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
5fd43c0
·
verified ·
1 Parent(s): 40fae8e

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 +56 -41
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.git).
19
- 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/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/quic/ai-hub-models/blob/main/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/quic/ai-hub-models/blob/main/qai_hub_models/models/yolor) for usage instructions.
31
 
32
 
33
  ## Model Details
@@ -43,45 +43,60 @@ See our repository for [Yolo-R on GitHub](https://github.com/quic/ai-hub-models/
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® X Elite | 58.077 ms | 74 - 74 MB | NPU
47
- | Yolo-R | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 41.792 ms | 6 - 352 MB | NPU
48
- | Yolo-R | ONNX | float | Qualcomm® QCS8550 (Proxy) | 56.438 ms | 0 - 79 MB | NPU
49
- | Yolo-R | ONNX | float | Qualcomm® QCS9075 | 52.883 ms | 5 - 12 MB | NPU
50
- | Yolo-R | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 37.174 ms | 3 - 234 MB | NPU
51
- | Yolo-R | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 26.905 ms | 6 - 318 MB | NPU
52
- | Yolo-R | ONNX | float | Snapdragon® X2 Elite | 26.205 ms | 75 - 75 MB | NPU
53
- | Yolo-R | ONNX | w8a16 | Snapdragon® X Elite | 30.372 ms | 40 - 40 MB | NPU
54
- | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 20.883 ms | 2 - 498 MB | NPU
55
- | Yolo-R | ONNX | w8a16 | Qualcomm® QCS6490 | 2267.909 ms | 127 - 136 MB | CPU
56
- | Yolo-R | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 29.364 ms | 0 - 49 MB | NPU
57
- | Yolo-R | ONNX | w8a16 | Qualcomm® QCS9075 | 30.707 ms | 1 - 6 MB | NPU
58
- | Yolo-R | ONNX | w8a16 | Qualcomm® QCM6690 | 1177.508 ms | 80 - 93 MB | CPU
59
- | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 17.123 ms | 1 - 354 MB | NPU
60
- | Yolo-R | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1121.096 ms | 125 - 138 MB | CPU
61
- | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 17.966 ms | 3 - 428 MB | NPU
62
- | Yolo-R | ONNX | w8a16 | Snapdragon® X2 Elite | 18.3 ms | 41 - 41 MB | NPU
 
63
  | Yolo-R | QNN_DLC | float | Snapdragon® X Elite | 29.418 ms | 5 - 5 MB | NPU
64
- | Yolo-R | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 22.571 ms | 2 - 322 MB | NPU
65
- | Yolo-R | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 100.259 ms | 1 - 253 MB | NPU
66
- | Yolo-R | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 29.695 ms | 5 - 40 MB | NPU
67
- | Yolo-R | QNN_DLC | float | Qualcomm® SA8775P | 36.081 ms | 1 - 259 MB | NPU
68
- | Yolo-R | QNN_DLC | float | Qualcomm® QCS9075 | 37.318 ms | 5 - 11 MB | NPU
69
- | Yolo-R | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 50.214 ms | 4 - 377 MB | NPU
70
- | Yolo-R | QNN_DLC | float | Qualcomm® SA7255P | 100.259 ms | 1 - 253 MB | NPU
71
- | Yolo-R | QNN_DLC | float | Qualcomm® SA8295P | 44.061 ms | 0 - 307 MB | NPU
72
- | Yolo-R | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 18.489 ms | 0 - 232 MB | NPU
73
- | Yolo-R | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 14.036 ms | 3 - 294 MB | NPU
74
- | Yolo-R | QNN_DLC | float | Snapdragon® X2 Elite | 15.22 ms | 5 - 5 MB | NPU
75
- | Yolo-R | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 39.226 ms | 0 - 442 MB | NPU
76
- | Yolo-R | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 137.603 ms | 1 - 328 MB | NPU
77
- | Yolo-R | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 59.157 ms | 1 - 3 MB | NPU
78
- | Yolo-R | TFLITE | float | Qualcomm® SA8775P | 66.396 ms | 1 - 310 MB | NPU
79
- | Yolo-R | TFLITE | float | Qualcomm® QCS9075 | 50.958 ms | 1 - 86 MB | NPU
80
- | Yolo-R | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 88.808 ms | 0 - 468 MB | NPU
81
- | Yolo-R | TFLITE | float | Qualcomm® SA7255P | 137.603 ms | 1 - 328 MB | NPU
82
- | Yolo-R | TFLITE | float | Qualcomm® SA8295P | 76.893 ms | 1 - 355 MB | NPU
83
- | Yolo-R | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 31.724 ms | 1 - 288 MB | NPU
84
- | Yolo-R | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 26.427 ms | 1 - 342 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
 
86
  ## License
87
  * 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.git).
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/main/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/main/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/main/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® X2 Elite | 26.309 ms | 75 - 75 MB | NPU
47
+ | Yolo-R | ONNX | float | Snapdragon® X Elite | 57.577 ms | 74 - 74 MB | NPU
48
+ | Yolo-R | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 41.986 ms | 2 - 346 MB | NPU
49
+ | Yolo-R | ONNX | float | Qualcomm® QCS8550 (Proxy) | 55.998 ms | 0 - 79 MB | NPU
50
+ | Yolo-R | ONNX | float | Qualcomm® QCS9075 | 52.751 ms | 5 - 12 MB | NPU
51
+ | Yolo-R | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 37.052 ms | 3 - 233 MB | NPU
52
+ | Yolo-R | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 26.443 ms | 6 - 318 MB | NPU
53
+ | Yolo-R | ONNX | w8a16 | Snapdragon® X2 Elite | 18.322 ms | 41 - 41 MB | NPU
54
+ | Yolo-R | ONNX | w8a16 | Snapdragon® X Elite | 30.49 ms | 40 - 40 MB | NPU
55
+ | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 20.897 ms | 0 - 490 MB | NPU
56
+ | Yolo-R | ONNX | w8a16 | Qualcomm® QCS6490 | 2282.662 ms | 129 - 136 MB | CPU
57
+ | Yolo-R | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 29.166 ms | 0 - 50 MB | NPU
58
+ | Yolo-R | ONNX | w8a16 | Qualcomm® QCS9075 | 29.553 ms | 1 - 6 MB | NPU
59
+ | Yolo-R | ONNX | w8a16 | Qualcomm® QCM6690 | 1176.534 ms | 48 - 62 MB | CPU
60
+ | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 17.119 ms | 1 - 364 MB | NPU
61
+ | Yolo-R | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1118.647 ms | 154 - 166 MB | CPU
62
+ | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 17.934 ms | 3 - 429 MB | NPU
63
+ | Yolo-R | QNN_DLC | float | Snapdragon® X2 Elite | 15.23 ms | 5 - 5 MB | NPU
64
  | Yolo-R | QNN_DLC | float | Snapdragon® X Elite | 29.418 ms | 5 - 5 MB | NPU
65
+ | Yolo-R | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 22.761 ms | 0 - 317 MB | NPU
66
+ | Yolo-R | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 100.329 ms | 0 - 252 MB | NPU
67
+ | Yolo-R | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 29.567 ms | 5 - 7 MB | NPU
68
+ | Yolo-R | QNN_DLC | float | Qualcomm® SA8775P | 36.109 ms | 0 - 259 MB | NPU
69
+ | Yolo-R | QNN_DLC | float | Qualcomm® QCS9075 | 37.531 ms | 5 - 11 MB | NPU
70
+ | Yolo-R | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 50.546 ms | 5 - 377 MB | NPU
71
+ | Yolo-R | QNN_DLC | float | Qualcomm® SA7255P | 100.329 ms | 0 - 252 MB | NPU
72
+ | Yolo-R | QNN_DLC | float | Qualcomm® SA8295P | 44.017 ms | 0 - 307 MB | NPU
73
+ | Yolo-R | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 18.262 ms | 0 - 230 MB | NPU
74
+ | Yolo-R | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 13.999 ms | 5 - 295 MB | NPU
75
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 8.363 ms | 2 - 2 MB | NPU
76
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® X Elite | 18.967 ms | 2 - 2 MB | NPU
77
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 12.323 ms | 2 - 370 MB | NPU
78
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 77.324 ms | 3 - 7 MB | NPU
79
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 37.394 ms | 0 - 288 MB | NPU
80
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 18.116 ms | 2 - 4 MB | NPU
81
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8775P | 18.34 ms | 0 - 288 MB | NPU
82
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 20.195 ms | 1 - 5 MB | NPU
83
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 246.253 ms | 2 - 400 MB | NPU
84
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 25.017 ms | 2 - 371 MB | NPU
85
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA7255P | 37.394 ms | 0 - 288 MB | NPU
86
+ | Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8295P | 23.495 ms | 0 - 291 MB | NPU
87
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 9.865 ms | 0 - 299 MB | NPU
88
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 26.414 ms | 2 - 312 MB | NPU
89
+ | Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 7.295 ms | 2 - 303 MB | NPU
90
+ | Yolo-R | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 39.801 ms | 0 - 445 MB | NPU
91
+ | Yolo-R | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 137.818 ms | 1 - 328 MB | NPU
92
+ | Yolo-R | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 59.564 ms | 1 - 3 MB | NPU
93
+ | Yolo-R | TFLITE | float | Qualcomm® SA8775P | 66.658 ms | 1 - 310 MB | NPU
94
+ | Yolo-R | TFLITE | float | Qualcomm® QCS9075 | 50.464 ms | 1 - 86 MB | NPU
95
+ | Yolo-R | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 88.543 ms | 1 - 471 MB | NPU
96
+ | Yolo-R | TFLITE | float | Qualcomm® SA7255P | 137.818 ms | 1 - 328 MB | NPU
97
+ | Yolo-R | TFLITE | float | Qualcomm® SA8295P | 76.899 ms | 1 - 355 MB | NPU
98
+ | Yolo-R | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 31.258 ms | 1 - 281 MB | NPU
99
+ | Yolo-R | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 26.051 ms | 0 - 341 MB | NPU
100
 
101
  ## License
102
  * The license for the original implementation of Yolo-R can be found