Hugging Face's logo

qualcomm
/
ESRGAN

Image-to-Image
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
6f6ebd2
·
verified ·
1 Parent(s): 06c9ea6

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 +62 -33
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-to-image
14
  ESRGAN is a machine learning model that upscales an image with minimal loss in quality.
15
 
16
  This is based on the implementation of ESRGAN found [here](https://github.com/xinntao/ESRGAN/).
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/esrgan) 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
 
@@ -27,23 +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 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/esrgan/releases/v0.46.0/esrgan-onnx-float.zip)
31
- | QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/esrgan/releases/v0.46.0/esrgan-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/esrgan/releases/v0.46.0/esrgan-tflite-float.zip)
 
 
33
 
34
  For more device-specific assets and performance metrics, visit **[ESRGAN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/esrgan)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/esrgan) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
- See our repository for [ESRGAN on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/esrgan) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -58,33 +60,60 @@ See our repository for [ESRGAN on GitHub](https://github.com/quic/ai-hub-models/
58
  ## Performance Summary
59
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
  |---|---|---|---|---|---|---
61
- | ESRGAN | ONNX | float | Snapdragon® X Elite | 65.559 ms | 38 - 38 MB | NPU
62
- | ESRGAN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 51.0 ms | 7 - 697 MB | NPU
63
- | ESRGAN | ONNX | float | Qualcomm® QCS8550 (Proxy) | 65.676 ms | 0 - 45 MB | NPU
64
- | ESRGAN | ONNX | float | Qualcomm® QCS9075 | 106.901 ms | 6 - 9 MB | NPU
65
- | ESRGAN | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.988 ms | 7 - 257 MB | NPU
66
- | ESRGAN | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 28.071 ms | 0 - 261 MB | NPU
67
- | ESRGAN | QNN_DLC | float | Snapdragon® X Elite | 64.947 ms | 0 - 0 MB | NPU
68
- | ESRGAN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 49.399 ms | 0 - 748 MB | NPU
69
- | ESRGAN | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 451.839 ms | 0 - 347 MB | NPU
70
- | ESRGAN | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 62.453 ms | 0 - 3 MB | NPU
71
- | ESRGAN | QNN_DLC | float | Qualcomm® SA8775P | 105.38 ms | 0 - 347 MB | NPU
72
- | ESRGAN | QNN_DLC | float | Qualcomm® QCS9075 | 106.848 ms | 0 - 5 MB | NPU
73
- | ESRGAN | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 112.556 ms | 0 - 753 MB | NPU
74
- | ESRGAN | QNN_DLC | float | Qualcomm® SA7255P | 451.839 ms | 0 - 347 MB | NPU
75
- | ESRGAN | QNN_DLC | float | Qualcomm® SA8295P | 111.274 ms | 0 - 357 MB | NPU
76
- | ESRGAN | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.15 ms | 0 - 332 MB | NPU
77
- | ESRGAN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 25.883 ms | 0 - 331 MB | NPU
78
- | ESRGAN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 49.641 ms | 3 - 798 MB | NPU
79
- | ESRGAN | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 451.971 ms | 7 - 398 MB | NPU
80
- | ESRGAN | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 59.589 ms | 3 - 6 MB | NPU
81
- | ESRGAN | TFLITE | float | Qualcomm® SA8775P | 105.469 ms | 3 - 394 MB | NPU
82
- | ESRGAN | TFLITE | float | Qualcomm® QCS9075 | 107.96 ms | 3 - 47 MB | NPU
83
- | ESRGAN | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 122.167 ms | 3 - 797 MB | NPU
84
- | ESRGAN | TFLITE | float | Qualcomm® SA7255P | 451.971 ms | 7 - 398 MB | NPU
85
- | ESRGAN | TFLITE | float | Qualcomm® SA8295P | 111.299 ms | 3 - 398 MB | NPU
86
- | ESRGAN | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.09 ms | 3 - 376 MB | NPU
87
- | ESRGAN | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.14 ms | 1 - 374 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
 
89
  ## License
90
  * The license for the original implementation of ESRGAN can be found
 
14
  ESRGAN is a machine learning model that upscales an image with minimal loss in quality.
15
 
16
  This is based on the implementation of ESRGAN found [here](https://github.com/xinntao/ESRGAN/).
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/esrgan) 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/esrgan/releases/v0.49.1/esrgan-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/esrgan/releases/v0.49.1/esrgan-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/esrgan/releases/v0.49.1/esrgan-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/esrgan/releases/v0.49.1/esrgan-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/esrgan/releases/v0.49.1/esrgan-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[ESRGAN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/esrgan)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/esrgan) 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 [ESRGAN on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/esrgan) 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
+ | ESRGAN | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 28.538 ms | 7 - 353 MB | NPU
64
+ | ESRGAN | ONNX | float | Snapdragon® X2 Elite | 34.444 ms | 37 - 37 MB | NPU
65
+ | ESRGAN | ONNX | float | Snapdragon® X Elite | 65.508 ms | 37 - 37 MB | NPU
66
+ | ESRGAN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 49.826 ms | 7 - 788 MB | NPU
67
+ | ESRGAN | ONNX | float | Qualcomm® QCS8550 (Proxy) | 70.495 ms | 0 - 44 MB | NPU
68
+ | ESRGAN | ONNX | float | Qualcomm® QCS9075 | 106.789 ms | 6 - 9 MB | NPU
69
+ | ESRGAN | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.098 ms | 2 - 348 MB | NPU
70
+ | ESRGAN | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 16.934 ms | 3 - 1057 MB | NPU
71
+ | ESRGAN | ONNX | w8a16 | Snapdragon® X2 Elite | 22.032 ms | 29 - 29 MB | NPU
72
+ | ESRGAN | ONNX | w8a16 | Snapdragon® X Elite | 43.59 ms | 26 - 26 MB | NPU
73
+ | ESRGAN | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 31.864 ms | 3 - 1277 MB | NPU
74
+ | ESRGAN | ONNX | w8a16 | Qualcomm® QCS6490 | 15432.176 ms | 201 - 206 MB | CPU
75
+ | ESRGAN | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 42.578 ms | 0 - 33 MB | NPU
76
+ | ESRGAN | ONNX | w8a16 | Qualcomm® QCS9075 | 45.3 ms | 3 - 6 MB | NPU
77
+ | ESRGAN | ONNX | w8a16 | Qualcomm® QCM6690 | 7969.71 ms | 183 - 205 MB | CPU
78
+ | ESRGAN | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 26.4 ms | 3 - 906 MB | NPU
79
+ | ESRGAN | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7740.946 ms | 146 - 165 MB | CPU
80
+ | ESRGAN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 26.79 ms | 0 - 327 MB | NPU
81
+ | ESRGAN | QNN_DLC | float | Snapdragon® X2 Elite | 34.26 ms | 0 - 0 MB | NPU
82
+ | ESRGAN | QNN_DLC | float | Snapdragon® X Elite | 64.939 ms | 0 - 0 MB | NPU
83
+ | ESRGAN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 49.222 ms | 0 - 750 MB | NPU
84
+ | ESRGAN | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 451.992 ms | 0 - 348 MB | NPU
85
+ | ESRGAN | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 63.691 ms | 0 - 13 MB | NPU
86
+ | ESRGAN | QNN_DLC | float | Qualcomm® SA8775P | 503.818 ms | 0 - 348 MB | NPU
87
+ | ESRGAN | QNN_DLC | float | Qualcomm® QCS9075 | 106.514 ms | 0 - 5 MB | NPU
88
+ | ESRGAN | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 124.339 ms | 0 - 754 MB | NPU
89
+ | ESRGAN | QNN_DLC | float | Qualcomm® SA7255P | 451.992 ms | 0 - 348 MB | NPU
90
+ | ESRGAN | QNN_DLC | float | Qualcomm® SA8295P | 111.36 ms | 0 - 357 MB | NPU
91
+ | ESRGAN | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.175 ms | 0 - 333 MB | NPU
92
+ | ESRGAN | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 17.147 ms | 0 - 985 MB | NPU
93
+ | ESRGAN | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 22.043 ms | 0 - 0 MB | NPU
94
+ | ESRGAN | QNN_DLC | w8a16 | Snapdragon® X Elite | 43.159 ms | 0 - 0 MB | NPU
95
+ | ESRGAN | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 31.434 ms | 0 - 1192 MB | NPU
96
+ | ESRGAN | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 241.211 ms | 0 - 3 MB | NPU
97
+ | ESRGAN | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 132.69 ms | 0 - 668 MB | NPU
98
+ | ESRGAN | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 41.561 ms | 0 - 3 MB | NPU
99
+ | ESRGAN | QNN_DLC | w8a16 | Qualcomm® SA8775P | 37.772 ms | 0 - 668 MB | NPU
100
+ | ESRGAN | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 44.05 ms | 0 - 3 MB | NPU
101
+ | ESRGAN | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 1138.246 ms | 0 - 645 MB | NPU
102
+ | ESRGAN | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 77.4 ms | 1 - 1275 MB | NPU
103
+ | ESRGAN | QNN_DLC | w8a16 | Qualcomm® SA7255P | 132.69 ms | 0 - 668 MB | NPU
104
+ | ESRGAN | QNN_DLC | w8a16 | Qualcomm® SA8295P | 64.975 ms | 0 - 712 MB | NPU
105
+ | ESRGAN | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 28.332 ms | 0 - 839 MB | NPU
106
+ | ESRGAN | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 89.218 ms | 0 - 703 MB | NPU
107
+ | ESRGAN | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.777 ms | 3 - 371 MB | NPU
108
+ | ESRGAN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 48.58 ms | 1 - 798 MB | NPU
109
+ | ESRGAN | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 452.045 ms | 3 - 391 MB | NPU
110
+ | ESRGAN | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 59.672 ms | 3 - 6 MB | NPU
111
+ | ESRGAN | TFLITE | float | Qualcomm® SA8775P | 105.566 ms | 3 - 392 MB | NPU
112
+ | ESRGAN | TFLITE | float | Qualcomm® QCS9075 | 107.995 ms | 3 - 47 MB | NPU
113
+ | ESRGAN | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 118.399 ms | 4 - 796 MB | NPU
114
+ | ESRGAN | TFLITE | float | Qualcomm® SA7255P | 452.045 ms | 3 - 391 MB | NPU
115
+ | ESRGAN | TFLITE | float | Qualcomm® SA8295P | 111.389 ms | 3 - 396 MB | NPU
116
+ | ESRGAN | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 37.517 ms | 3 - 364 MB | NPU
117
 
118
  ## License
119
  * The license for the original implementation of ESRGAN can be found