Hugging Face's logo

qualcomm
/
ResNeXt101

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
ae9bf20
·
verified ·
1 Parent(s): 61c03bd

v0.48.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

Files changed (1) hide show
  1. README.md +74 -74
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
16
  ResNeXt101 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.
17
 
18
  This is based on the implementation of ResNeXt101 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py).
19
- 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/resnext101) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
@@ -29,26 +29,26 @@ Below are pre-exported model assets ready for deployment.
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
- | 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/resnext101/releases/v0.47.0/resnext101-onnx-float.zip)
33
- | 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/resnext101/releases/v0.47.0/resnext101-onnx-w8a8.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext101/releases/v0.47.0/resnext101-qnn_dlc-float.zip)
35
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext101/releases/v0.47.0/resnext101-qnn_dlc-w8a8.zip)
36
- | 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/resnext101/releases/v0.47.0/resnext101-tflite-float.zip)
37
- | 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/resnext101/releases/v0.47.0/resnext101-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[ResNeXt101 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnext101)**.
40
 
41
 
42
  ### Option 2: Export with Custom Configurations
43
 
44
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/resnext101) Python library to compile and export the model with your own:
45
  - Custom weights (e.g., fine-tuned checkpoints)
46
  - Custom input shapes
47
  - Target device and runtime configurations
48
 
49
  This option is ideal if you need to customize the model beyond the default configuration provided here.
50
 
51
- See our repository for [ResNeXt101 on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/resnext101) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -64,73 +64,73 @@ See our repository for [ResNeXt101 on GitHub](https://github.com/quic/ai-hub-mod
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
- | ResNeXt101 | ONNX | float | Snapdragon® X Elite | 6.733 ms | 172 - 172 MB | NPU
68
- | ResNeXt101 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.532 ms | 73 - 457 MB | NPU
69
- | ResNeXt101 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.6 ms | 1 - 5 MB | NPU
 
70
  | ResNeXt101 | ONNX | float | Qualcomm® QCS9075 | 9.735 ms | 0 - 4 MB | NPU
71
- | ResNeXt101 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.875 ms | 0 - 175 MB | NPU
72
  | ResNeXt101 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.043 ms | 1 - 203 MB | NPU
73
- | ResNeXt101 | ONNX | float | Snapdragon® X2 Elite | 3.101 ms | 173 - 173 MB | NPU
74
- | ResNeXt101 | ONNX | w8a8 | Snapdragon® X Elite | 3.13 ms | 87 - 87 MB | NPU
75
- | ResNeXt101 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 2.144 ms | 0 - 258 MB | NPU
76
- | ResNeXt101 | ONNX | w8a8 | Qualcomm® QCS6490 | 113.168 ms | 8 - 43 MB | CPU
77
- | ResNeXt101 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.924 ms | 0 - 100 MB | NPU
78
- | ResNeXt101 | ONNX | w8a8 | Qualcomm® QCS9075 | 3.143 ms | 0 - 3 MB | NPU
79
- | ResNeXt101 | ONNX | w8a8 | Qualcomm® QCM6690 | 73.293 ms | 0 - 12 MB | CPU
80
- | ResNeXt101 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.87 ms | 0 - 219 MB | NPU
81
- | ResNeXt101 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 67.91 ms | 0 - 12 MB | CPU
82
- | ResNeXt101 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.563 ms | 0 - 215 MB | NPU
83
- | ResNeXt101 | ONNX | w8a8 | Snapdragon® X2 Elite | 1.396 ms | 87 - 87 MB | NPU
84
- | ResNeXt101 | QNN_DLC | float | Snapdragon® X Elite | 6.934 ms | 1 - 1 MB | NPU
85
- | ResNeXt101 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 4.65 ms | 0 - 368 MB | NPU
86
- | ResNeXt101 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 35.92 ms | 1 - 191 MB | NPU
87
- | ResNeXt101 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 6.776 ms | 1 - 3 MB | NPU
88
- | ResNeXt101 | QNN_DLC | float | Qualcomm® SA8775P | 45.041 ms | 1 - 203 MB | NPU
89
- | ResNeXt101 | QNN_DLC | float | Qualcomm® QCS9075 | 10.003 ms | 1 - 3 MB | NPU
90
- | ResNeXt101 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.895 ms | 0 - 313 MB | NPU
91
- | ResNeXt101 | QNN_DLC | float | Qualcomm® SA7255P | 35.92 ms | 1 - 191 MB | NPU
92
- | ResNeXt101 | QNN_DLC | float | Qualcomm® SA8295P | 10.896 ms | 1 - 140 MB | NPU
93
- | ResNeXt101 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.975 ms | 0 - 189 MB | NPU
94
- | ResNeXt101 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.081 ms | 0 - 192 MB | NPU
95
- | ResNeXt101 | QNN_DLC | float | Snapdragon® X2 Elite | 3.686 ms | 1 - 1 MB | NPU
96
- | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® X Elite | 3.076 ms | 0 - 0 MB | NPU
97
- | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 2.121 ms | 0 - 253 MB | NPU
98
- | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 9.316 ms | 0 - 2 MB | NPU
99
- | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 6.52 ms | 0 - 206 MB | NPU
100
- | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.838 ms | 0 - 2 MB | NPU
101
- | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 3.514 ms | 0 - 208 MB | NPU
102
- | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 3.129 ms | 2 - 4 MB | NPU
103
- | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 33.196 ms | 0 - 370 MB | NPU
104
- | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 3.897 ms | 0 - 252 MB | NPU
105
- | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 6.52 ms | 0 - 206 MB | NPU
106
- | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 4.243 ms | 0 - 209 MB | NPU
107
- | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.817 ms | 0 - 205 MB | NPU
108
- | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 4.062 ms | 0 - 239 MB | NPU
109
- | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.512 ms | 0 - 210 MB | NPU
110
- | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 1.696 ms | 1 - 1 MB | NPU
111
- | ResNeXt101 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.615 ms | 0 - 571 MB | NPU
112
- | ResNeXt101 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 35.89 ms | 0 - 396 MB | NPU
113
- | ResNeXt101 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 6.891 ms | 0 - 3 MB | NPU
114
- | ResNeXt101 | TFLITE | float | Qualcomm® SA8775P | 10.283 ms | 0 - 396 MB | NPU
115
- | ResNeXt101 | TFLITE | float | Qualcomm® QCS9075 | 10.033 ms | 0 - 174 MB | NPU
116
- | ResNeXt101 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 9.811 ms | 0 - 510 MB | NPU
117
- | ResNeXt101 | TFLITE | float | Qualcomm® SA7255P | 35.89 ms | 0 - 396 MB | NPU
118
- | ResNeXt101 | TFLITE | float | Qualcomm® SA8295P | 10.967 ms | 0 - 336 MB | NPU
119
- | ResNeXt101 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.953 ms | 0 - 398 MB | NPU
120
- | ResNeXt101 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.102 ms | 0 - 401 MB | NPU
121
- | ResNeXt101 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.976 ms | 0 - 245 MB | NPU
122
- | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS6490 | 8.858 ms | 0 - 88 MB | NPU
123
- | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 6.313 ms | 0 - 210 MB | NPU
124
- | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.677 ms | 0 - 2 MB | NPU
125
- | ResNeXt101 | TFLITE | w8a8 | Qualcomm® SA8775P | 3.361 ms | 0 - 210 MB | NPU
126
- | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS9075 | 2.953 ms | 0 - 89 MB | NPU
127
- | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCM6690 | 30.629 ms | 0 - 369 MB | NPU
128
- | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 3.744 ms | 0 - 250 MB | NPU
129
- | ResNeXt101 | TFLITE | w8a8 | Qualcomm® SA7255P | 6.313 ms | 0 - 210 MB | NPU
130
- | ResNeXt101 | TFLITE | w8a8 | Qualcomm® SA8295P | 4.108 ms | 0 - 212 MB | NPU
131
- | ResNeXt101 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.772 ms | 0 - 206 MB | NPU
132
- | ResNeXt101 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.959 ms | 0 - 225 MB | NPU
133
- | ResNeXt101 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.485 ms | 0 - 209 MB | NPU
134
 
135
  ## License
136
  * The license for the original implementation of ResNeXt101 can be found
 
16
  ResNeXt101 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.
17
 
18
  This is based on the implementation of ResNeXt101 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py).
19
+ 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/resnext101) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
 
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
+ | 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/resnext101/releases/v0.48.0/resnext101-onnx-float.zip)
33
+ | 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/resnext101/releases/v0.48.0/resnext101-onnx-w8a8.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext101/releases/v0.48.0/resnext101-qnn_dlc-float.zip)
35
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnext101/releases/v0.48.0/resnext101-qnn_dlc-w8a8.zip)
36
+ | 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/resnext101/releases/v0.48.0/resnext101-tflite-float.zip)
37
+ | 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/resnext101/releases/v0.48.0/resnext101-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[ResNeXt101 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnext101)**.
40
 
41
 
42
  ### Option 2: Export with Custom Configurations
43
 
44
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/resnext101) Python library to compile and export the model with your own:
45
  - Custom weights (e.g., fine-tuned checkpoints)
46
  - Custom input shapes
47
  - Target device and runtime configurations
48
 
49
  This option is ideal if you need to customize the model beyond the default configuration provided here.
50
 
51
+ See our repository for [ResNeXt101 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/resnext101) for usage instructions.
52
 
53
  ## Model Details
54
 
 
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
+ | ResNeXt101 | ONNX | float | Snapdragon® X2 Elite | 3.091 ms | 173 - 173 MB | NPU
68
+ | ResNeXt101 | ONNX | float | Snapdragon® X Elite | 6.718 ms | 172 - 172 MB | NPU
69
+ | ResNeXt101 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.584 ms | 0 - 383 MB | NPU
70
+ | ResNeXt101 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.651 ms | 1 - 4 MB | NPU
71
  | ResNeXt101 | ONNX | float | Qualcomm® QCS9075 | 9.735 ms | 0 - 4 MB | NPU
72
+ | ResNeXt101 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.904 ms | 0 - 174 MB | NPU
73
  | ResNeXt101 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.043 ms | 1 - 203 MB | NPU
74
+ | ResNeXt101 | ONNX | w8a8 | Snapdragon® X2 Elite | 1.395 ms | 87 - 87 MB | NPU
75
+ | ResNeXt101 | ONNX | w8a8 | Snapdragon® X Elite | 3.123 ms | 87 - 87 MB | NPU
76
+ | ResNeXt101 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 2.136 ms | 0 - 255 MB | NPU
77
+ | ResNeXt101 | ONNX | w8a8 | Qualcomm® QCS6490 | 111.944 ms | 8 - 42 MB | CPU
78
+ | ResNeXt101 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.911 ms | 0 - 102 MB | NPU
79
+ | ResNeXt101 | ONNX | w8a8 | Qualcomm® QCS9075 | 3.131 ms | 0 - 3 MB | NPU
80
+ | ResNeXt101 | ONNX | w8a8 | Qualcomm® QCM6690 | 73.196 ms | 1 - 12 MB | CPU
81
+ | ResNeXt101 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.854 ms | 0 - 220 MB | NPU
82
+ | ResNeXt101 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 68.935 ms | 0 - 12 MB | CPU
83
+ | ResNeXt101 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.574 ms | 0 - 216 MB | NPU
84
+ | ResNeXt101 | QNN_DLC | float | Snapdragon® X2 Elite | 3.731 ms | 1 - 1 MB | NPU
85
+ | ResNeXt101 | QNN_DLC | float | Snapdragon® X Elite | 6.915 ms | 1 - 1 MB | NPU
86
+ | ResNeXt101 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 4.62 ms | 0 - 367 MB | NPU
87
+ | ResNeXt101 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 35.889 ms | 1 - 191 MB | NPU
88
+ | ResNeXt101 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 6.978 ms | 1 - 3 MB | NPU
89
+ | ResNeXt101 | QNN_DLC | float | Qualcomm® SA8775P | 10.322 ms | 1 - 204 MB | NPU
90
+ | ResNeXt101 | QNN_DLC | float | Qualcomm® QCS9075 | 9.992 ms | 3 - 5 MB | NPU
91
+ | ResNeXt101 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.859 ms | 0 - 313 MB | NPU
92
+ | ResNeXt101 | QNN_DLC | float | Qualcomm® SA7255P | 35.889 ms | 1 - 191 MB | NPU
93
+ | ResNeXt101 | QNN_DLC | float | Qualcomm® SA8295P | 10.901 ms | 1 - 140 MB | NPU
94
+ | ResNeXt101 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.036 ms | 1 - 189 MB | NPU
95
+ | ResNeXt101 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.089 ms | 1 - 193 MB | NPU
96
+ | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 1.709 ms | 0 - 0 MB | NPU
97
+ | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® X Elite | 3.068 ms | 0 - 0 MB | NPU
98
+ | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 2.128 ms | 0 - 250 MB | NPU
99
+ | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 9.07 ms | 0 - 2 MB | NPU
100
+ | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 6.549 ms | 0 - 206 MB | NPU
101
+ | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.816 ms | 0 - 2 MB | NPU
102
+ | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 3.505 ms | 0 - 207 MB | NPU
103
+ | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 3.133 ms | 0 - 2 MB | NPU
104
+ | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 26.9 ms | 0 - 367 MB | NPU
105
+ | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 4.027 ms | 0 - 253 MB | NPU
106
+ | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 6.549 ms | 0 - 206 MB | NPU
107
+ | ResNeXt101 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 4.306 ms | 0 - 209 MB | NPU
108
+ | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.803 ms | 0 - 204 MB | NPU
109
+ | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 4.068 ms | 0 - 239 MB | NPU
110
+ | ResNeXt101 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.52 ms | 0 - 210 MB | NPU
111
+ | ResNeXt101 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.688 ms | 0 - 580 MB | NPU
112
+ | ResNeXt101 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 35.88 ms | 0 - 396 MB | NPU
113
+ | ResNeXt101 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 6.834 ms | 0 - 2 MB | NPU
114
+ | ResNeXt101 | TFLITE | float | Qualcomm® SA8775P | 10.321 ms | 0 - 395 MB | NPU
115
+ | ResNeXt101 | TFLITE | float | Qualcomm® QCS9075 | 10.041 ms | 0 - 174 MB | NPU
116
+ | ResNeXt101 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 9.941 ms | 0 - 511 MB | NPU
117
+ | ResNeXt101 | TFLITE | float | Qualcomm® SA7255P | 35.88 ms | 0 - 396 MB | NPU
118
+ | ResNeXt101 | TFLITE | float | Qualcomm® SA8295P | 10.94 ms | 0 - 336 MB | NPU
119
+ | ResNeXt101 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.974 ms | 0 - 389 MB | NPU
120
+ | ResNeXt101 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.091 ms | 0 - 401 MB | NPU
121
+ | ResNeXt101 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.977 ms | 0 - 250 MB | NPU
122
+ | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS6490 | 8.901 ms | 0 - 88 MB | NPU
123
+ | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 6.289 ms | 0 - 209 MB | NPU
124
+ | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.658 ms | 0 - 2 MB | NPU
125
+ | ResNeXt101 | TFLITE | w8a8 | Qualcomm® SA8775P | 12.696 ms | 0 - 210 MB | NPU
126
+ | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS9075 | 2.95 ms | 0 - 89 MB | NPU
127
+ | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCM6690 | 24.89 ms | 0 - 371 MB | NPU
128
+ | ResNeXt101 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 3.966 ms | 0 - 249 MB | NPU
129
+ | ResNeXt101 | TFLITE | w8a8 | Qualcomm® SA7255P | 6.289 ms | 0 - 209 MB | NPU
130
+ | ResNeXt101 | TFLITE | w8a8 | Qualcomm® SA8295P | 4.112 ms | 0 - 213 MB | NPU
131
+ | ResNeXt101 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.784 ms | 0 - 211 MB | NPU
132
+ | ResNeXt101 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.948 ms | 0 - 225 MB | NPU
133
+ | ResNeXt101 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.473 ms | 0 - 210 MB | NPU
 
134
 
135
  ## License
136
  * The license for the original implementation of ResNeXt101 can be found