Hugging Face's logo

qualcomm
/
BGNet

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
e64116b
·
verified ·
1 Parent(s): c4d7bbc

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 +34 -34
README.md CHANGED
@@ -36,36 +36,36 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | BGNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 117.922 ms | 1 - 140 MB | NPU | -- |
40
- | BGNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 114.838 ms | 0 - 76 MB | NPU | -- |
41
- | BGNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 33.455 ms | 1 - 213 MB | NPU | -- |
42
- | BGNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 42.382 ms | 2 - 72 MB | NPU | -- |
43
- | BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 22.904 ms | 0 - 24 MB | NPU | -- |
44
- | BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 19.434 ms | 2 - 27 MB | NPU | -- |
45
- | BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 19.008 ms | 3 - 28 MB | NPU | -- |
46
- | BGNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 34.739 ms | 1 - 140 MB | NPU | -- |
47
- | BGNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 31.6 ms | 2 - 79 MB | NPU | -- |
48
- | BGNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 117.922 ms | 1 - 140 MB | NPU | -- |
49
- | BGNet | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 114.838 ms | 0 - 76 MB | NPU | -- |
50
- | BGNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 22.936 ms | 1 - 24 MB | NPU | -- |
51
- | BGNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 19.487 ms | 2 - 31 MB | NPU | -- |
52
- | BGNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 37.513 ms | 1 - 109 MB | NPU | -- |
53
- | BGNet | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 35.091 ms | 2 - 55 MB | NPU | -- |
54
- | BGNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 23.155 ms | 1 - 23 MB | NPU | -- |
55
- | BGNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 19.513 ms | 2 - 31 MB | NPU | -- |
56
- | BGNet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 34.739 ms | 1 - 140 MB | NPU | -- |
57
- | BGNet | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 31.6 ms | 2 - 79 MB | NPU | -- |
58
- | BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 16.936 ms | 1 - 226 MB | NPU | -- |
59
- | BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 14.213 ms | 2 - 92 MB | NPU | -- |
60
- | BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 13.9 ms | 2 - 94 MB | NPU | -- |
61
- | BGNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 12.858 ms | 0 - 137 MB | NPU | -- |
62
- | BGNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 11.124 ms | 2 - 81 MB | NPU | -- |
63
- | BGNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 11.053 ms | 0 - 76 MB | NPU | -- |
64
- | BGNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 11.101 ms | 1 - 139 MB | NPU | -- |
65
- | BGNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 9.888 ms | 2 - 87 MB | NPU | -- |
66
- | BGNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 9.282 ms | 2 - 86 MB | NPU | -- |
67
- | BGNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 20.0 ms | 428 - 428 MB | NPU | -- |
68
- | BGNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.245 ms | 154 - 154 MB | NPU | -- |
69
 
70
 
71
 
@@ -81,9 +81,9 @@ pip install "qai-hub-models[bgnet]"
81
  ```
82
 
83
 
84
- ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
85
 
86
- Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
87
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
88
 
89
  With this API token, you can configure your client to run models on the cloud
@@ -91,7 +91,7 @@ hosted devices.
91
  ```bash
92
  qai-hub configure --api_token API_TOKEN
93
  ```
94
- Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
95
 
96
 
97
 
@@ -202,7 +202,7 @@ With the output of the model, you can compute like PSNR, relative errors or
202
  spot check the output with expected output.
203
 
204
  **Note**: This on-device profiling and inference requires access to Qualcomm®
205
- AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
206
 
207
 
208
 
 
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | BGNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 117.969 ms | 1 - 143 MB | NPU | -- |
40
+ | BGNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 114.959 ms | 2 - 78 MB | NPU | -- |
41
+ | BGNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 33.59 ms | 1 - 218 MB | NPU | -- |
42
+ | BGNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 38.675 ms | 2 - 68 MB | NPU | -- |
43
+ | BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 23.009 ms | 1 - 23 MB | NPU | -- |
44
+ | BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 20.17 ms | 2 - 28 MB | NPU | -- |
45
+ | BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 18.796 ms | 0 - 180 MB | NPU | -- |
46
+ | BGNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 154.396 ms | 1 - 142 MB | NPU | -- |
47
+ | BGNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 32.303 ms | 1 - 79 MB | NPU | -- |
48
+ | BGNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 117.969 ms | 1 - 143 MB | NPU | -- |
49
+ | BGNet | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 114.959 ms | 2 - 78 MB | NPU | -- |
50
+ | BGNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 23.045 ms | 1 - 23 MB | NPU | -- |
51
+ | BGNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 20.194 ms | 2 - 28 MB | NPU | -- |
52
+ | BGNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 37.507 ms | 0 - 110 MB | NPU | -- |
53
+ | BGNet | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 33.987 ms | 2 - 55 MB | NPU | -- |
54
+ | BGNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 22.985 ms | 0 - 23 MB | NPU | -- |
55
+ | BGNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 20.31 ms | 2 - 28 MB | NPU | -- |
56
+ | BGNet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 154.396 ms | 1 - 142 MB | NPU | -- |
57
+ | BGNet | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 32.303 ms | 1 - 79 MB | NPU | -- |
58
+ | BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 16.668 ms | 1 - 227 MB | NPU | -- |
59
+ | BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 14.497 ms | 2 - 94 MB | NPU | -- |
60
+ | BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 13.941 ms | 3 - 98 MB | NPU | -- |
61
+ | BGNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 12.899 ms | 0 - 140 MB | NPU | -- |
62
+ | BGNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 11.566 ms | 2 - 84 MB | NPU | -- |
63
+ | BGNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 11.082 ms | 2 - 79 MB | NPU | -- |
64
+ | BGNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 11.08 ms | 1 - 141 MB | NPU | -- |
65
+ | BGNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 8.872 ms | 2 - 89 MB | NPU | -- |
66
+ | BGNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 9.291 ms | 2 - 86 MB | NPU | -- |
67
+ | BGNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 20.719 ms | 403 - 403 MB | NPU | -- |
68
+ | BGNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.194 ms | 154 - 154 MB | NPU | -- |
69
 
70
 
71
 
 
81
  ```
82
 
83
 
84
+ ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
85
 
86
+ Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
87
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
88
 
89
  With this API token, you can configure your client to run models on the cloud
 
91
  ```bash
92
  qai-hub configure --api_token API_TOKEN
93
  ```
94
+ Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
95
 
96
 
97
 
 
202
  spot check the output with expected output.
203
 
204
  **Note**: This on-device profiling and inference requires access to Qualcomm®
205
+ AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
206
 
207
 
208