Image Classification
PyTorch
backbone
android
qaihm-bot commited on
Commit
6176d3e
·
verified ·
1 Parent(s): 3ba55a1

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

Files changed (1) hide show
  1. README.md +74 -74
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
15
  RegNet is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
16
 
17
  This is based on the implementation of RegNet found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/regnet.py).
18
- 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/regnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
@@ -28,26 +28,26 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | 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/regnet/releases/v0.48.0/regnet-onnx-float.zip)
32
- | 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/regnet/releases/v0.48.0/regnet-onnx-w8a8.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.48.0/regnet-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.48.0/regnet-qnn_dlc-w8a8.zip)
35
- | 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/regnet/releases/v0.48.0/regnet-tflite-float.zip)
36
- | 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/regnet/releases/v0.48.0/regnet-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[RegNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/regnet)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/regnet) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
- See our repository for [RegNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/regnet) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,73 +63,73 @@ See our repository for [RegNet on GitHub](https://github.com/qualcomm/ai-hub-mod
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | RegNet | ONNX | float | Snapdragon® X2 Elite | 0.906 ms | 39 - 39 MB | NPU
67
- | RegNet | ONNX | float | Snapdragon® X Elite | 1.958 ms | 39 - 39 MB | NPU
68
- | RegNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.24 ms | 0 - 141 MB | NPU
69
- | RegNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.751 ms | 0 - 54 MB | NPU
70
- | RegNet | ONNX | float | Qualcomm® QCS9075 | 2.856 ms | 0 - 4 MB | NPU
71
- | RegNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.013 ms | 0 - 88 MB | NPU
72
- | RegNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.836 ms | 1 - 88 MB | NPU
73
- | RegNet | ONNX | w8a8 | Snapdragon® X2 Elite | 0.518 ms | 20 - 20 MB | NPU
74
- | RegNet | ONNX | w8a8 | Snapdragon® X Elite | 1.103 ms | 20 - 20 MB | NPU
75
- | RegNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.652 ms | 0 - 133 MB | NPU
76
- | RegNet | ONNX | w8a8 | Qualcomm® QCS6490 | 28.232 ms | 8 - 20 MB | CPU
77
- | RegNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.895 ms | 0 - 30 MB | NPU
78
- | RegNet | ONNX | w8a8 | Qualcomm® QCS9075 | 1.077 ms | 0 - 3 MB | NPU
79
- | RegNet | ONNX | w8a8 | Qualcomm® QCM6690 | 18.271 ms | 7 - 16 MB | CPU
80
- | RegNet | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.545 ms | 0 - 79 MB | NPU
81
- | RegNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 13.94 ms | 8 - 17 MB | CPU
82
- | RegNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.511 ms | 0 - 89 MB | NPU
83
- | RegNet | QNN_DLC | float | Snapdragon® X2 Elite | 1.227 ms | 1 - 1 MB | NPU
84
- | RegNet | QNN_DLC | float | Snapdragon® X Elite | 2.327 ms | 1 - 1 MB | NPU
85
- | RegNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.399 ms | 0 - 127 MB | NPU
86
- | RegNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 9.918 ms | 1 - 77 MB | NPU
87
- | RegNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.079 ms | 1 - 2 MB | NPU
88
- | RegNet | QNN_DLC | float | Qualcomm® SA8775P | 3.286 ms | 1 - 79 MB | NPU
89
- | RegNet | QNN_DLC | float | Qualcomm® QCS9075 | 3.068 ms | 1 - 3 MB | NPU
90
- | RegNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.483 ms | 0 - 117 MB | NPU
91
- | RegNet | QNN_DLC | float | Qualcomm® SA7255P | 9.918 ms | 1 - 77 MB | NPU
92
- | RegNet | QNN_DLC | float | Qualcomm® SA8295P | 3.528 ms | 0 - 65 MB | NPU
93
- | RegNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.121 ms | 1 - 78 MB | NPU
94
- | RegNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.9 ms | 1 - 81 MB | NPU
95
- | RegNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.598 ms | 0 - 0 MB | NPU
96
- | RegNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.073 ms | 0 - 0 MB | NPU
97
- | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.643 ms | 0 - 110 MB | NPU
98
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.693 ms | 0 - 2 MB | NPU
99
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.288 ms | 0 - 76 MB | NPU
100
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.888 ms | 0 - 2 MB | NPU
101
- | RegNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 4.983 ms | 0 - 76 MB | NPU
102
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.081 ms | 2 - 4 MB | NPU
103
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 7.096 ms | 0 - 197 MB | NPU
104
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.366 ms | 0 - 110 MB | NPU
105
- | RegNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.288 ms | 0 - 76 MB | NPU
106
- | RegNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.636 ms | 0 - 75 MB | NPU
107
- | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.487 ms | 0 - 76 MB | NPU
108
- | RegNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.148 ms | 0 - 77 MB | NPU
109
- | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.441 ms | 0 - 80 MB | NPU
110
- | RegNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.408 ms | 0 - 160 MB | NPU
111
- | RegNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 9.901 ms | 0 - 101 MB | NPU
112
- | RegNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.047 ms | 0 - 2 MB | NPU
113
- | RegNet | TFLITE | float | Qualcomm® SA8775P | 14.216 ms | 0 - 100 MB | NPU
114
- | RegNet | TFLITE | float | Qualcomm® QCS9075 | 3.056 ms | 0 - 42 MB | NPU
115
- | RegNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.448 ms | 0 - 142 MB | NPU
116
- | RegNet | TFLITE | float | Qualcomm® SA7255P | 9.901 ms | 0 - 101 MB | NPU
117
- | RegNet | TFLITE | float | Qualcomm® SA8295P | 3.497 ms | 0 - 83 MB | NPU
118
- | RegNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.109 ms | 0 - 104 MB | NPU
119
- | RegNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.895 ms | 0 - 104 MB | NPU
120
- | RegNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.54 ms | 0 - 119 MB | NPU
121
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.257 ms | 0 - 21 MB | NPU
 
122
  | RegNet | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.984 ms | 0 - 74 MB | NPU
123
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.731 ms | 0 - 3 MB | NPU
124
- | RegNet | TFLITE | w8a8 | Qualcomm® SA8775P | 1.14 ms | 0 - 76 MB | NPU
125
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.89 ms | 0 - 22 MB | NPU
126
- | RegNet | TFLITE | w8a8 | Qualcomm® QCM6690 | 6.644 ms | 0 - 190 MB | NPU
127
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.099 ms | 0 - 117 MB | NPU
128
  | RegNet | TFLITE | w8a8 | Qualcomm® SA7255P | 1.984 ms | 0 - 74 MB | NPU
129
- | RegNet | TFLITE | w8a8 | Qualcomm® SA8295P | 1.412 ms | 0 - 71 MB | NPU
130
- | RegNet | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.423 ms | 0 - 79 MB | NPU
131
- | RegNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.988 ms | 0 - 71 MB | NPU
132
- | RegNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.392 ms | 0 - 78 MB | NPU
133
 
134
  ## License
135
  * The license for the original implementation of RegNet can be found
 
15
  RegNet is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
16
 
17
  This is based on the implementation of RegNet found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/regnet.py).
18
+ 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/regnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | 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/regnet/releases/v0.49.1/regnet-onnx-float.zip)
32
+ | 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/regnet/releases/v0.49.1/regnet-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.49.1/regnet-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.49.1/regnet-qnn_dlc-w8a8.zip)
35
+ | 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/regnet/releases/v0.49.1/regnet-tflite-float.zip)
36
+ | 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/regnet/releases/v0.49.1/regnet-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[RegNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/regnet)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/regnet) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
+ See our repository for [RegNet on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/regnet) for usage instructions.
51
 
52
  ## Model Details
53
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | RegNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.839 ms | 1 - 88 MB | NPU
67
+ | RegNet | ONNX | float | Snapdragon® X2 Elite | 0.904 ms | 39 - 39 MB | NPU
68
+ | RegNet | ONNX | float | Snapdragon® X Elite | 1.957 ms | 39 - 39 MB | NPU
69
+ | RegNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.246 ms | 0 - 136 MB | NPU
70
+ | RegNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.749 ms | 0 - 44 MB | NPU
71
+ | RegNet | ONNX | float | Qualcomm® QCS9075 | 2.849 ms | 1 - 4 MB | NPU
72
+ | RegNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.0 ms | 0 - 85 MB | NPU
73
+ | RegNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.504 ms | 0 - 89 MB | NPU
74
+ | RegNet | ONNX | w8a8 | Snapdragon® X2 Elite | 0.502 ms | 20 - 20 MB | NPU
75
+ | RegNet | ONNX | w8a8 | Snapdragon® X Elite | 1.123 ms | 20 - 20 MB | NPU
76
+ | RegNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.654 ms | 0 - 135 MB | NPU
77
+ | RegNet | ONNX | w8a8 | Qualcomm® QCS6490 | 27.965 ms | 9 - 19 MB | CPU
78
+ | RegNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.901 ms | 0 - 28 MB | NPU
79
+ | RegNet | ONNX | w8a8 | Qualcomm® QCS9075 | 1.076 ms | 0 - 3 MB | NPU
80
+ | RegNet | ONNX | w8a8 | Qualcomm® QCM6690 | 17.962 ms | 8 - 17 MB | CPU
81
+ | RegNet | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.554 ms | 0 - 89 MB | NPU
82
+ | RegNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 13.724 ms | 8 - 18 MB | CPU
83
+ | RegNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.899 ms | 1 - 81 MB | NPU
84
+ | RegNet | QNN_DLC | float | Snapdragon® X2 Elite | 1.231 ms | 1 - 1 MB | NPU
85
+ | RegNet | QNN_DLC | float | Snapdragon® X Elite | 2.317 ms | 1 - 1 MB | NPU
86
+ | RegNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.426 ms | 0 - 128 MB | NPU
87
+ | RegNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 9.898 ms | 1 - 76 MB | NPU
88
+ | RegNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.073 ms | 1 - 161 MB | NPU
89
+ | RegNet | QNN_DLC | float | Qualcomm® SA8775P | 3.305 ms | 1 - 79 MB | NPU
90
+ | RegNet | QNN_DLC | float | Qualcomm® QCS9075 | 3.071 ms | 1 - 3 MB | NPU
91
+ | RegNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.536 ms | 0 - 115 MB | NPU
92
+ | RegNet | QNN_DLC | float | Qualcomm® SA7255P | 9.898 ms | 1 - 76 MB | NPU
93
+ | RegNet | QNN_DLC | float | Qualcomm® SA8295P | 3.496 ms | 0 - 65 MB | NPU
94
+ | RegNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.118 ms | 0 - 77 MB | NPU
95
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.44 ms | 0 - 80 MB | NPU
96
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.625 ms | 0 - 0 MB | NPU
97
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.077 ms | 0 - 0 MB | NPU
98
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.63 ms | 0 - 108 MB | NPU
99
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.699 ms | 0 - 2 MB | NPU
100
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.263 ms | 0 - 76 MB | NPU
101
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.893 ms | 0 - 2 MB | NPU
102
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.32 ms | 0 - 79 MB | NPU
103
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.084 ms | 2 - 4 MB | NPU
104
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 7.108 ms | 0 - 195 MB | NPU
105
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.293 ms | 0 - 110 MB | NPU
106
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.263 ms | 0 - 76 MB | NPU
107
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.608 ms | 0 - 75 MB | NPU
108
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.497 ms | 0 - 79 MB | NPU
109
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.171 ms | 0 - 77 MB | NPU
110
+ | RegNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.9 ms | 0 - 105 MB | NPU
111
+ | RegNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.396 ms | 0 - 156 MB | NPU
112
+ | RegNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 9.871 ms | 0 - 100 MB | NPU
113
+ | RegNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.092 ms | 0 - 3 MB | NPU
114
+ | RegNet | TFLITE | float | Qualcomm® SA8775P | 3.376 ms | 0 - 103 MB | NPU
115
+ | RegNet | TFLITE | float | Qualcomm® QCS9075 | 3.054 ms | 0 - 42 MB | NPU
116
+ | RegNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.455 ms | 0 - 143 MB | NPU
117
+ | RegNet | TFLITE | float | Qualcomm® SA7255P | 9.871 ms | 0 - 100 MB | NPU
118
+ | RegNet | TFLITE | float | Qualcomm® SA8295P | 3.5 ms | 0 - 83 MB | NPU
119
+ | RegNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.109 ms | 0 - 102 MB | NPU
120
+ | RegNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.384 ms | 0 - 78 MB | NPU
121
+ | RegNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.516 ms | 0 - 111 MB | NPU
122
+ | RegNet | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.326 ms | 0 - 21 MB | NPU
123
  | RegNet | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.984 ms | 0 - 74 MB | NPU
124
+ | RegNet | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.726 ms | 0 - 3 MB | NPU
125
+ | RegNet | TFLITE | w8a8 | Qualcomm® SA8775P | 1.139 ms | 0 - 77 MB | NPU
126
+ | RegNet | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.892 ms | 0 - 22 MB | NPU
127
+ | RegNet | TFLITE | w8a8 | Qualcomm® QCM6690 | 6.661 ms | 0 - 190 MB | NPU
128
+ | RegNet | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.131 ms | 0 - 116 MB | NPU
129
  | RegNet | TFLITE | w8a8 | Qualcomm® SA7255P | 1.984 ms | 0 - 74 MB | NPU
130
+ | RegNet | TFLITE | w8a8 | Qualcomm® SA8295P | 1.414 ms | 0 - 71 MB | NPU
131
+ | RegNet | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.436 ms | 0 - 70 MB | NPU
132
+ | RegNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.991 ms | 0 - 71 MB | NPU
 
133
 
134
  ## License
135
  * The license for the original implementation of RegNet can be found