpoint-tflite-float.zip"
22
  }
23
  }
24
  }
 
1
  {
2
+ "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
+ "qairt": "2.50.0.260828221209",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.63.0/centerpoint-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
+ "qairt": "2.50.0.260828221209"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.63.0/centerpoint-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {},
21
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.63.0/centerpoint-tflite-float.zip"
22
  }
23
  }
24
  }