Hugging Face's logo

qualcomm
/
QuickSRNetLarge

Image-to-Image
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
76da9b4
·
verified ·
1 Parent(s): 6c102fa

v0.49.1

Browse files

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

Files changed (2) hide show
  1. LICENSE +1 -1
  2. README.md +72 -61
LICENSE CHANGED
@@ -1 +1 @@
1
- The license of the original trained model can be found at https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf.
 
1
+ The license of the original trained model can be found at https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.md.
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-to-image
14
  QuickSRNet Large is designed for upscaling images on mobile platforms to sharpen in real-time.
15
 
16
  This is based on the implementation of QuickSRNetLarge found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet).
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/quicksrnetlarge) 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 +27,26 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/releases/v0.46.0/quicksrnetlarge-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/quicksrnetlarge/releases/v0.46.0/quicksrnetlarge-qnn_dlc-float.zip)
32
- | QNN_DLC | w8a8 | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/releases/v0.46.0/quicksrnetlarge-qnn_dlc-w8a8.zip)
33
- | 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/quicksrnetlarge/releases/v0.46.0/quicksrnetlarge-tflite-float.zip)
34
- | TFLITE | w8a8 | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/quicksrnetlarge/releases/v0.46.0/quicksrnetlarge-tflite-w8a8.zip)
 
35
 
36
  For more device-specific assets and performance metrics, visit **[QuickSRNetLarge on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/quicksrnetlarge)**.
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/quicksrnetlarge) 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 [QuickSRNetLarge on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/quicksrnetlarge) for usage instructions.
49
 
50
  ## Model Details
51
 
@@ -61,64 +62,74 @@ See our repository for [QuickSRNetLarge on GitHub](https://github.com/quic/ai-hu
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
- | QuickSRNetLarge | ONNX | float | Snapdragon® X Elite | 2.289 ms | 7 - 7 MB | NPU
65
- | QuickSRNetLarge | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.721 ms | 0 - 103 MB | NPU
66
- | QuickSRNetLarge | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.355 ms | 0 - 59 MB | NPU
67
- | QuickSRNetLarge | ONNX | float | Qualcomm® QCS9075 | 3.723 ms | 7 - 10 MB | NPU
68
- | QuickSRNetLarge | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.354 ms | 0 - 92 MB | NPU
69
- | QuickSRNetLarge | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.054 ms | 0 - 91 MB | NPU
70
- | QuickSRNetLarge | QNN_DLC | float | Snapdragon® X Elite | 2.019 ms | 0 - 0 MB | NPU
71
- | QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.29 ms | 0 - 37 MB | NPU
72
- | QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 11.865 ms | 0 - 22 MB | NPU
73
- | QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.825 ms | 0 - 1 MB | NPU
74
- | QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8775P | 14.61 ms | 0 - 25 MB | NPU
75
- | QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS9075 | 3.349 ms | 0 - 5 MB | NPU
 
 
 
 
 
 
 
 
 
 
76
  | QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.288 ms | 0 - 38 MB | NPU
77
- | QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA7255P | 11.865 ms | 0 - 22 MB | NPU
78
- | QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8295P | 3.937 ms | 0 - 20 MB | NPU
79
- | QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.04 ms | 0 - 22 MB | NPU
80
- | QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.831 ms | 0 - 27 MB | NPU
81
- | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.738 ms | 0 - 0 MB | NPU
82
- | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.395 ms | 0 - 32 MB | NPU
83
- | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.713 ms | 2 - 4 MB | NPU
84
- | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.947 ms | 0 - 22 MB | NPU
85
- | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.589 ms | 0 - 1 MB | NPU
86
- | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.771 ms | 0 - 23 MB | NPU
87
- | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.832 ms | 2 - 4 MB | NPU
88
- | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 8.347 ms | 0 - 134 MB | NPU
89
- | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.857 ms | 0 - 32 MB | NPU
90
- | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.947 ms | 0 - 22 MB | NPU
91
- | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.343 ms | 0 - 20 MB | NPU
92
- | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.345 ms | 0 - 21 MB | NPU
93
- | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.884 ms | 0 - 21 MB | NPU
94
- | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.266 ms | 0 - 24 MB | NPU
95
- | QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.461 ms | 0 - 40 MB | NPU
96
- | QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 12.085 ms | 3 - 29 MB | NPU
97
- | QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.154 ms | 0 - 1 MB | NPU
98
- | QuickSRNetLarge | TFLITE | float | Qualcomm® SA8775P | 3.734 ms | 0 - 26 MB | NPU
99
- | QuickSRNetLarge | TFLITE | float | Qualcomm® QCS9075 | 3.697 ms | 3 - 9 MB | NPU
100
- | QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.514 ms | 0 - 40 MB | NPU
101
- | QuickSRNetLarge | TFLITE | float | Qualcomm® SA7255P | 12.085 ms | 3 - 29 MB | NPU
102
- | QuickSRNetLarge | TFLITE | float | Qualcomm® SA8295P | 4.177 ms | 0 - 22 MB | NPU
103
- | QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.094 ms | 0 - 24 MB | NPU
104
- | QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.872 ms | 0 - 28 MB | NPU
 
105
  | QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.483 ms | 0 - 34 MB | NPU
106
- | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.695 ms | 0 - 3 MB | NPU
107
- | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.228 ms | 0 - 26 MB | NPU
108
- | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.766 ms | 0 - 1 MB | NPU
109
- | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8775P | 0.994 ms | 0 - 27 MB | NPU
110
- | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.965 ms | 0 - 3 MB | NPU
111
- | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCM6690 | 8.51 ms | 0 - 136 MB | NPU
112
- | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.034 ms | 0 - 35 MB | NPU
113
- | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA7255P | 2.228 ms | 0 - 26 MB | NPU
114
- | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8295P | 1.476 ms | 0 - 23 MB | NPU
115
- | QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.371 ms | 0 - 26 MB | NPU
116
- | QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.977 ms | 0 - 23 MB | NPU
117
- | QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.331 ms | 0 - 26 MB | NPU
118
 
119
  ## License
120
  * The license for the original implementation of QuickSRNetLarge can be found
121
- [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
122
 
123
  ## References
124
  * [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://arxiv.org/abs/2303.04336)
 
14
  QuickSRNet Large is designed for upscaling images on mobile platforms to sharpen in real-time.
15
 
16
  This is based on the implementation of QuickSRNetLarge found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet).
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/quicksrnetlarge) 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/quicksrnetlarge/releases/v0.49.1/quicksrnetlarge-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/quicksrnetlarge/releases/v0.49.1/quicksrnetlarge-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/quicksrnetlarge/releases/v0.49.1/quicksrnetlarge-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/quicksrnetlarge/releases/v0.49.1/quicksrnetlarge-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/quicksrnetlarge/releases/v0.49.1/quicksrnetlarge-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/quicksrnetlarge/releases/v0.49.1/quicksrnetlarge-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[QuickSRNetLarge on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/quicksrnetlarge)**.
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/quicksrnetlarge) 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 [QuickSRNetLarge on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/quicksrnetlarge) for usage instructions.
50
 
51
  ## Model Details
52
 
 
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
+ | QuickSRNetLarge | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.938 ms | 0 - 23 MB | NPU
66
+ | QuickSRNetLarge | ONNX | float | Snapdragon® X2 Elite | 1.779 ms | 6 - 6 MB | NPU
67
+ | QuickSRNetLarge | ONNX | float | Snapdragon® X Elite | 2.172 ms | 8 - 8 MB | NPU
68
+ | QuickSRNetLarge | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.501 ms | 0 - 39 MB | NPU
69
+ | QuickSRNetLarge | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.98 ms | 0 - 2 MB | NPU
70
+ | QuickSRNetLarge | ONNX | float | Qualcomm® QCS9075 | 3.524 ms | 7 - 9 MB | NPU
71
+ | QuickSRNetLarge | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.26 ms | 0 - 24 MB | NPU
72
+ | QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.341 ms | 0 - 27 MB | CPU
73
+ | QuickSRNetLarge | ONNX | w8a8 | Snapdragon® X2 Elite | 0.388 ms | 3 - 3 MB | CPU
74
+ | QuickSRNetLarge | ONNX | w8a8 | Snapdragon® X Elite | 0.877 ms | 3 - 3 MB | CPU
75
+ | QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.501 ms | 0 - 36 MB | CPU
76
+ | QuickSRNetLarge | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.749 ms | 0 - 3 MB | CPU
77
+ | QuickSRNetLarge | ONNX | w8a8 | Qualcomm® QCS9075 | 0.965 ms | 0 - 3 MB | CPU
78
+ | QuickSRNetLarge | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.392 ms | 0 - 28 MB | CPU
79
+ | QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.82 ms | 0 - 26 MB | NPU
80
+ | QuickSRNetLarge | QNN_DLC | float | Snapdragon® X2 Elite | 1.213 ms | 0 - 0 MB | NPU
81
+ | QuickSRNetLarge | QNN_DLC | float | Snapdragon® X Elite | 1.989 ms | 0 - 0 MB | NPU
82
+ | QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.293 ms | 0 - 36 MB | NPU
83
+ | QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 11.859 ms | 0 - 22 MB | NPU
84
+ | QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.823 ms | 0 - 24 MB | NPU
85
+ | QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8775P | 3.422 ms | 0 - 24 MB | NPU
86
+ | QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS9075 | 3.363 ms | 0 - 5 MB | NPU
87
  | QuickSRNetLarge | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.288 ms | 0 - 38 MB | NPU
88
+ | QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA7255P | 11.859 ms | 0 - 22 MB | NPU
89
+ | QuickSRNetLarge | QNN_DLC | float | Qualcomm® SA8295P | 3.923 ms | 0 - 20 MB | NPU
90
+ | QuickSRNetLarge | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.049 ms | 0 - 26 MB | NPU
91
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.248 ms | 0 - 24 MB | NPU
92
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.388 ms | 0 - 0 MB | NPU
93
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.733 ms | 0 - 0 MB | NPU
94
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.399 ms | 0 - 32 MB | NPU
95
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.777 ms | 0 - 2 MB | NPU
96
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.942 ms | 0 - 24 MB | NPU
97
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.587 ms | 0 - 2 MB | NPU
98
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8775P | 3.093 ms | 0 - 23 MB | NPU
99
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.835 ms | 0 - 2 MB | NPU
100
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 8.358 ms | 0 - 134 MB | NPU
101
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.852 ms | 0 - 32 MB | NPU
102
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.942 ms | 0 - 24 MB | NPU
103
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.357 ms | 0 - 20 MB | NPU
104
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.336 ms | 0 - 21 MB | NPU
105
+ | QuickSRNetLarge | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.877 ms | 0 - 21 MB | NPU
106
+ | QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.863 ms | 0 - 28 MB | NPU
107
+ | QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.463 ms | 0 - 39 MB | NPU
108
+ | QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 12.301 ms | 3 - 29 MB | NPU
109
+ | QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.124 ms | 0 - 1 MB | NPU
110
+ | QuickSRNetLarge | TFLITE | float | Qualcomm® SA8775P | 3.77 ms | 0 - 26 MB | NPU
111
+ | QuickSRNetLarge | TFLITE | float | Qualcomm® QCS9075 | 3.716 ms | 3 - 9 MB | NPU
112
+ | QuickSRNetLarge | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.521 ms | 0 - 40 MB | NPU
113
+ | QuickSRNetLarge | TFLITE | float | Qualcomm® SA7255P | 12.301 ms | 3 - 29 MB | NPU
114
+ | QuickSRNetLarge | TFLITE | float | Qualcomm® SA8295P | 4.193 ms | 3 - 24 MB | NPU
115
+ | QuickSRNetLarge | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.09 ms | 0 - 29 MB | NPU
116
+ | QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.287 ms | 0 - 26 MB | NPU
117
  | QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.483 ms | 0 - 34 MB | NPU
118
+ | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.954 ms | 0 - 3 MB | NPU
119
+ | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.199 ms | 0 - 25 MB | NPU
120
+ | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.776 ms | 0 - 17 MB | NPU
121
+ | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8775P | 0.997 ms | 0 - 26 MB | NPU
122
+ | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.966 ms | 0 - 3 MB | NPU
123
+ | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCM6690 | 8.485 ms | 0 - 140 MB | NPU
124
+ | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.063 ms | 0 - 36 MB | NPU
125
+ | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA7255P | 2.199 ms | 0 - 25 MB | NPU
126
+ | QuickSRNetLarge | TFLITE | w8a8 | Qualcomm® SA8295P | 1.439 ms | 0 - 22 MB | NPU
127
+ | QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.365 ms | 0 - 27 MB | NPU
128
+ | QuickSRNetLarge | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.98 ms | 0 - 23 MB | NPU
 
129
 
130
  ## License
131
  * The license for the original implementation of QuickSRNetLarge can be found
132
+ [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.md).
133
 
134
  ## References
135
  * [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://arxiv.org/abs/2303.04336)