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
c2fd719
·
verified ·
1 Parent(s): 1d1e587

v0.64.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.64.0 for changelog.

Files changed (1) hide show
  1. README.md +34 -46
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/v0.63.0/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
@@ -43,18 +43,6 @@ 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® 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
@@ -69,39 +57,39 @@ See our repository for [Yolo-R on GitHub](https://github.com/qualcomm/ai-hub-mod
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
 
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/v0.64.0/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/v0.64.0/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/v0.64.0/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 | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 14.486 ms | 1 - 328 MB | NPU
47
  | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 13.576 ms | 1 - 320 MB | NPU
48
  | Yolo-R | ONNX | w8a16 | Snapdragon® X2 Elite | 15.19 ms | 2 - 2 MB | NPU
 
57
  | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 34.113 ms | 3 - 307 MB | NPU
58
  | Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 13.576 ms | 1 - 320 MB | NPU
59
  | Yolo-R | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 34.113 ms | 3 - 307 MB | NPU
60
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.738 ms | 1 - 313 MB | NPU
61
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 7.379 ms | 2 - 307 MB | NPU
62
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 6.978 ms | 2 - 2 MB | NPU
63
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® X Elite | 16.004 ms | 2 - 2 MB | NPU
64
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 9.907 ms | 2 - 370 MB | NPU
65
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 23.056 ms | 2 - 371 MB | NPU
66
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 56.814 ms | 2 - 7 MB | NPU
67
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 13.95 ms | 2 - 8 MB | NPU
68
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.109 ms | 2 - 5 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8650P | 15.488 ms | 1 - 310 MB | NPU
70
  | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8255P | 15.488 ms | 1 - 310 MB | NPU
71
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 23.056 ms | 2 - 371 MB | NPU
72
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 15.461 ms | 0 - 5 MB | NPU
73
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 16.004 ms | 2 - 2 MB | NPU
74
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 170.895 ms | 2 - 343 MB | NPU
75
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 21.866 ms | 2 - 318 MB | NPU
76
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 7.379 ms | 2 - 307 MB | NPU
77
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8295P | 19.914 ms | 0 - 301 MB | NPU
78
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 21.866 ms | 2 - 318 MB | NPU
79
+ | Yolo-R | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 15.188 ms | 0 - 285 MB | NPU
80
+ | Yolo-R | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 18.086 ms | 1 - 275 MB | NPU
81
+ | Yolo-R | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 48.145 ms | 0 - 398 MB | NPU
82
+ | Yolo-R | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 56.554 ms | 0 - 438 MB | NPU
83
+ | Yolo-R | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 64.291 ms | 1 - 86 MB | NPU
84
+ | Yolo-R | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 67.898 ms | 0 - 2 MB | NPU
85
+ | Yolo-R | TFLITE | float | Qualcomm® SA8775P | 133.821 ms | 17 - 41 MB | GPU
86
+ | Yolo-R | TFLITE | float | Qualcomm® SA8650P | 133.821 ms | 17 - 41 MB | GPU
87
+ | Yolo-R | TFLITE | float | Qualcomm® SA8255P | 133.821 ms | 17 - 41 MB | GPU
88
+ | Yolo-R | TFLITE | float | Qualcomm® QCS8450 | 56.554 ms | 0 - 438 MB | NPU
89
+ | Yolo-R | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 71.3 ms | 0 - 85 MB | NPU
90
+ | Yolo-R | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 18.086 ms | 1 - 275 MB | NPU
91
+ | Yolo-R | TFLITE | float | Qualcomm® SA7255P | 129.396 ms | 1 - 285 MB | NPU
92
+ | Yolo-R | TFLITE | float | Qualcomm® SA8295P | 53.337 ms | 1 - 329 MB | NPU
93
 
94
  ## License
95
  * The license for the original implementation of Yolo-R can be found