Hugging Face's logo

qualcomm
/
YOLOv11-Segmentation

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
f00d86e
·
verified ·
1 Parent(s): 29ac0fa

v0.42.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.42.0 for changelog.

Files changed (1) hide show
  1. README.md +32 -32
README.md CHANGED
@@ -38,34 +38,34 @@ More details on model performance across various devices, can be found
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
- | YOLOv11-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 16.091 ms | 4 - 86 MB | NPU | -- |
42
- | YOLOv11-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 15.266 ms | 1 - 98 MB | NPU | -- |
43
- | YOLOv11-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.984 ms | 4 - 46 MB | NPU | -- |
44
- | YOLOv11-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.532 ms | 0 - 76 MB | NPU | -- |
45
- | YOLOv11-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.29 ms | 0 - 51 MB | NPU | -- |
46
- | YOLOv11-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 6.133 ms | 0 - 71 MB | NPU | -- |
47
- | YOLOv11-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 24.457 ms | 4 - 87 MB | NPU | -- |
48
- | YOLOv11-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.038 ms | 1 - 102 MB | NPU | -- |
49
- | YOLOv11-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 16.091 ms | 4 - 86 MB | NPU | -- |
50
- | YOLOv11-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 15.266 ms | 1 - 98 MB | NPU | -- |
51
- | YOLOv11-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.533 ms | 0 - 81 MB | NPU | -- |
52
- | YOLOv11-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.313 ms | 0 - 43 MB | NPU | -- |
53
- | YOLOv11-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 10.408 ms | 4 - 39 MB | NPU | -- |
54
- | YOLOv11-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.524 ms | 0 - 80 MB | NPU | -- |
55
- | YOLOv11-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.24 ms | 0 - 38 MB | NPU | -- |
56
- | YOLOv11-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 24.457 ms | 4 - 87 MB | NPU | -- |
57
- | YOLOv11-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 6.038 ms | 1 - 102 MB | NPU | -- |
58
- | YOLOv11-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.316 ms | 0 - 160 MB | NPU | -- |
59
- | YOLOv11-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.152 ms | 5 - 227 MB | NPU | -- |
60
- | YOLOv11-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.115 ms | 0 - 102 MB | NPU | -- |
61
- | YOLOv11-Segmentation | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 2.59 ms | 0 - 89 MB | NPU | -- |
62
- | YOLOv11-Segmentation | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 2.396 ms | 0 - 108 MB | NPU | -- |
63
- | YOLOv11-Segmentation | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.095 ms | 2 - 93 MB | NPU | -- |
64
- | YOLOv11-Segmentation | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 2.148 ms | 0 - 86 MB | NPU | -- |
65
- | YOLOv11-Segmentation | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 2.008 ms | 5 - 128 MB | NPU | -- |
66
- | YOLOv11-Segmentation | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 3.065 ms | 4 - 72 MB | NPU | -- |
67
- | YOLOv11-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.626 ms | 124 - 124 MB | NPU | -- |
68
- | YOLOv11-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.367 ms | 17 - 17 MB | NPU | -- |
69
 
70
 
71
 
@@ -80,9 +80,9 @@ pip install "qai-hub-models[yolov11-seg]"
80
  ```
81
 
82
 
83
- ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
84
 
85
- Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
86
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
87
 
88
  With this API token, you can configure your client to run models on the cloud
@@ -90,7 +90,7 @@ hosted devices.
90
  ```bash
91
  qai-hub configure --api_token API_TOKEN
92
  ```
93
- Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
94
 
95
 
96
 
@@ -201,7 +201,7 @@ With the output of the model, you can compute like PSNR, relative errors or
201
  spot check the output with expected output.
202
 
203
  **Note**: This on-device profiling and inference requires access to Qualcomm®
204
- AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
205
 
206
 
207
 
 
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
+ | YOLOv11-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 16.228 ms | 4 - 88 MB | NPU | -- |
42
+ | YOLOv11-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 15.246 ms | 0 - 98 MB | NPU | -- |
43
+ | YOLOv11-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 9.073 ms | 4 - 46 MB | NPU | -- |
44
+ | YOLOv11-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.675 ms | 0 - 85 MB | NPU | -- |
45
+ | YOLOv11-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.303 ms | 4 - 61 MB | NPU | -- |
46
+ | YOLOv11-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 6.043 ms | 3 - 77 MB | NPU | -- |
47
+ | YOLOv11-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 25.312 ms | 4 - 88 MB | NPU | -- |
48
+ | YOLOv11-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.071 ms | 1 - 104 MB | NPU | -- |
49
+ | YOLOv11-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 16.228 ms | 4 - 88 MB | NPU | -- |
50
+ | YOLOv11-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 15.246 ms | 0 - 98 MB | NPU | -- |
51
+ | YOLOv11-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.708 ms | 0 - 84 MB | NPU | -- |
52
+ | YOLOv11-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.312 ms | 2 - 43 MB | NPU | -- |
53
+ | YOLOv11-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 10.436 ms | 4 - 41 MB | NPU | -- |
54
+ | YOLOv11-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.684 ms | 0 - 83 MB | NPU | -- |
55
+ | YOLOv11-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.297 ms | 5 - 60 MB | NPU | -- |
56
+ | YOLOv11-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 25.312 ms | 4 - 88 MB | NPU | -- |
57
+ | YOLOv11-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 6.071 ms | 1 - 104 MB | NPU | -- |
58
+ | YOLOv11-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.445 ms | 0 - 155 MB | NPU | -- |
59
+ | YOLOv11-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.164 ms | 5 - 229 MB | NPU | -- |
60
+ | YOLOv11-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.089 ms | 0 - 109 MB | NPU | -- |
61
+ | YOLOv11-Segmentation | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 2.625 ms | 0 - 89 MB | NPU | -- |
62
+ | YOLOv11-Segmentation | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 2.427 ms | 5 - 113 MB | NPU | -- |
63
+ | YOLOv11-Segmentation | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.137 ms | 0 - 93 MB | NPU | -- |
64
+ | YOLOv11-Segmentation | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 2.195 ms | 0 - 90 MB | NPU | -- |
65
+ | YOLOv11-Segmentation | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 2.007 ms | 5 - 130 MB | NPU | -- |
66
+ | YOLOv11-Segmentation | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 3.066 ms | 4 - 70 MB | NPU | -- |
67
+ | YOLOv11-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.688 ms | 123 - 123 MB | NPU | -- |
68
+ | YOLOv11-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.366 ms | 17 - 17 MB | NPU | -- |
69
 
70
 
71
 
 
80
  ```
81
 
82
 
83
+ ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
84
 
85
+ Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
86
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
87
 
88
  With this API token, you can configure your client to run models on the cloud
 
90
  ```bash
91
  qai-hub configure --api_token API_TOKEN
92
  ```
93
+ Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
94
 
95
 
96
 
 
201
  spot check the output with expected output.
202
 
203
  **Note**: This on-device profiling and inference requires access to Qualcomm®
204
+ AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
205
 
206
 
207