Hugging Face's logo

qualcomm
/
PSPNet

Image Segmentation
PyTorch
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
5f9e8a0
·
verified ·
1 Parent(s): f2bd4c0

v0.64.0

Browse files

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

Files changed (2) hide show
  1. README.md +37 -36
  2. release_assets.json +6 -6
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/v0.63.0/src/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
 
@@ -27,25 +27,25 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-onnx-float.zip)
31
- | ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-onnx-w8a8.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-qnn_dlc-w8a8.zip)
34
- | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[PSPNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/pspnet)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/pspnet) Python library to compile and export the model with your own:
42
  - Custom weights (e.g., fine-tuned checkpoints)
43
  - Custom input shapes
44
  - Target device and runtime configurations
45
 
46
  This option is ideal if you need to customize the model beyond the default configuration provided here.
47
 
48
- See our repository for [PSPNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/pspnet) for usage instructions.
49
 
50
  ## Model Details
51
 
@@ -86,36 +86,36 @@ See our repository for [PSPNet on GitHub](https://github.com/qualcomm/ai-hub-mod
86
  | PSPNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 147.868 ms | 71 - 572 MB | NPU
87
  | PSPNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 43.809 ms | 70 - 444 MB | NPU
88
  | PSPNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 147.868 ms | 71 - 572 MB | NPU
89
- | PSPNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 547.188 ms | 0 - 1652 MB | NPU
90
- | PSPNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 581.819 ms | 0 - 1591 MB | NPU
91
- | PSPNet | QNN_DLC | float | Snapdragon® X2 Elite | 545.139 ms | 3 - 3 MB | NPU
92
- | PSPNet | QNN_DLC | float | Snapdragon® X Elite | 789.801 ms | 3 - 3 MB | NPU
93
- | PSPNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 617.269 ms | 3 - 2800 MB | NPU
94
- | PSPNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1076.551 ms | 0 - 702 MB | NPU
95
- | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 912.417 ms | 3 - 136 MB | NPU
96
- | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 787.043 ms | 3 - 6 MB | NPU
97
  | PSPNet | QNN_DLC | float | Qualcomm® SA8650P | 2618.077 ms | 2 - 1308 MB | NPU
98
  | PSPNet | QNN_DLC | float | Qualcomm® SA8255P | 2618.077 ms | 2 - 1308 MB | NPU
99
- | PSPNet | QNN_DLC | float | Qualcomm® QCS8450 | 1076.551 ms | 0 - 702 MB | NPU
100
- | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 870.035 ms | 5 - 137 MB | NPU
101
- | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 789.801 ms | 3 - 3 MB | NPU
102
- | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 581.819 ms | 0 - 1591 MB | NPU
103
- | PSPNet | QNN_DLC | float | Qualcomm® SA8295P | 966.131 ms | 0 - 556 MB | NPU
104
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 41.119 ms | 1 - 570 MB | NPU
105
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 46.776 ms | 1 - 378 MB | NPU
106
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 37.145 ms | 1 - 1 MB | NPU
107
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 70.678 ms | 1 - 1 MB | NPU
108
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 57.117 ms | 1 - 594 MB | NPU
109
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 91.096 ms | 1 - 550 MB | NPU
110
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 75.61 ms | 1 - 36 MB | NPU
111
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 72.746 ms | 1 - 4 MB | NPU
112
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 91.096 ms | 1 - 550 MB | NPU
113
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 73.347 ms | 1 - 35 MB | NPU
114
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 70.678 ms | 1 - 1 MB | NPU
115
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 145.545 ms | 1 - 484 MB | NPU
116
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 46.776 ms | 1 - 378 MB | NPU
117
- | PSPNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 98.657 ms | 1 - 437 MB | NPU
118
- | PSPNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 145.545 ms | 1 - 484 MB | NPU
119
  | PSPNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 554.788 ms | 111 - 1804 MB | NPU
120
  | PSPNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 584.683 ms | 127 - 1760 MB | NPU
121
  | PSPNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 605.29 ms | 134 - 3020 MB | NPU
@@ -127,6 +127,7 @@ See our repository for [PSPNet on GitHub](https://github.com/qualcomm/ai-hub-mod
127
  | PSPNet | TFLITE | float | Qualcomm® QCS8450 | 1445.795 ms | 83 - 1008 MB | NPU
128
  | PSPNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 871.696 ms | 0 - 278 MB | NPU
129
  | PSPNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 584.683 ms | 127 - 1760 MB | NPU
 
130
  | PSPNet | TFLITE | float | Qualcomm® SA8295P | 890.415 ms | 93 - 807 MB | NPU
131
 
132
  ## License
 
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/v0.64.0/src/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 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-onnx-float.zip)
31
+ | ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-onnx-w8a8.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-qnn_dlc-w8a8.zip)
34
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[PSPNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/pspnet)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/pspnet) Python library to compile and export the model with your own:
42
  - Custom weights (e.g., fine-tuned checkpoints)
43
  - Custom input shapes
44
  - Target device and runtime configurations
45
 
46
  This option is ideal if you need to customize the model beyond the default configuration provided here.
47
 
48
+ See our repository for [PSPNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/pspnet) for usage instructions.
49
 
50
  ## Model Details
51
 
 
86
  | PSPNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 147.868 ms | 71 - 572 MB | NPU
87
  | PSPNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 43.809 ms | 70 - 444 MB | NPU
88
  | PSPNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 147.868 ms | 71 - 572 MB | NPU
89
+ | PSPNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 546.312 ms | 0 - 1652 MB | NPU
90
+ | PSPNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 571.78 ms | 3 - 1594 MB | NPU
91
+ | PSPNet | QNN_DLC | float | Snapdragon® X2 Elite | 545.219 ms | 3 - 3 MB | NPU
92
+ | PSPNet | QNN_DLC | float | Snapdragon® X Elite | 787.972 ms | 3 - 3 MB | NPU
93
+ | PSPNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 621.508 ms | 3 - 2801 MB | NPU
94
+ | PSPNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1073.257 ms | 0 - 703 MB | NPU
95
+ | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 913.255 ms | 3 - 136 MB | NPU
96
+ | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 797.908 ms | 3 - 1360 MB | NPU
97
  | PSPNet | QNN_DLC | float | Qualcomm® SA8650P | 2618.077 ms | 2 - 1308 MB | NPU
98
  | PSPNet | QNN_DLC | float | Qualcomm® SA8255P | 2618.077 ms | 2 - 1308 MB | NPU
99
+ | PSPNet | QNN_DLC | float | Qualcomm® QCS8450 | 1073.257 ms | 0 - 703 MB | NPU
100
+ | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 868.583 ms | 5 - 137 MB | NPU
101
+ | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 787.972 ms | 3 - 3 MB | NPU
102
+ | PSPNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 571.78 ms | 3 - 1594 MB | NPU
103
+ | PSPNet | QNN_DLC | float | Qualcomm® SA8295P | 966.467 ms | 10 - 566 MB | NPU
104
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 41.077 ms | 1 - 571 MB | NPU
105
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 49.024 ms | 0 - 376 MB | NPU
106
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 37.337 ms | 1 - 1 MB | NPU
107
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 70.915 ms | 1 - 1 MB | NPU
108
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 58.01 ms | 1 - 596 MB | NPU
109
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 92.296 ms | 1 - 550 MB | NPU
110
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 75.218 ms | 1 - 36 MB | NPU
111
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 75.224 ms | 1 - 548 MB | NPU
112
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 92.296 ms | 1 - 550 MB | NPU
113
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 73.595 ms | 1 - 35 MB | NPU
114
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 70.915 ms | 1 - 1 MB | NPU
115
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 146.11 ms | 1 - 486 MB | NPU
116
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 49.024 ms | 0 - 376 MB | NPU
117
+ | PSPNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 98.682 ms | 1 - 437 MB | NPU
118
+ | PSPNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 146.11 ms | 1 - 486 MB | NPU
119
  | PSPNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 554.788 ms | 111 - 1804 MB | NPU
120
  | PSPNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 584.683 ms | 127 - 1760 MB | NPU
121
  | PSPNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 605.29 ms | 134 - 3020 MB | NPU
 
127
  | PSPNet | TFLITE | float | Qualcomm® QCS8450 | 1445.795 ms | 83 - 1008 MB | NPU
128
  | PSPNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 871.696 ms | 0 - 278 MB | NPU
129
  | PSPNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 584.683 ms | 127 - 1760 MB | NPU
130
+ | PSPNet | TFLITE | float | Qualcomm® SA7255P | 11763.129 ms | 516 - 526 MB | CPU
131
  | PSPNet | TFLITE | float | Qualcomm® SA8295P | 890.415 ms | 93 - 807 MB | NPU
132
 
133
  ## License
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
8
  "qairt": "2.50.0.260828221209",
9
  "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.50.0.260828221209"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.50.0.260828221209"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,13 +31,13 @@
31
  "qairt": "2.50.0.260828221209",
32
  "onnx_runtime": "1.27.1"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-onnx-w8a8.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.50.0.260828221209"
39
  },
40
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.63.0/pspnet-qnn_dlc-w8a8.zip"
41
  }
42
  }
43
  }
 
1
  {
2
+ "version": "0.64.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.50.0.260828221209",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.50.0.260828221209"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.50.0.260828221209"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-tflite-float.zip"
24
  }
25
  }
26
  },
 
31
  "qairt": "2.50.0.260828221209",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-onnx-w8a8.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.50.0.260828221209"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pspnet/releases/v0.64.0/pspnet-qnn_dlc-w8a8.zip"
41
  }
42
  }
43
  }