Hugging Face's logo

qualcomm
/
PSPNet

Image Segmentation
PyTorch
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
9ee1f98
·
verified ·
1 Parent(s): 60d342b

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +57 -57
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-segmentation
14
 
15
  PSPNet (Pyramid Scene Parsing Network) is a semantic segmentation model that captures global context information by applying pyramid pooling modules. It is designed to improve scene understanding by aggregating contextual features at multiple scales.
16
 
17
- 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/pspnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
 
19
  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.
20
 
@@ -27,26 +27,26 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.48.0/pspnet-onnx-float.zip)
31
- | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.48.0/pspnet-onnx-w8a8.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.48.0/pspnet-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.48.0/pspnet-qnn_dlc-w8a8.zip)
34
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.48.0/pspnet-tflite-float.zip)
35
- | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.48.0/pspnet-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[PSPNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/pspnet)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/pspnet) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
- See our repository for [PSPNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/pspnet) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -61,54 +61,54 @@ See our repository for [PSPNet on GitHub](https://github.com/qualcomm/ai-hub-mod
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
- | PSPNet | ONNX | float | Snapdragon® X2 Elite | 428.799 ms | 266 - 266 MB | NPU
65
- | PSPNet | ONNX | float | Snapdragon® X Elite | 695.154 ms | 529 - 529 MB | NPU
66
- | PSPNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 513.442 ms | 147 - 1066 MB | NPU
67
- | PSPNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 606.249 ms | 188 - 190 MB | NPU
68
- | PSPNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 334.904 ms | 248 - 1006 MB | NPU
69
- | PSPNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 324.487 ms | 224 - 992 MB | NPU
70
- | PSPNet | ONNX | w8a8 | Snapdragon® X2 Elite | 15.299 ms | 131 - 131 MB | NPU
71
- | PSPNet | ONNX | w8a8 | Snapdragon® X Elite | 28.506 ms | 133 - 133 MB | NPU
72
- | PSPNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 22.095 ms | 71 - 492 MB | NPU
73
- | PSPNet | ONNX | w8a8 | Qualcomm® QCS6490 | 3343.057 ms | 204 - 285 MB | CPU
74
- | PSPNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 30.252 ms | 32 - 115 MB | NPU
75
- | PSPNet | ONNX | w8a8 | Qualcomm® QCS9075 | 34.05 ms | 70 - 73 MB | NPU
76
- | PSPNet | ONNX | w8a8 | Qualcomm® QCM6690 | 3145.346 ms | 63 - 74 MB | CPU
77
- | PSPNet | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 19.001 ms | 71 - 342 MB | NPU
78
- | PSPNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2605.807 ms | 91 - 103 MB | CPU
79
- | PSPNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.968 ms | 71 - 340 MB | NPU
80
- | PSPNet | QNN_DLC | float | Snapdragon® X2 Elite | 230.422 ms | 3 - 3 MB | NPU
81
- | PSPNet | QNN_DLC | float | Snapdragon® X Elite | 544.385 ms | 3 - 3 MB | NPU
82
- | PSPNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 621.548 ms | 0 - 873 MB | NPU
83
- | PSPNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 1865.275 ms | 2 - 722 MB | NPU
84
- | PSPNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 609.258 ms | 3 - 5 MB | NPU
85
- | PSPNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1698.164 ms | 0 - 429 MB | NPU
86
- | PSPNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 303.534 ms | 141 - 860 MB | NPU
87
- | PSPNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 270.855 ms | 1 - 734 MB | NPU
88
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 14.594 ms | 1 - 1 MB | NPU
89
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 26.084 ms | 1 - 1 MB | NPU
90
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 21.318 ms | 1 - 362 MB | NPU
91
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 63.872 ms | 1 - 263 MB | NPU
92
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 27.353 ms | 1 - 3 MB | NPU
93
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 32.019 ms | 1 - 35 MB | NPU
94
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 38.613 ms | 1 - 360 MB | NPU
95
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 18.41 ms | 1 - 233 MB | NPU
96
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 91.51 ms | 1 - 430 MB | NPU
97
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 15.938 ms | 1 - 238 MB | NPU
98
- | PSPNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 530.504 ms | 120 - 1170 MB | NPU
99
- | PSPNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 1684.384 ms | 121 - 956 MB | NPU
100
- | PSPNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 617.858 ms | 121 - 124 MB | NPU
101
- | PSPNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1564.358 ms | 44 - 617 MB | NPU
102
- | PSPNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 971.866 ms | 38 - 795 MB | NPU
103
- | PSPNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 328.449 ms | 128 - 965 MB | NPU
104
- | PSPNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 21.514 ms | 50 - 437 MB | NPU
105
- | PSPNet | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 66.574 ms | 32 - 304 MB | NPU
106
- | PSPNet | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 30.01 ms | 32 - 34 MB | NPU
107
- | PSPNet | TFLITE | w8a8 | Qualcomm® QCS9075 | 32.442 ms | 32 - 131 MB | NPU
108
- | PSPNet | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 40.322 ms | 18 - 403 MB | NPU
109
- | PSPNet | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 18.543 ms | 32 - 285 MB | NPU
110
- | PSPNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 95.006 ms | 32 - 445 MB | NPU
111
- | PSPNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 15.312 ms | 32 - 283 MB | NPU
112
 
113
  ## License
114
  * The license for the original implementation of PSPNet can be found
 
14
 
15
  PSPNet (Pyramid Scene Parsing Network) is a semantic segmentation model that captures global context information by applying pyramid pooling modules. It is designed to improve scene understanding by aggregating contextual features at multiple scales.
16
 
17
+ 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/tree/v0.49.1/qai_hub_models/models/pspnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
 
19
  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.
20
 
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.49.1/pspnet-onnx-float.zip)
31
+ | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.49.1/pspnet-onnx-w8a8.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.49.1/pspnet-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.49.1/pspnet-qnn_dlc-w8a8.zip)
34
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.49.1/pspnet-tflite-float.zip)
35
+ | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.49.1/pspnet-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[PSPNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/pspnet)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/pspnet) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
+ See our repository for [PSPNet on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/pspnet) for usage instructions.
50
 
51
  ## Model Details
52
 
 
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
+ | PSPNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 323.654 ms | 233 - 1001 MB | NPU
65
+ | PSPNet | ONNX | float | Snapdragon® X2 Elite | 427.869 ms | 266 - 266 MB | NPU
66
+ | PSPNet | ONNX | float | Snapdragon® X Elite | 695.005 ms | 529 - 529 MB | NPU
67
+ | PSPNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 506.756 ms | 136 - 1053 MB | NPU
68
+ | PSPNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 602.812 ms | 195 - 199 MB | NPU
69
+ | PSPNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 333.199 ms | 246 - 1003 MB | NPU
70
+ | PSPNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.884 ms | 72 - 340 MB | NPU
71
+ | PSPNet | ONNX | w8a8 | Snapdragon® X2 Elite | 15.251 ms | 131 - 131 MB | NPU
72
+ | PSPNet | ONNX | w8a8 | Snapdragon® X Elite | 28.661 ms | 133 - 133 MB | NPU
73
+ | PSPNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 22.334 ms | 72 - 494 MB | NPU
74
+ | PSPNet | ONNX | w8a8 | Qualcomm® QCS6490 | 3318.926 ms | 196 - 276 MB | CPU
75
+ | PSPNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 29.465 ms | 64 - 576 MB | NPU
76
+ | PSPNet | ONNX | w8a8 | Qualcomm® QCS9075 | 34.444 ms | 70 - 74 MB | NPU
77
+ | PSPNet | ONNX | w8a8 | Qualcomm® QCM6690 | 3277.178 ms | 95 - 110 MB | CPU
78
+ | PSPNet | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 19.038 ms | 72 - 343 MB | NPU
79
+ | PSPNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2589.577 ms | 50 - 62 MB | CPU
80
+ | PSPNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 269.084 ms | 3 - 741 MB | NPU
81
+ | PSPNet | QNN_DLC | float | Snapdragon® X2 Elite | 229.121 ms | 3 - 3 MB | NPU
82
+ | PSPNet | QNN_DLC | float | Snapdragon® X Elite | 545.535 ms | 3 - 3 MB | NPU
83
+ | PSPNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 623.685 ms | 0 - 874 MB | NPU
84
+ | PSPNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 1863.358 ms | 2 - 722 MB | NPU
85
+ | PSPNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 608.77 ms | 3 - 5 MB | NPU
86
+ | PSPNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1689.881 ms | 0 - 431 MB | NPU
87
+ | PSPNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 301.937 ms | 0 - 718 MB | NPU
88
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.214 ms | 1 - 239 MB | NPU
89
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 14.344 ms | 1 - 1 MB | NPU
90
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 26.117 ms | 1 - 1 MB | NPU
91
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 20.679 ms | 1 - 365 MB | NPU
92
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 63.897 ms | 1 - 263 MB | NPU
93
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 27.013 ms | 0 - 9 MB | NPU
94
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 31.865 ms | 0 - 34 MB | NPU
95
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 36.677 ms | 1 - 358 MB | NPU
96
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 18.068 ms | 1 - 234 MB | NPU
97
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 91.895 ms | 1 - 458 MB | NPU
98
+ | PSPNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 326.397 ms | 128 - 965 MB | NPU
99
+ | PSPNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 528.08 ms | 0 - 1049 MB | NPU
100
+ | PSPNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 1688.514 ms | 124 - 958 MB | NPU
101
+ | PSPNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 619.017 ms | 128 - 131 MB | NPU
102
+ | PSPNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1563.118 ms | 125 - 698 MB | NPU
103
+ | PSPNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 974.903 ms | 128 - 884 MB | NPU
104
+ | PSPNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 17.665 ms | 32 - 284 MB | NPU
105
+ | PSPNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 26.587 ms | 30 - 427 MB | NPU
106
+ | PSPNet | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 74.606 ms | 32 - 304 MB | NPU
107
+ | PSPNet | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 34.862 ms | 32 - 35 MB | NPU
108
+ | PSPNet | TFLITE | w8a8 | Qualcomm® QCS9075 | 38.16 ms | 32 - 131 MB | NPU
109
+ | PSPNet | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 55.328 ms | 32 - 417 MB | NPU
110
+ | PSPNet | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 22.633 ms | 32 - 286 MB | NPU
111
+ | PSPNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 356.021 ms | 384 - 904 MB | NPU
112
 
113
  ## License
114
  * The license for the original implementation of PSPNet can be found