Hugging Face's logo

qualcomm
/
Yolo-R

Object Detection
PyTorch
bu_auto
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
1d1e587
·
verified ·
1 Parent(s): b0bf744

v0.63.0

Browse files

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

Files changed (1) hide show
  1. README.md +58 -62
README.md CHANGED
@@ -16,18 +16,18 @@ pipeline_tag: object-detection
16
  YoloR is a machine learning model that predicts bounding boxes and classes of objects in an image.
17
 
18
  This is based on the implementation of Yolo-R found [here](https://github.com/WongKinYiu/yolor).
19
- 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/yolor) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
23
  ## Getting Started
24
  Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
25
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/yolor) Python library to compile and export the model with your own:
26
  - Custom weights (e.g., fine-tuned checkpoints)
27
  - Custom input shapes
28
  - Target device and runtime configurations
29
 
30
- See our repository for [Yolo-R on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/yolor) for usage instructions.
31
 
32
 
33
  ## Model Details
@@ -43,69 +43,65 @@ See our repository for [Yolo-R on GitHub](https://github.com/qualcomm/ai-hub-mod
43
  ## Performance Summary
44
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
45
  |---|---|---|---|---|---|---
46
- | Yolo-R | ONNX | float | Snapdragon® X2 Elite | 27.222 ms | 5 - 5 MB | NPU
47
- | Yolo-R | ONNX | float | Snapdragon® X Elite | 45.796 ms | 72 - 72 MB | NPU
48
- | Yolo-R | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 35.091 ms | 1 - 249 MB | NPU
49
- | Yolo-R | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 72.384 ms | 1 - 311 MB | NPU
50
- | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 54.017 ms | 5 - 13 MB | NPU
51
- | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 45.68 ms | 5 - 444 MB | NPU
52
- | Yolo-R | ONNX | float | Qualcomm® QCS8450 | 72.384 ms | 1 - 311 MB | NPU
53
- | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 51.648 ms | 5 - 12 MB | NPU
54
- | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 45.796 ms | 72 - 72 MB | NPU
55
- | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 30.266 ms | 2 - 196 MB | NPU
56
- | Yolo-R | ONNX | float | Snapdragon® 8 Elite Mobile | 30.266 ms | 2 - 196 MB | NPU
57
- | Yolo-R | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.816 ms | 3 - 202 MB | NPU
58
- | Yolo-R | ONNX | w8a16 | Snapdragon® X2 Elite | 15.382 ms | 2 - 2 MB | NPU
59
- | Yolo-R | ONNX | w8a16 | Snapdragon® X Elite | 23.73 ms | 37 - 37 MB | NPU
60
- | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 15.901 ms | 0 - 398 MB | NPU
61
- | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 32.195 ms | 3 - 405 MB | NPU
62
- | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 21.601 ms | 1 - 7 MB | NPU
63
- | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 22.789 ms | 0 - 47 MB | NPU
64
- | Yolo-R | ONNX | w8a16 | Qualcomm® QCS8450 | 32.195 ms | 3 - 405 MB | NPU
65
- | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 23.321 ms | 1 - 6 MB | NPU
66
- | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 23.73 ms | 37 - 37 MB | NPU
67
- | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 47.307 ms | 3 - 320 MB | NPU
68
- | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 13.573 ms | 1 - 334 MB | NPU
69
- | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 13.573 ms | 1 - 334 MB | NPU
70
- | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 14.619 ms | 1 - 342 MB | NPU
71
- | Yolo-R | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 47.307 ms | 3 - 320 MB | NPU
72
- | Yolo-R | QNN_DLC | float | Snapdragon® X2 Elite | 18.205 ms | 5 - 5 MB | NPU
73
- | Yolo-R | QNN_DLC | float | Snapdragon® X Elite | 51.659 ms | 5 - 5 MB | NPU
74
- | Yolo-R | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 40.865 ms | 0 - 253 MB | NPU
75
- | Yolo-R | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 65.516 ms | 5 - 312 MB | NPU
76
- | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 58.207 ms | 5 - 12 MB | NPU
77
- | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 55.198 ms | 5 - 406 MB | NPU
78
- | Yolo-R | QNN_DLC | float | Qualcomm® SA8775P | 61.374 ms | 1 - 197 MB | NPU
 
79
  | Yolo-R | QNN_DLC | float | Qualcomm® SA8650P | 61.374 ms | 1 - 197 MB | NPU
80
  | Yolo-R | QNN_DLC | float | Qualcomm® SA8255P | 61.374 ms | 1 - 197 MB | NPU
81
- | Yolo-R | QNN_DLC | float | Qualcomm® QCS8450 | 65.516 ms | 5 - 312 MB | NPU
82
- | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 61.449 ms | 7 - 13 MB | NPU
83
- | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 51.659 ms | 5 - 5 MB | NPU
84
- | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 22.853 ms | 5 - 199 MB | NPU
85
- | Yolo-R | QNN_DLC | float | Qualcomm® SA7255P | 124.404 ms | 1 - 198 MB | NPU
86
- | Yolo-R | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 22.853 ms | 5 - 199 MB | NPU
87
- | Yolo-R | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 19.092 ms | 5 - 211 MB | NPU
88
- | Yolo-R | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 7.053 ms | 2 - 2 MB | NPU
89
- | Yolo-R | QNN_DLC | w8a16 | Snapdragon® X Elite | 16.333 ms | 2 - 2 MB | NPU
90
- | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 10.015 ms | 2 - 382 MB | NPU
91
- | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 25.198 ms | 2 - 382 MB | NPU
92
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 65.097 ms | 2 - 7 MB | NPU
93
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 13.954 ms | 2 - 7 MB | NPU
94
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.338 ms | 2 - 4 MB | NPU
95
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8775P | 15.488 ms | 1 - 310 MB | NPU
96
  | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8650P | 15.488 ms | 1 - 310 MB | NPU
97
  | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8255P | 15.488 ms | 1 - 310 MB | NPU
98
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 25.198 ms | 2 - 382 MB | NPU
99
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 15.889 ms | 4 - 8 MB | NPU
100
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 16.333 ms | 2 - 2 MB | NPU
101
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 165.426 ms | 2 - 350 MB | NPU
102
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 21.262 ms | 2 - 326 MB | NPU
103
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 7.358 ms | 2 - 320 MB | NPU
104
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA7255P | 32.554 ms | 1 - 311 MB | NPU
105
- | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8295P | 20.795 ms | 0 - 312 MB | NPU
106
- | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 7.358 ms | 2 - 320 MB | NPU
107
- | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 5.854 ms | 2 - 326 MB | NPU
108
- | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 21.262 ms | 2 - 326 MB | NPU
109
 
110
  ## License
111
  * The license for the original implementation of Yolo-R can be found
 
16
  YoloR is a machine learning model that predicts bounding boxes and classes of objects in an image.
17
 
18
  This is based on the implementation of Yolo-R found [here](https://github.com/WongKinYiu/yolor).
19
+ 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/yolor) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
23
  ## Getting Started
24
  Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
25
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/yolor) Python library to compile and export the model with your own:
26
  - Custom weights (e.g., fine-tuned checkpoints)
27
  - Custom input shapes
28
  - Target device and runtime configurations
29
 
30
+ See our repository for [Yolo-R on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/yolor) for usage instructions.
31
 
32
 
33
  ## Model Details
 
43
  ## Performance Summary
44
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
45
  |---|---|---|---|---|---|---
46
+ | Yolo-R | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 25.765 ms | 1 - 190 MB | NPU
47
+ | Yolo-R | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.099 ms | 3 - 188 MB | NPU
48
+ | Yolo-R | ONNX | float | Snapdragon® X2 Elite | 35.909 ms | 5 - 5 MB | NPU
49
+ | Yolo-R | ONNX | float | Snapdragon® X Elite | 40.33 ms | 72 - 72 MB | NPU
50
+ | Yolo-R | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 32.364 ms | 6 - 253 MB | NPU
51
+ | Yolo-R | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 54.675 ms | 1 - 305 MB | NPU
52
+ | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 49.729 ms | 5 - 13 MB | NPU
53
+ | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 40.984 ms | 0 - 77 MB | NPU
54
+ | Yolo-R | ONNX | float | Qualcomm® QCS8450 | 54.675 ms | 1 - 305 MB | NPU
55
+ | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 47.783 ms | 5 - 13 MB | NPU
56
+ | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 40.33 ms | 72 - 72 MB | NPU
57
+ | Yolo-R | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 27.099 ms | 3 - 188 MB | NPU
58
+ | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 14.486 ms | 1 - 328 MB | NPU
59
+ | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 13.576 ms | 1 - 320 MB | NPU
60
+ | Yolo-R | ONNX | w8a16 | Snapdragon® X2 Elite | 15.19 ms | 2 - 2 MB | NPU
61
+ | Yolo-R | ONNX | w8a16 | Snapdragon® X Elite | 23.229 ms | 37 - 37 MB | NPU
62
+ | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 15.874 ms | 3 - 393 MB | NPU
63
+ | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 30.311 ms | 0 - 389 MB | NPU
64
+ | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 21.484 ms | 1 - 7 MB | NPU
65
+ | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 22.502 ms | 0 - 40 MB | NPU
66
+ | Yolo-R | ONNX | w8a16 | Qualcomm® QCS8450 | 30.311 ms | 0 - 389 MB | NPU
67
+ | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 23.232 ms | 1 - 6 MB | NPU
68
+ | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 23.229 ms | 37 - 37 MB | NPU
69
+ | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 34.113 ms | 3 - 307 MB | NPU
70
+ | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 13.576 ms | 1 - 320 MB | NPU
71
+ | Yolo-R | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 34.113 ms | 3 - 307 MB | NPU
72
+ | Yolo-R | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 24.446 ms | 5 - 196 MB | NPU
73
+ | Yolo-R | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 20.795 ms | 0 - 186 MB | NPU
74
+ | Yolo-R | QNN_DLC | float | Snapdragon® X2 Elite | 27.008 ms | 5 - 5 MB | NPU
75
+ | Yolo-R | QNN_DLC | float | Snapdragon® X Elite | 32.207 ms | 5 - 5 MB | NPU
76
+ | Yolo-R | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 25.728 ms | 3 - 243 MB | NPU
77
+ | Yolo-R | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 50.503 ms | 5 - 304 MB | NPU
78
+ | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 40.83 ms | 5 - 13 MB | NPU
79
+ | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 33.138 ms | 5 - 7 MB | NPU
80
  | Yolo-R | QNN_DLC | float | Qualcomm® SA8650P | 61.374 ms | 1 - 197 MB | NPU
81
  | Yolo-R | QNN_DLC | float | Qualcomm® SA8255P | 61.374 ms | 1 - 197 MB | NPU
82
+ | Yolo-R | QNN_DLC | float | Qualcomm® QCS8450 | 50.503 ms | 5 - 304 MB | NPU
83
+ | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 40.378 ms | 5 - 12 MB | NPU
84
+ | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 32.207 ms | 5 - 5 MB | NPU
85
+ | Yolo-R | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 20.795 ms | 0 - 186 MB | NPU
86
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.742 ms | 2 - 314 MB | NPU
87
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 7.405 ms | 2 - 307 MB | NPU
88
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 7.006 ms | 2 - 2 MB | NPU
89
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® X Elite | 16.026 ms | 2 - 2 MB | NPU
90
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 9.927 ms | 2 - 369 MB | NPU
91
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 23.072 ms | 2 - 370 MB | NPU
92
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 56.763 ms | 2 - 7 MB | NPU
93
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 13.89 ms | 2 - 8 MB | NPU
94
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.086 ms | 2 - 5 MB | NPU
 
 
95
  | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8650P | 15.488 ms | 1 - 310 MB | NPU
96
  | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8255P | 15.488 ms | 1 - 310 MB | NPU
97
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 23.072 ms | 2 - 370 MB | NPU
98
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 15.503 ms | 1 - 6 MB | NPU
99
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 16.026 ms | 2 - 2 MB | NPU
100
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 153.244 ms | 2 - 341 MB | NPU
101
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 21.917 ms | 2 - 318 MB | NPU
102
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 7.405 ms | 2 - 307 MB | NPU
103
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8295P | 19.92 ms | 0 - 301 MB | NPU
104
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 21.917 ms | 2 - 318 MB | NPU
 
 
 
105
 
106
  ## License
107
  * The license for the original implementation of Yolo-R can be found