Hugging Face's logo

qualcomm
/
SESR-M5

Image-to-Image
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
5ced008
·
verified ·
1 Parent(s): dd67bab

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 +71 -72
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
  SESR M5 performs efficient on-device upscaling of images.
15
 
16
  This is based on the implementation of SESR-M5 found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/sesr).
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/sesr_m5) 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 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sesr_m5/releases/v0.46.0/sesr_m5-onnx-float.zip)
31
- | ONNX | w8a8 | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sesr_m5/releases/v0.46.0/sesr_m5-onnx-w8a8.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sesr_m5/releases/v0.46.0/sesr_m5-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a8 | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sesr_m5/releases/v0.46.0/sesr_m5-qnn_dlc-w8a8.zip)
34
- | 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/sesr_m5/releases/v0.46.0/sesr_m5-tflite-float.zip)
35
- | 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/sesr_m5/releases/v0.46.0/sesr_m5-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[SESR-M5 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sesr_m5)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/sesr_m5) 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 [SESR-M5 on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/sesr_m5) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -62,73 +62,72 @@ See our repository for [SESR-M5 on GitHub](https://github.com/quic/ai-hub-models
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | SESR-M5 | ONNX | float | Snapdragon® X Elite | 2.261 ms | 8 - 8 MB | NPU
66
- | SESR-M5 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.615 ms | 0 - 101 MB | NPU
67
- | SESR-M5 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.321 ms | 0 - 4 MB | NPU
68
- | SESR-M5 | ONNX | float | Qualcomm® QCS9075 | 3.402 ms | 7 - 10 MB | NPU
69
- | SESR-M5 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.315 ms | 0 - 93 MB | NPU
70
- | SESR-M5 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.073 ms | 0 - 92 MB | NPU
71
- | SESR-M5 | ONNX | w8a8 | Snapdragon® X Elite | 0.892 ms | 3 - 3 MB | NPU
72
- | SESR-M5 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.748 ms | 0 - 100 MB | NPU
73
- | SESR-M5 | ONNX | w8a8 | Qualcomm® QCS6490 | 42.249 ms | 38 - 41 MB | CPU
74
- | SESR-M5 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.953 ms | 0 - 115 MB | NPU
75
- | SESR-M5 | ONNX | w8a8 | Qualcomm® QCS9075 | 1.222 ms | 0 - 3 MB | NPU
76
- | SESR-M5 | ONNX | w8a8 | Qualcomm® QCM6690 | 30.371 ms | 36 - 43 MB | CPU
77
- | SESR-M5 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.536 ms | 0 - 90 MB | NPU
78
- | SESR-M5 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 22.496 ms | 38 - 45 MB | CPU
79
- | SESR-M5 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.488 ms | 0 - 94 MB | NPU
80
- | SESR-M5 | QNN_DLC | float | Snapdragon® X Elite | 2.085 ms | 0 - 0 MB | NPU
81
- | SESR-M5 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.281 ms | 0 - 35 MB | NPU
82
- | SESR-M5 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 10.536 ms | 0 - 24 MB | NPU
83
- | SESR-M5 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.911 ms | 0 - 30 MB | NPU
84
- | SESR-M5 | QNN_DLC | float | Qualcomm® SA8775P | 3.023 ms | 0 - 25 MB | NPU
85
- | SESR-M5 | QNN_DLC | float | Qualcomm® QCS9075 | 3.06 ms | 0 - 5 MB | NPU
86
- | SESR-M5 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 2.788 ms | 0 - 38 MB | NPU
87
- | SESR-M5 | QNN_DLC | float | Qualcomm® SA7255P | 10.536 ms | 0 - 24 MB | NPU
88
- | SESR-M5 | QNN_DLC | float | Qualcomm® SA8295P | 3.462 ms | 0 - 21 MB | NPU
89
- | SESR-M5 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.035 ms | 0 - 28 MB | NPU
90
- | SESR-M5 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.873 ms | 0 - 27 MB | NPU
91
- | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.756 ms | 0 - 0 MB | NPU
92
- | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.446 ms | 0 - 31 MB | NPU
93
- | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.729 ms | 2 - 4 MB | NPU
94
- | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.93 ms | 0 - 24 MB | NPU
95
- | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.628 ms | 0 - 2 MB | NPU
96
- | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.843 ms | 0 - 23 MB | NPU
97
- | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.887 ms | 0 - 2 MB | NPU
98
- | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 6.844 ms | 0 - 134 MB | NPU
99
- | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.944 ms | 0 - 33 MB | NPU
100
- | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.93 ms | 0 - 24 MB | NPU
101
- | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.386 ms | 0 - 19 MB | NPU
102
- | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.384 ms | 0 - 21 MB | NPU
 
 
 
 
103
  | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.84 ms | 0 - 21 MB | NPU
104
- | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.316 ms | 0 - 24 MB | NPU
105
- | SESR-M5 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.283 ms | 0 - 35 MB | NPU
106
- | SESR-M5 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 59.86 ms | 3 - 21 MB | GPU
107
- | SESR-M5 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.872 ms | 0 - 2 MB | NPU
108
- | SESR-M5 | TFLITE | float | Qualcomm® SA8775P | 3.065 ms | 0 - 26 MB | NPU
109
- | SESR-M5 | TFLITE | float | Qualcomm® QCS9075 | 3.086 ms | 3 - 9 MB | NPU
110
- | SESR-M5 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2.8 ms | 0 - 37 MB | NPU
111
- | SESR-M5 | TFLITE | float | Qualcomm® SA7255P | 59.86 ms | 3 - 21 MB | GPU
112
- | SESR-M5 | TFLITE | float | Qualcomm® SA8295P | 3.441 ms | 0 - 22 MB | NPU
113
- | SESR-M5 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.041 ms | 0 - 24 MB | NPU
114
- | SESR-M5 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.874 ms | 0 - 28 MB | NPU
115
- | SESR-M5 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.448 ms | 0 - 31 MB | NPU
116
- | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.479 ms | 0 - 3 MB | NPU
117
- | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.971 ms | 0 - 23 MB | NPU
118
- | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.641 ms | 0 - 69 MB | NPU
119
- | SESR-M5 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.879 ms | 0 - 24 MB | NPU
120
- | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.91 ms | 0 - 3 MB | NPU
121
- | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCM6690 | 6.848 ms | 1 - 135 MB | NPU
122
- | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.952 ms | 0 - 32 MB | NPU
123
- | SESR-M5 | TFLITE | w8a8 | Qualcomm® SA7255P | 1.971 ms | 0 - 23 MB | NPU
124
- | SESR-M5 | TFLITE | w8a8 | Qualcomm® SA8295P | 1.392 ms | 0 - 20 MB | NPU
125
- | SESR-M5 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.383 ms | 0 - 21 MB | NPU
126
- | SESR-M5 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.847 ms | 0 - 21 MB | NPU
127
- | SESR-M5 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.315 ms | 0 - 24 MB | NPU
128
 
129
  ## License
130
  * The license for the original implementation of SESR-M5 can be found
131
- [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
132
 
133
  ## References
134
  * [Collapsible Linear Blocks for Super-Efficient Super Resolution](https://arxiv.org/abs/2103.09404)
 
14
  SESR M5 performs efficient on-device upscaling of images.
15
 
16
  This is based on the implementation of SESR-M5 found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/sesr).
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/sesr_m5) 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/sesr_m5/releases/v0.49.1/sesr_m5-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/sesr_m5/releases/v0.49.1/sesr_m5-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/sesr_m5/releases/v0.49.1/sesr_m5-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/sesr_m5/releases/v0.49.1/sesr_m5-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/sesr_m5/releases/v0.49.1/sesr_m5-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/sesr_m5/releases/v0.49.1/sesr_m5-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[SESR-M5 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sesr_m5)**.
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/sesr_m5) 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 [SESR-M5 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/sesr_m5) 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
+ | SESR-M5 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.969 ms | 0 - 25 MB | NPU
66
+ | SESR-M5 | ONNX | float | Snapdragon® X2 Elite | 1.144 ms | 6 - 6 MB | NPU
67
+ | SESR-M5 | ONNX | float | Snapdragon® X Elite | 2.203 ms | 8 - 8 MB | NPU
68
+ | SESR-M5 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.0 ms | 0 - 2 MB | NPU
69
+ | SESR-M5 | ONNX | float | Qualcomm® QCS9075 | 3.236 ms | 6 - 9 MB | NPU
70
+ | SESR-M5 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.206 ms | 0 - 21 MB | NPU
71
+ | SESR-M5 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.378 ms | 0 - 26 MB | NPU
72
+ | SESR-M5 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.407 ms | 1 - 1 MB | NPU
73
+ | SESR-M5 | ONNX | w8a8 | Snapdragon® X Elite | 0.929 ms | 3 - 3 MB | NPU
74
+ | SESR-M5 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.533 ms | 0 - 33 MB | NPU
75
+ | SESR-M5 | ONNX | w8a8 | Qualcomm® QCS6490 | 42.395 ms | 38 - 41 MB | CPU
76
+ | SESR-M5 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.785 ms | 0 - 24 MB | NPU
77
+ | SESR-M5 | ONNX | w8a8 | Qualcomm® QCS9075 | 0.981 ms | 0 - 3 MB | NPU
78
+ | SESR-M5 | ONNX | w8a8 | Qualcomm® QCM6690 | 31.12 ms | 38 - 44 MB | CPU
79
+ | SESR-M5 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.427 ms | 0 - 27 MB | NPU
80
+ | SESR-M5 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 23.759 ms | 38 - 45 MB | CPU
81
+ | SESR-M5 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.864 ms | 0 - 27 MB | NPU
82
+ | SESR-M5 | QNN_DLC | float | Snapdragon® X2 Elite | 1.19 ms | 0 - 0 MB | NPU
83
+ | SESR-M5 | QNN_DLC | float | Snapdragon® X Elite | 2.064 ms | 0 - 0 MB | NPU
84
+ | SESR-M5 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.275 ms | 0 - 35 MB | NPU
85
+ | SESR-M5 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 10.546 ms | 0 - 23 MB | NPU
86
+ | SESR-M5 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.882 ms | 0 - 26 MB | NPU
87
+ | SESR-M5 | QNN_DLC | float | Qualcomm® SA8775P | 3.015 ms | 0 - 25 MB | NPU
88
+ | SESR-M5 | QNN_DLC | float | Qualcomm® QCS9075 | 3.046 ms | 0 - 5 MB | NPU
89
+ | SESR-M5 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 2.796 ms | 0 - 37 MB | NPU
90
+ | SESR-M5 | QNN_DLC | float | Qualcomm® SA7255P | 10.546 ms | 0 - 23 MB | NPU
91
+ | SESR-M5 | QNN_DLC | float | Qualcomm® SA8295P | 3.469 ms | 0 - 21 MB | NPU
92
+ | SESR-M5 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.04 ms | 0 - 28 MB | NPU
93
+ | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.301 ms | 0 - 24 MB | NPU
94
+ | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.448 ms | 0 - 0 MB | NPU
95
+ | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.773 ms | 0 - 0 MB | NPU
96
+ | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.443 ms | 0 - 31 MB | NPU
97
+ | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.736 ms | 0 - 2 MB | NPU
98
+ | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.946 ms | 0 - 22 MB | NPU
99
+ | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.623 ms | 0 - 52 MB | NPU
100
+ | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.852 ms | 0 - 23 MB | NPU
101
+ | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.885 ms | 0 - 2 MB | NPU
102
+ | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 6.821 ms | 0 - 135 MB | NPU
103
+ | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.941 ms | 0 - 32 MB | NPU
104
+ | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.946 ms | 0 - 22 MB | NPU
105
+ | SESR-M5 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.393 ms | 0 - 20 MB | NPU
106
+ | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.38 ms | 0 - 21 MB | NPU
107
  | SESR-M5 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.84 ms | 0 - 21 MB | NPU
108
+ | SESR-M5 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.866 ms | 0 - 28 MB | NPU
109
+ | SESR-M5 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.281 ms | 0 - 35 MB | NPU
110
+ | SESR-M5 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 10.563 ms | 3 - 27 MB | NPU
111
+ | SESR-M5 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.888 ms | 0 - 2 MB | NPU
112
+ | SESR-M5 | TFLITE | float | Qualcomm® SA8775P | 3.078 ms | 0 - 26 MB | NPU
113
+ | SESR-M5 | TFLITE | float | Qualcomm® QCS9075 | 3.063 ms | 3 - 9 MB | NPU
114
+ | SESR-M5 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2.787 ms | 0 - 37 MB | NPU
115
+ | SESR-M5 | TFLITE | float | Qualcomm® SA7255P | 10.563 ms | 3 - 27 MB | NPU
116
+ | SESR-M5 | TFLITE | float | Qualcomm® SA8295P | 3.498 ms | 0 - 22 MB | NPU
117
+ | SESR-M5 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.038 ms | 0 - 24 MB | NPU
118
+ | SESR-M5 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.46 ms | 0 - 30 MB | NPU
119
+ | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.704 ms | 0 - 3 MB | NPU
120
+ | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.638 ms | 0 - 1 MB | NPU
121
+ | SESR-M5 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.887 ms | 0 - 24 MB | NPU
122
+ | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.9 ms | 0 - 3 MB | NPU
123
+ | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCM6690 | 6.837 ms | 1 - 135 MB | NPU
124
+ | SESR-M5 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.947 ms | 0 - 33 MB | NPU
125
+ | SESR-M5 | TFLITE | w8a8 | Qualcomm® SA8295P | 1.396 ms | 0 - 20 MB | NPU
126
+ | SESR-M5 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.377 ms | 0 - 21 MB | NPU
 
 
 
 
 
127
 
128
  ## License
129
  * The license for the original implementation of SESR-M5 can be found
130
+ [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.md).
131
 
132
  ## References
133
  * [Collapsible Linear Blocks for Super-Efficient Super Resolution](https://arxiv.org/abs/2103.09404)