Hugging Face's logo

qualcomm
/
RegNet

Image Classification
PyTorch
backbone
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
8845495
·
verified ·
1 Parent(s): 9dfdd74

v0.58.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.

Files changed (2) hide show
  1. README.md +104 -98
  2. release_assets.json +7 -7
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/v0.57.3/src/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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-onnx-float.zip)
32
- | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-onnx-w8a8.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-qnn_dlc-w8a8.zip)
35
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-tflite-float.zip)
36
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/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/v0.57.3/src/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/v0.57.3/src/qai_hub_models/models/regnet) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,96 +63,102 @@ 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 | 0.904 ms | 212 - 212 MB | NPU
67
- | RegNet | ONNX | float | Snapdragon® X Elite | 1.755 ms | 148 - 148 MB | NPU
68
- | RegNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.212 ms | 1 - 117 MB | NPU
69
- | RegNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.72 ms | 1 - 108 MB | NPU
70
- | RegNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.789 ms | 0 - 43 MB | NPU
71
- | RegNet | ONNX | float | Qualcomm® QCS8450 | 2.72 ms | 1 - 108 MB | NPU
72
- | RegNet | ONNX | float | Snapdragon® 8 Elite Mobile | 0.995 ms | 0 - 77 MB | NPU
73
- | RegNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.838 ms | 1 - 76 MB | NPU
74
- | RegNet | ONNX | float | Qualcomm® QCS9075 | 2.835 ms | 1 - 46 MB | NPU
75
- | RegNet | ONNX | float | Qualcomm® QCS8750 | 0.995 ms | 0 - 77 MB | NPU
76
- | RegNet | ONNX | float | Qualcomm® QCS7181 | 1.755 ms | 148 - 148 MB | NPU
77
- | RegNet | ONNX | w8a8 | Snapdragon® X2 Elite | 0.469 ms | 213 - 213 MB | NPU
78
- | RegNet | ONNX | w8a8 | Snapdragon® X Elite | 0.936 ms | 149 - 149 MB | NPU
79
- | RegNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.656 ms | 0 - 126 MB | NPU
80
- | RegNet | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.289 ms | 0 - 124 MB | NPU
81
- | RegNet | ONNX | w8a8 | Qualcomm® QCS6490 | 2.37 ms | 0 - 45 MB | NPU
82
- | RegNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.891 ms | 0 - 3 MB | NPU
83
- | RegNet | ONNX | w8a8 | Qualcomm® QCS8450 | 1.289 ms | 0 - 124 MB | NPU
84
- | RegNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.508 ms | 0 - 84 MB | NPU
85
- | RegNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.154 ms | 0 - 82 MB | NPU
86
- | RegNet | ONNX | w8a8 | Qualcomm® QCM6690 | 7.237 ms | 0 - 201 MB | NPU
87
- | RegNet | ONNX | w8a8 | Qualcomm® QCS9075 | 1.064 ms | 0 - 45 MB | NPU
88
- | RegNet | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.55 ms | 0 - 90 MB | NPU
89
- | RegNet | ONNX | w8a8 | Qualcomm® QCS7790 | 1.154 ms | 0 - 82 MB | NPU
90
- | RegNet | ONNX | w8a8 | Qualcomm® QCS8750 | 0.55 ms | 0 - 90 MB | NPU
91
- | RegNet | ONNX | w8a8 | Qualcomm® QCS7181 | 0.936 ms | 149 - 149 MB | NPU
92
- | RegNet | QNN_DLC | float | Snapdragon® X2 Elite | 1.228 ms | 1 - 1 MB | NPU
93
- | RegNet | QNN_DLC | float | Snapdragon® X Elite | 2.247 ms | 1 - 1 MB | NPU
94
- | RegNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.401 ms | 0 - 125 MB | NPU
95
- | RegNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 3.502 ms | 1 - 117 MB | NPU
96
- | RegNet | QNN_DLC | float | Qualcomm® QCS8275 | 9.863 ms | 1 - 72 MB | NPU
97
- | RegNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.042 ms | 1 - 124 MB | NPU
98
- | RegNet | QNN_DLC | float | Qualcomm® QCS8450 | 3.502 ms | 1 - 117 MB | NPU
99
- | RegNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.107 ms | 1 - 74 MB | NPU
100
- | RegNet | QNN_DLC | float | Qualcomm® SA8295P | 3.471 ms | 0 - 61 MB | NPU
101
- | RegNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.902 ms | 1 - 77 MB | NPU
102
- | RegNet | QNN_DLC | float | Qualcomm® SA7255P | 9.863 ms | 1 - 72 MB | NPU
103
- | RegNet | QNN_DLC | float | Qualcomm® QCS9075 | 3.034 ms | 3 - 5 MB | NPU
104
- | RegNet | QNN_DLC | float | Qualcomm® QCS8750 | 1.107 ms | 1 - 74 MB | NPU
105
- | RegNet | QNN_DLC | float | Qualcomm® QCS7181 | 2.247 ms | 1 - 1 MB | NPU
106
- | RegNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.58 ms | 0 - 0 MB | NPU
107
- | RegNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.053 ms | 0 - 0 MB | NPU
 
 
 
108
  | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.637 ms | 0 - 111 MB | NPU
109
- | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.307 ms | 0 - 112 MB | NPU
110
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.668 ms | 2 - 4 MB | NPU
111
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 2.283 ms | 0 - 80 MB | NPU
112
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.866 ms | 0 - 4 MB | NPU
113
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 1.307 ms | 0 - 112 MB | NPU
114
- | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.443 ms | 0 - 81 MB | NPU
115
- | RegNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.174 ms | 0 - 80 MB | NPU
116
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 7.122 ms | 0 - 199 MB | NPU
117
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.054 ms | 0 - 2 MB | NPU
118
- | RegNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.283 ms | 0 - 80 MB | NPU
119
- | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.482 ms | 0 - 78 MB | NPU
120
- | RegNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.605 ms | 0 - 78 MB | NPU
121
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 1.174 ms | 0 - 80 MB | NPU
122
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 0.482 ms | 0 - 78 MB | NPU
123
- | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 1.053 ms | 0 - 0 MB | NPU
124
- | RegNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.401 ms | 0 - 153 MB | NPU
125
- | RegNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 3.47 ms | 0 - 138 MB | NPU
126
- | RegNet | TFLITE | float | Qualcomm® QCS8275 | 9.855 ms | 0 - 89 MB | NPU
127
- | RegNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.038 ms | 0 - 2 MB | NPU
128
- | RegNet | TFLITE | float | Qualcomm® SA8775P | 14.573 ms | 0 - 29 MB | GPU
129
- | RegNet | TFLITE | float | Qualcomm® SA8650P | 14.573 ms | 0 - 29 MB | GPU
130
- | RegNet | TFLITE | float | Qualcomm® SA8255P | 14.573 ms | 0 - 29 MB | GPU
131
- | RegNet | TFLITE | float | Qualcomm® QCS8450 | 3.47 ms | 0 - 138 MB | NPU
132
- | RegNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.104 ms | 0 - 92 MB | NPU
133
- | RegNet | TFLITE | float | Qualcomm® SA8295P | 3.48 ms | 0 - 72 MB | NPU
134
- | RegNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.899 ms | 0 - 86 MB | NPU
135
- | RegNet | TFLITE | float | Qualcomm® SA7255P | 9.855 ms | 0 - 89 MB | NPU
136
- | RegNet | TFLITE | float | Qualcomm® QCS9075 | 3.03 ms | 0 - 42 MB | NPU
137
- | RegNet | TFLITE | float | Qualcomm® QCS8750 | 1.104 ms | 0 - 92 MB | NPU
138
- | RegNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.527 ms | 0 - 120 MB | NPU
139
- | RegNet | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.105 ms | 0 - 116 MB | NPU
140
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.368 ms | 0 - 22 MB | NPU
141
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS8275 | 2.004 ms | 0 - 75 MB | NPU
142
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.707 ms | 0 - 2 MB | NPU
143
- | RegNet | TFLITE | w8a8 | Qualcomm® SA8775P | 15.165 ms | 1 - 31 MB | GPU
144
- | RegNet | TFLITE | w8a8 | Qualcomm® SA8650P | 15.165 ms | 1 - 31 MB | GPU
145
- | RegNet | TFLITE | w8a8 | Qualcomm® SA8255P | 15.165 ms | 1 - 31 MB | GPU
146
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS8450 | 1.105 ms | 0 - 116 MB | NPU
147
- | RegNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.393 ms | 0 - 75 MB | NPU
148
- | RegNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.983 ms | 0 - 73 MB | NPU
149
- | RegNet | TFLITE | w8a8 | Qualcomm® QCM6690 | 6.647 ms | 0 - 190 MB | NPU
150
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.864 ms | 0 - 22 MB | NPU
151
- | RegNet | TFLITE | w8a8 | Qualcomm® SA7255P | 2.004 ms | 0 - 75 MB | NPU
152
- | RegNet | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.421 ms | 0 - 71 MB | NPU
153
- | RegNet | TFLITE | w8a8 | Qualcomm® SA8295P | 1.41 ms | 0 - 72 MB | NPU
154
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS7790 | 0.983 ms | 0 - 73 MB | NPU
155
- | RegNet | TFLITE | w8a8 | Qualcomm® QCS8750 | 0.421 ms | 0 - 71 MB | NPU
 
 
 
156
 
157
  ## License
158
  * 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/blob/v0.58.0/src/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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-onnx-float.zip)
32
+ | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-qnn_dlc-w8a8.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-tflite-float.zip)
36
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/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/v0.58.0/src/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/v0.58.0/src/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® X2 Elite | 0.915 ms | 2 - 2 MB | NPU
67
+ | RegNet | ONNX | float | Snapdragon® X Elite | 1.768 ms | 39 - 39 MB | NPU
68
+ | RegNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.235 ms | 0 - 126 MB | NPU
69
+ | RegNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.726 ms | 0 - 116 MB | NPU
70
+ | RegNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.738 ms | 0 - 68 MB | NPU
71
+ | RegNet | ONNX | float | Qualcomm® QCS8450 | 2.726 ms | 0 - 116 MB | NPU
72
+ | RegNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 2.803 ms | 0 - 4 MB | NPU
73
+ | RegNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.835 ms | 0 - 77 MB | NPU
74
+ | RegNet | ONNX | float | Snapdragon® 8 Elite Mobile | 0.996 ms | 0 - 76 MB | NPU
75
+ | RegNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.996 ms | 0 - 76 MB | NPU
76
+ | RegNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.768 ms | 39 - 39 MB | NPU
77
+ | RegNet | ONNX | w8a8 | Snapdragon® X2 Elite | 0.473 ms | 1 - 1 MB | NPU
78
+ | RegNet | ONNX | w8a8 | Snapdragon® X Elite | 0.931 ms | 20 - 20 MB | NPU
79
+ | RegNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.633 ms | 0 - 134 MB | NPU
80
+ | RegNet | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.3 ms | 0 - 134 MB | NPU
81
+ | RegNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 3.792 ms | 0 - 3 MB | NPU
82
+ | RegNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.904 ms | 0 - 26 MB | NPU
83
+ | RegNet | ONNX | w8a8 | Qualcomm® QCS8450 | 1.3 ms | 0 - 134 MB | NPU
84
+ | RegNet | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.547 ms | 0 - 91 MB | NPU
85
+ | RegNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.166 ms | 0 - 87 MB | NPU
86
+ | RegNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.508 ms | 0 - 89 MB | NPU
87
+ | RegNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.162 ms | 0 - 3 MB | NPU
88
+ | RegNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 7.239 ms | 0 - 206 MB | NPU
89
+ | RegNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.166 ms | 0 - 87 MB | NPU
90
+ | RegNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.547 ms | 0 - 91 MB | NPU
91
+ | RegNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.931 ms | 20 - 20 MB | NPU
92
+ | RegNet | QNN_DLC | float | Snapdragon® X2 Elite | 1.211 ms | 1 - 1 MB | NPU
93
+ | RegNet | QNN_DLC | float | Snapdragon® X Elite | 2.254 ms | 1 - 1 MB | NPU
94
+ | RegNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.406 ms | 0 - 126 MB | NPU
95
+ | RegNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 3.481 ms | 0 - 115 MB | NPU
96
+ | RegNet | QNN_DLC | float | Qualcomm® QCS8275 | 9.847 ms | 1 - 72 MB | NPU
97
+ | RegNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.053 ms | 1 - 33 MB | NPU
98
+ | RegNet | QNN_DLC | float | Qualcomm® SA8775P | 3.264 ms | 1 - 74 MB | NPU
99
+ | RegNet | QNN_DLC | float | Qualcomm® SA8650P | 3.264 ms | 1 - 74 MB | NPU
100
+ | RegNet | QNN_DLC | float | Qualcomm® SA8255P | 3.264 ms | 1 - 74 MB | NPU
101
+ | RegNet | QNN_DLC | float | Qualcomm® QCS8450 | 3.481 ms | 0 - 115 MB | NPU
102
+ | RegNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 3.041 ms | 1 - 3 MB | NPU
103
+ | RegNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.893 ms | 1 - 76 MB | NPU
104
+ | RegNet | QNN_DLC | float | Qualcomm® SA7255P | 9.847 ms | 1 - 72 MB | NPU
105
+ | RegNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.106 ms | 1 - 74 MB | NPU
106
+ | RegNet | QNN_DLC | float | Qualcomm® SA8295P | 3.464 ms | 0 - 61 MB | NPU
107
+ | RegNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.106 ms | 1 - 74 MB | NPU
108
+ | RegNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.254 ms | 1 - 1 MB | NPU
109
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.576 ms | 0 - 0 MB | NPU
110
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.054 ms | 0 - 0 MB | NPU
111
  | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.637 ms | 0 - 111 MB | NPU
112
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.313 ms | 0 - 112 MB | NPU
113
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 4.13 ms | 0 - 2 MB | NPU
114
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 2.312 ms | 0 - 80 MB | NPU
115
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.884 ms | 0 - 8 MB | NPU
116
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.301 ms | 0 - 82 MB | NPU
117
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® SA8650P | 1.301 ms | 0 - 82 MB | NPU
118
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® SA8255P | 1.301 ms | 0 - 82 MB | NPU
119
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 1.313 ms | 0 - 112 MB | NPU
120
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.481 ms | 0 - 78 MB | NPU
121
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.178 ms | 0 - 80 MB | NPU
122
+ | RegNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.443 ms | 0 - 82 MB | NPU
123
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.119 ms | 0 - 2 MB | NPU
124
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 7.109 ms | 0 - 199 MB | NPU
125
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.312 ms | 0 - 80 MB | NPU
126
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.601 ms | 0 - 78 MB | NPU
127
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.178 ms | 0 - 80 MB | NPU
128
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.481 ms | 0 - 78 MB | NPU
129
+ | RegNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.054 ms | 0 - 0 MB | NPU
130
+ | RegNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.397 ms | 0 - 148 MB | NPU
131
+ | RegNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 3.47 ms | 0 - 137 MB | NPU
132
+ | RegNet | TFLITE | float | Qualcomm® QCS8275 | 9.882 ms | 0 - 89 MB | NPU
133
+ | RegNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.037 ms | 0 - 7 MB | NPU
134
+ | RegNet | TFLITE | float | Qualcomm® SA8775P | 3.315 ms | 0 - 92 MB | NPU
135
+ | RegNet | TFLITE | float | Qualcomm® SA8650P | 3.315 ms | 0 - 92 MB | NPU
136
+ | RegNet | TFLITE | float | Qualcomm® SA8255P | 3.315 ms | 0 - 92 MB | NPU
137
+ | RegNet | TFLITE | float | Qualcomm® QCS8450 | 3.47 ms | 0 - 137 MB | NPU
138
+ | RegNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 3.036 ms | 0 - 42 MB | NPU
139
+ | RegNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.901 ms | 0 - 86 MB | NPU
140
+ | RegNet | TFLITE | float | Qualcomm® SA7255P | 9.882 ms | 0 - 89 MB | NPU
141
+ | RegNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.105 ms | 0 - 92 MB | NPU
142
+ | RegNet | TFLITE | float | Qualcomm® SA8295P | 3.461 ms | 0 - 72 MB | NPU
143
+ | RegNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.105 ms | 0 - 92 MB | NPU
144
+ | RegNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.548 ms | 0 - 118 MB | NPU
145
+ | RegNet | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.111 ms | 0 - 119 MB | NPU
146
+ | RegNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 3.918 ms | 0 - 22 MB | NPU
147
+ | RegNet | TFLITE | w8a8 | Qualcomm® QCS8275 | 1.976 ms | 0 - 75 MB | NPU
148
+ | RegNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.708 ms | 0 - 2 MB | NPU
149
+ | RegNet | TFLITE | w8a8 | Qualcomm® SA8775P | 1.119 ms | 0 - 79 MB | NPU
150
+ | RegNet | TFLITE | w8a8 | Qualcomm® SA8650P | 1.119 ms | 0 - 79 MB | NPU
151
+ | RegNet | TFLITE | w8a8 | Qualcomm® SA8255P | 1.119 ms | 0 - 79 MB | NPU
152
+ | RegNet | TFLITE | w8a8 | Qualcomm® QCS8450 | 1.111 ms | 0 - 119 MB | NPU
153
+ | RegNet | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.442 ms | 0 - 79 MB | NPU
154
+ | RegNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.988 ms | 0 - 73 MB | NPU
155
+ | RegNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.394 ms | 0 - 77 MB | NPU
156
+ | RegNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.958 ms | 0 - 22 MB | NPU
157
+ | RegNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 6.627 ms | 0 - 193 MB | NPU
158
+ | RegNet | TFLITE | w8a8 | Qualcomm® SA7255P | 1.976 ms | 0 - 75 MB | NPU
159
+ | RegNet | TFLITE | w8a8 | Qualcomm® SA8295P | 1.418 ms | 0 - 72 MB | NPU
160
+ | RegNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.988 ms | 0 - 73 MB | NPU
161
+ | RegNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.442 ms | 0 - 79 MB | NPU
162
 
163
  ## License
164
  * The license for the original implementation of RegNet can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,20 +8,20 @@
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-onnx-float.zip"
25
  }
26
  }
27
  },
@@ -32,20 +32,20 @@
32
  "qairt": "2.45.0.260326154327",
33
  "litert": "1.4.4"
34
  },
35
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-tflite-w8a8.zip"
36
  },
37
  "qnn_dlc": {
38
  "tool_versions": {
39
  "qairt": "2.45.0.260326154327"
40
  },
41
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-qnn_dlc-w8a8.zip"
42
  },
43
  "onnx": {
44
  "tool_versions": {
45
  "qairt": "2.45.0.260326154327",
46
  "onnx_runtime": "1.25.0"
47
  },
48
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.57.3/regnet-onnx-w8a8.zip"
49
  }
50
  }
51
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-onnx-float.zip"
25
  }
26
  }
27
  },
 
32
  "qairt": "2.45.0.260326154327",
33
  "litert": "1.4.4"
34
  },
35
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-tflite-w8a8.zip"
36
  },
37
  "qnn_dlc": {
38
  "tool_versions": {
39
  "qairt": "2.45.0.260326154327"
40
  },
41
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-qnn_dlc-w8a8.zip"
42
  },
43
  "onnx": {
44
  "tool_versions": {
45
  "qairt": "2.45.0.260326154327",
46
  "onnx_runtime": "1.25.0"
47
  },
48
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/regnet/releases/v0.58.0/regnet-onnx-w8a8.zip"
49
  }
50
  }
51
  }