Hugging Face's logo

qualcomm
/
AOT-GAN

Image-to-Image
PyTorch
android
Model card Files
xet
 Community
1
qaihm-bot commited on
Commit
f020e9f
·
verified ·
1 Parent(s): 2af83f3

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 +62 -62
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-to-image
14
  AOT-GAN is a machine learning model that allows to erase and in-paint part of given input image.
15
 
16
  This is based on the implementation of AOT-GAN found [here](https://github.com/researchmm/AOT-GAN-for-Inpainting).
17
- 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/aotgan) 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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/aotgan/releases/v0.47.0/aotgan-onnx-float.zip)
31
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/aotgan/releases/v0.47.0/aotgan-onnx-w8a16.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/aotgan/releases/v0.47.0/aotgan-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/aotgan/releases/v0.47.0/aotgan-qnn_dlc-w8a16.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/aotgan/releases/v0.47.0/aotgan-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[AOT-GAN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/aotgan)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/aotgan) 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 [AOT-GAN on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/aotgan) for usage instructions.
49
 
50
  ## Model Details
51
 
@@ -60,60 +60,60 @@ See our repository for [AOT-GAN on GitHub](https://github.com/quic/ai-hub-models
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
- | AOT-GAN | ONNX | float | Snapdragon® X Elite | 149.561 ms | 31 - 31 MB | NPU
64
- | AOT-GAN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 102.267 ms | 0 - 739 MB | NPU
65
- | AOT-GAN | ONNX | float | Qualcomm® QCS8550 (Proxy) | 146.589 ms | 0 - 457 MB | NPU
66
- | AOT-GAN | ONNX | float | Qualcomm® QCS9075 | 226.001 ms | 4 - 11 MB | NPU
67
- | AOT-GAN | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 78.791 ms | 6 - 633 MB | NPU
68
- | AOT-GAN | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 59.034 ms | 10 - 504 MB | NPU
69
- | AOT-GAN | ONNX | float | Snapdragon® X2 Elite | 61.048 ms | 32 - 32 MB | NPU
70
- | AOT-GAN | ONNX | w8a16 | Snapdragon® X Elite | 85.697 ms | 21 - 21 MB | NPU
71
- | AOT-GAN | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 61.863 ms | 5 - 715 MB | NPU
72
- | AOT-GAN | ONNX | w8a16 | Qualcomm® QCS6490 | 13192.303 ms | 393 - 396 MB | CPU
73
- | AOT-GAN | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 82.146 ms | 0 - 41 MB | NPU
74
- | AOT-GAN | ONNX | w8a16 | Qualcomm® QCS9075 | 109.839 ms | 5 - 8 MB | NPU
75
- | AOT-GAN | ONNX | w8a16 | Qualcomm® QCM6690 | 6693.772 ms | 328 - 336 MB | CPU
76
- | AOT-GAN | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 46.905 ms | 5 - 527 MB | NPU
77
- | AOT-GAN | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6586.752 ms | 324 - 333 MB | CPU
78
- | AOT-GAN | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 34.755 ms | 5 - 617 MB | NPU
79
- | AOT-GAN | ONNX | w8a16 | Snapdragon® X2 Elite | 37.831 ms | 23 - 23 MB | NPU
80
- | AOT-GAN | QNN_DLC | float | Snapdragon® X Elite | 125.33 ms | 4 - 4 MB | NPU
81
- | AOT-GAN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 88.875 ms | 3 - 729 MB | NPU
82
- | AOT-GAN | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 544.1 ms | 1 - 539 MB | NPU
83
- | AOT-GAN | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 123.911 ms | 4 - 7 MB | NPU
84
- | AOT-GAN | QNN_DLC | float | Qualcomm® SA8775P | 164.553 ms | 1 - 541 MB | NPU
85
- | AOT-GAN | QNN_DLC | float | Qualcomm® QCS9075 | 213.201 ms | 4 - 13 MB | NPU
86
- | AOT-GAN | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 206.059 ms | 3 - 643 MB | NPU
87
- | AOT-GAN | QNN_DLC | float | Qualcomm® SA7255P | 544.1 ms | 1 - 539 MB | NPU
88
- | AOT-GAN | QNN_DLC | float | Qualcomm® SA8295P | 179.664 ms | 1 - 477 MB | NPU
89
- | AOT-GAN | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 71.016 ms | 3 - 583 MB | NPU
90
- | AOT-GAN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 47.017 ms | 2 - 488 MB | NPU
91
- | AOT-GAN | QNN_DLC | float | Snapdragon® X2 Elite | 52.376 ms | 4 - 4 MB | NPU
92
- | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® X Elite | 84.389 ms | 2 - 2 MB | NPU
93
- | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 62.959 ms | 2 - 722 MB | NPU
94
- | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 298.385 ms | 1 - 6 MB | NPU
95
- | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 189.993 ms | 2 - 510 MB | NPU
96
- | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 82.726 ms | 2 - 612 MB | NPU
97
- | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® SA8775P | 82.085 ms | 2 - 512 MB | NPU
98
- | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 110.079 ms | 2 - 7 MB | NPU
99
- | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 1286.762 ms | 2 - 669 MB | NPU
100
- | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 144.598 ms | 2 - 711 MB | NPU
101
- | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® SA7255P | 189.993 ms | 2 - 510 MB | NPU
102
- | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® SA8295P | 115.664 ms | 2 - 511 MB | NPU
103
- | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 48.415 ms | 2 - 563 MB | NPU
104
- | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 124.262 ms | 2 - 671 MB | NPU
105
- | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 35.823 ms | 2 - 631 MB | NPU
106
- | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 38.732 ms | 2 - 2 MB | NPU
107
- | AOT-GAN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 89.569 ms | 3 - 768 MB | NPU
108
- | AOT-GAN | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 544.416 ms | 3 - 560 MB | NPU
109
- | AOT-GAN | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 123.17 ms | 3 - 5 MB | NPU
110
- | AOT-GAN | TFLITE | float | Qualcomm® SA8775P | 163.884 ms | 0 - 557 MB | NPU
111
- | AOT-GAN | TFLITE | float | Qualcomm® QCS9075 | 210.807 ms | 3 - 46 MB | NPU
112
- | AOT-GAN | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 200.48 ms | 3 - 676 MB | NPU
113
- | AOT-GAN | TFLITE | float | Qualcomm® SA7255P | 544.416 ms | 3 - 560 MB | NPU
114
- | AOT-GAN | TFLITE | float | Qualcomm® SA8295P | 179.019 ms | 0 - 488 MB | NPU
115
- | AOT-GAN | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 70.922 ms | 3 - 596 MB | NPU
116
- | AOT-GAN | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 46.972 ms | 1 - 503 MB | NPU
117
 
118
  ## License
119
  * The license for the original implementation of AOT-GAN can be found
 
14
  AOT-GAN is a machine learning model that allows to erase and in-paint part of given input image.
15
 
16
  This is based on the implementation of AOT-GAN found [here](https://github.com/researchmm/AOT-GAN-for-Inpainting).
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/aotgan) 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/aotgan/releases/v0.48.0/aotgan-onnx-float.zip)
31
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/aotgan/releases/v0.48.0/aotgan-onnx-w8a16.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/aotgan/releases/v0.48.0/aotgan-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/aotgan/releases/v0.48.0/aotgan-qnn_dlc-w8a16.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/aotgan/releases/v0.48.0/aotgan-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[AOT-GAN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/aotgan)**.
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/main/qai_hub_models/models/aotgan) 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 [AOT-GAN on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/aotgan) for usage instructions.
49
 
50
  ## Model Details
51
 
 
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
+ | AOT-GAN | ONNX | float | Snapdragon® X2 Elite | 61.291 ms | 32 - 32 MB | NPU
64
+ | AOT-GAN | ONNX | float | Snapdragon® X Elite | 149.23 ms | 31 - 31 MB | NPU
65
+ | AOT-GAN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 102.836 ms | 11 - 762 MB | NPU
66
+ | AOT-GAN | ONNX | float | Qualcomm® QCS8550 (Proxy) | 145.095 ms | 0 - 42 MB | NPU
67
+ | AOT-GAN | ONNX | float | Qualcomm® QCS9075 | 225.942 ms | 4 - 11 MB | NPU
68
+ | AOT-GAN | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 78.222 ms | 9 - 636 MB | NPU
69
+ | AOT-GAN | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 58.242 ms | 11 - 504 MB | NPU
70
+ | AOT-GAN | ONNX | w8a16 | Snapdragon® X2 Elite | 37.821 ms | 23 - 23 MB | NPU
71
+ | AOT-GAN | ONNX | w8a16 | Snapdragon® X Elite | 85.628 ms | 21 - 21 MB | NPU
72
+ | AOT-GAN | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 61.821 ms | 5 - 723 MB | NPU
73
+ | AOT-GAN | ONNX | w8a16 | Qualcomm® QCS6490 | 13218.859 ms | 394 - 396 MB | CPU
74
+ | AOT-GAN | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 82.195 ms | 0 - 25 MB | NPU
75
+ | AOT-GAN | ONNX | w8a16 | Qualcomm® QCS9075 | 109.763 ms | 5 - 8 MB | NPU
76
+ | AOT-GAN | ONNX | w8a16 | Qualcomm® QCM6690 | 6558.865 ms | 326 - 334 MB | CPU
77
+ | AOT-GAN | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 47.107 ms | 5 - 526 MB | NPU
78
+ | AOT-GAN | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6568.009 ms | 333 - 341 MB | CPU
79
+ | AOT-GAN | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 34.817 ms | 5 - 622 MB | NPU
80
+ | AOT-GAN | QNN_DLC | float | Snapdragon® X2 Elite | 52.604 ms | 4 - 4 MB | NPU
81
+ | AOT-GAN | QNN_DLC | float | Snapdragon® X Elite | 125.797 ms | 4 - 4 MB | NPU
82
+ | AOT-GAN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 89.365 ms | 2 - 726 MB | NPU
83
+ | AOT-GAN | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 545.515 ms | 1 - 540 MB | NPU
84
+ | AOT-GAN | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 124.651 ms | 4 - 732 MB | NPU
85
+ | AOT-GAN | QNN_DLC | float | Qualcomm® SA8775P | 164.958 ms | 1 - 540 MB | NPU
86
+ | AOT-GAN | QNN_DLC | float | Qualcomm® QCS9075 | 214.543 ms | 4 - 13 MB | NPU
87
+ | AOT-GAN | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 202.149 ms | 3 - 645 MB | NPU
88
+ | AOT-GAN | QNN_DLC | float | Qualcomm® SA7255P | 545.515 ms | 1 - 540 MB | NPU
89
+ | AOT-GAN | QNN_DLC | float | Qualcomm® SA8295P | 179.861 ms | 1 - 479 MB | NPU
90
+ | AOT-GAN | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 70.788 ms | 1 - 580 MB | NPU
91
+ | AOT-GAN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 47.377 ms | 4 - 490 MB | NPU
92
+ | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 39.686 ms | 2 - 2 MB | NPU
93
+ | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® X Elite | 84.221 ms | 2 - 2 MB | NPU
94
+ | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 62.909 ms | 1 - 718 MB | NPU
95
+ | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 298.491 ms | 1 - 6 MB | NPU
96
+ | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 190.225 ms | 2 - 511 MB | NPU
97
+ | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 82.536 ms | 2 - 4 MB | NPU
98
+ | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® SA8775P | 386.756 ms | 2 - 510 MB | NPU
99
+ | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 109.788 ms | 2 - 7 MB | NPU
100
+ | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 1325.187 ms | 2 - 666 MB | NPU
101
+ | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 146.613 ms | 2 - 717 MB | NPU
102
+ | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® SA7255P | 190.225 ms | 2 - 511 MB | NPU
103
+ | AOT-GAN | QNN_DLC | w8a16 | Qualcomm® SA8295P | 115.704 ms | 2 - 510 MB | NPU
104
+ | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 48.174 ms | 2 - 564 MB | NPU
105
+ | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 124.583 ms | 2 - 671 MB | NPU
106
+ | AOT-GAN | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 35.651 ms | 2 - 628 MB | NPU
107
+ | AOT-GAN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 88.814 ms | 3 - 761 MB | NPU
108
+ | AOT-GAN | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 543.046 ms | 3 - 559 MB | NPU
109
+ | AOT-GAN | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 124.537 ms | 3 - 6 MB | NPU
110
+ | AOT-GAN | TFLITE | float | Qualcomm® SA8775P | 163.926 ms | 3 - 560 MB | NPU
111
+ | AOT-GAN | TFLITE | float | Qualcomm® QCS9075 | 210.968 ms | 2 - 45 MB | NPU
112
+ | AOT-GAN | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 201.949 ms | 3 - 677 MB | NPU
113
+ | AOT-GAN | TFLITE | float | Qualcomm® SA7255P | 543.046 ms | 3 - 559 MB | NPU
114
+ | AOT-GAN | TFLITE | float | Qualcomm® SA8295P | 179.01 ms | 0 - 486 MB | NPU
115
+ | AOT-GAN | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 70.806 ms | 0 - 582 MB | NPU
116
+ | AOT-GAN | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 46.991 ms | 3 - 505 MB | NPU
117
 
118
  ## License
119
  * The license for the original implementation of AOT-GAN can be found