Hugging Face's logo

qualcomm
/
ResNet101

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
edbf3e2
·
verified ·
1 Parent(s): ac25bf3

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
  ResNet101 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 ResNet101 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/resnet101) 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/resnet101/releases/v0.47.0/resnet101-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/resnet101/releases/v0.47.0/resnet101-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/resnet101/releases/v0.47.0/resnet101-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/resnet101/releases/v0.47.0/resnet101-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/resnet101/releases/v0.47.0/resnet101-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/resnet101/releases/v0.47.0/resnet101-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[ResNet101 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet101)**.
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/resnet101) 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 [ResNet101 on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/resnet101) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -64,73 +64,73 @@ See our repository for [ResNet101 on GitHub](https://github.com/quic/ai-hub-mode
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
- | ResNet101 | ONNX | float | Snapdragon® X Elite | 3.289 ms | 85 - 85 MB | NPU
68
- | ResNet101 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.24 ms | 0 - 133 MB | NPU
69
- | ResNet101 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 3.142 ms | 1 - 4 MB | NPU
70
- | ResNet101 | ONNX | float | Qualcomm® QCS9075 | 5.128 ms | 1 - 4 MB | NPU
 
71
  | ResNet101 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.858 ms | 0 - 75 MB | NPU
72
- | ResNet101 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.609 ms | 1 - 77 MB | NPU
73
- | ResNet101 | ONNX | float | Snapdragon® X2 Elite | 1.624 ms | 86 - 86 MB | NPU
74
- | ResNet101 | ONNX | w8a8 | Snapdragon® X Elite | 1.306 ms | 43 - 43 MB | NPU
75
- | ResNet101 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.979 ms | 0 - 138 MB | NPU
76
- | ResNet101 | ONNX | w8a8 | Qualcomm® QCS6490 | 56.268 ms | 9 - 57 MB | CPU
77
- | ResNet101 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.28 ms | 0 - 51 MB | NPU
78
- | ResNet101 | ONNX | w8a8 | Qualcomm® QCS9075 | 1.331 ms | 0 - 3 MB | NPU
79
- | ResNet101 | ONNX | w8a8 | Qualcomm® QCM6690 | 42.32 ms | 10 - 20 MB | CPU
80
- | ResNet101 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.839 ms | 0 - 73 MB | NPU
81
- | ResNet101 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 39.525 ms | 10 - 21 MB | CPU
82
- | ResNet101 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.802 ms | 0 - 76 MB | NPU
83
- | ResNet101 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.557 ms | 43 - 43 MB | NPU
84
- | ResNet101 | QNN_DLC | float | Snapdragon® X Elite | 3.556 ms | 1 - 1 MB | NPU
85
- | ResNet101 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.405 ms | 0 - 126 MB | NPU
86
- | ResNet101 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 18.273 ms | 1 - 67 MB | NPU
87
- | ResNet101 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.334 ms | 1 - 9 MB | NPU
88
- | ResNet101 | QNN_DLC | float | Qualcomm® SA8775P | 5.402 ms | 1 - 71 MB | NPU
89
- | ResNet101 | QNN_DLC | float | Qualcomm® QCS9075 | 5.302 ms | 3 - 5 MB | NPU
90
- | ResNet101 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.949 ms | 0 - 93 MB | NPU
91
- | ResNet101 | QNN_DLC | float | Qualcomm® SA7255P | 18.273 ms | 1 - 67 MB | NPU
92
  | ResNet101 | QNN_DLC | float | Qualcomm® SA8295P | 5.664 ms | 1 - 43 MB | NPU
93
- | ResNet101 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.949 ms | 0 - 68 MB | NPU
94
- | ResNet101 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.622 ms | 1 - 69 MB | NPU
95
- | ResNet101 | QNN_DLC | float | Snapdragon® X2 Elite | 1.975 ms | 1 - 1 MB | NPU
96
- | ResNet101 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.27 ms | 0 - 0 MB | NPU
97
- | ResNet101 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.966 ms | 0 - 120 MB | NPU
98
- | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 4.583 ms | 0 - 2 MB | NPU
99
- | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.961 ms | 0 - 71 MB | NPU
100
- | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.276 ms | 0 - 28 MB | NPU
101
- | ResNet101 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.534 ms | 0 - 73 MB | NPU
102
- | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.32 ms | 0 - 2 MB | NPU
103
- | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 11.695 ms | 0 - 193 MB | NPU
104
- | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.797 ms | 0 - 123 MB | NPU
105
- | ResNet101 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.961 ms | 0 - 71 MB | NPU
106
- | ResNet101 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.945 ms | 0 - 68 MB | NPU
107
- | ResNet101 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.784 ms | 0 - 68 MB | NPU
108
- | ResNet101 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.8 ms | 0 - 80 MB | NPU
109
- | ResNet101 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.743 ms | 0 - 72 MB | NPU
110
- | ResNet101 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.623 ms | 0 - 0 MB | NPU
111
- | ResNet101 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.382 ms | 0 - 192 MB | NPU
112
- | ResNet101 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 18.202 ms | 0 - 124 MB | NPU
113
- | ResNet101 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.319 ms | 0 - 2 MB | NPU
114
- | ResNet101 | TFLITE | float | Qualcomm® SA8775P | 5.414 ms | 0 - 126 MB | NPU
115
- | ResNet101 | TFLITE | float | Qualcomm® QCS9075 | 5.288 ms | 0 - 88 MB | NPU
116
- | ResNet101 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.915 ms | 0 - 158 MB | NPU
117
- | ResNet101 | TFLITE | float | Qualcomm® SA7255P | 18.202 ms | 0 - 124 MB | NPU
118
- | ResNet101 | TFLITE | float | Qualcomm® SA8295P | 5.586 ms | 0 - 96 MB | NPU
119
- | ResNet101 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.927 ms | 0 - 130 MB | NPU
120
- | ResNet101 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.622 ms | 0 - 129 MB | NPU
121
- | ResNet101 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.871 ms | 0 - 132 MB | NPU
122
- | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS6490 | 4.477 ms | 0 - 45 MB | NPU
123
- | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.746 ms | 0 - 69 MB | NPU
124
- | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.138 ms | 0 - 14 MB | NPU
125
- | ResNet101 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.431 ms | 0 - 70 MB | NPU
126
- | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS9075 | 1.174 ms | 0 - 45 MB | NPU
127
- | ResNet101 | TFLITE | w8a8 | Qualcomm® QCM6690 | 11.746 ms | 0 - 194 MB | NPU
128
- | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.637 ms | 0 - 134 MB | NPU
129
- | ResNet101 | TFLITE | w8a8 | Qualcomm® SA7255P | 2.746 ms | 0 - 69 MB | NPU
130
- | ResNet101 | TFLITE | w8a8 | Qualcomm® SA8295P | 1.789 ms | 0 - 71 MB | NPU
131
- | ResNet101 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.733 ms | 0 - 66 MB | NPU
132
- | ResNet101 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.663 ms | 0 - 76 MB | NPU
133
- | ResNet101 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.698 ms | 0 - 70 MB | NPU
134
 
135
  ## License
136
  * The license for the original implementation of ResNet101 can be found
 
16
  ResNet101 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 ResNet101 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/resnet101) 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/resnet101/releases/v0.48.0/resnet101-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/resnet101/releases/v0.48.0/resnet101-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/resnet101/releases/v0.48.0/resnet101-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/resnet101/releases/v0.48.0/resnet101-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/resnet101/releases/v0.48.0/resnet101-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/resnet101/releases/v0.48.0/resnet101-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[ResNet101 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet101)**.
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/resnet101) 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 [ResNet101 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/resnet101) 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
+ | ResNet101 | ONNX | float | Snapdragon® X2 Elite | 1.622 ms | 86 - 86 MB | NPU
68
+ | ResNet101 | ONNX | float | Snapdragon® X Elite | 3.307 ms | 85 - 85 MB | NPU
69
+ | ResNet101 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.238 ms | 0 - 128 MB | NPU
70
+ | ResNet101 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 3.08 ms | 0 - 112 MB | NPU
71
+ | ResNet101 | ONNX | float | Qualcomm® QCS9075 | 5.132 ms | 0 - 4 MB | NPU
72
  | ResNet101 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.858 ms | 0 - 75 MB | NPU
73
+ | ResNet101 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.6 ms | 1 - 78 MB | NPU
74
+ | ResNet101 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.566 ms | 43 - 43 MB | NPU
75
+ | ResNet101 | ONNX | w8a8 | Snapdragon® X Elite | 1.294 ms | 43 - 43 MB | NPU
76
+ | ResNet101 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.983 ms | 0 - 145 MB | NPU
77
+ | ResNet101 | ONNX | w8a8 | Qualcomm® QCS6490 | 58.052 ms | 10 - 59 MB | CPU
78
+ | ResNet101 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.285 ms | 0 - 51 MB | NPU
79
+ | ResNet101 | ONNX | w8a8 | Qualcomm® QCS9075 | 1.337 ms | 0 - 3 MB | NPU
80
+ | ResNet101 | ONNX | w8a8 | Qualcomm® QCM6690 | 42.238 ms | 10 - 20 MB | CPU
81
+ | ResNet101 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.841 ms | 0 - 73 MB | NPU
82
+ | ResNet101 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 39.302 ms | 8 - 19 MB | CPU
83
+ | ResNet101 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.811 ms | 0 - 76 MB | NPU
84
+ | ResNet101 | QNN_DLC | float | Snapdragon® X2 Elite | 1.957 ms | 1 - 1 MB | NPU
85
+ | ResNet101 | QNN_DLC | float | Snapdragon® X Elite | 3.544 ms | 1 - 1 MB | NPU
86
+ | ResNet101 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.415 ms | 0 - 124 MB | NPU
87
+ | ResNet101 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 18.269 ms | 1 - 67 MB | NPU
88
+ | ResNet101 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.325 ms | 0 - 3 MB | NPU
89
+ | ResNet101 | QNN_DLC | float | Qualcomm® SA8775P | 5.441 ms | 1 - 69 MB | NPU
90
+ | ResNet101 | QNN_DLC | float | Qualcomm® QCS9075 | 5.321 ms | 3 - 5 MB | NPU
91
+ | ResNet101 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.92 ms | 0 - 92 MB | NPU
92
+ | ResNet101 | QNN_DLC | float | Qualcomm® SA7255P | 18.269 ms | 1 - 67 MB | NPU
93
  | ResNet101 | QNN_DLC | float | Qualcomm® SA8295P | 5.664 ms | 1 - 43 MB | NPU
94
+ | ResNet101 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.96 ms | 0 - 67 MB | NPU
95
+ | ResNet101 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.615 ms | 1 - 69 MB | NPU
96
+ | ResNet101 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.695 ms | 0 - 0 MB | NPU
97
+ | ResNet101 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.281 ms | 0 - 0 MB | NPU
98
+ | ResNet101 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.968 ms | 0 - 123 MB | NPU
99
+ | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 4.705 ms | 0 - 2 MB | NPU
100
+ | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.957 ms | 0 - 70 MB | NPU
101
+ | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.272 ms | 0 - 2 MB | NPU
102
+ | ResNet101 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.531 ms | 0 - 72 MB | NPU
103
+ | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.322 ms | 0 - 2 MB | NPU
104
+ | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 11.647 ms | 0 - 196 MB | NPU
105
+ | ResNet101 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.781 ms | 0 - 121 MB | NPU
106
+ | ResNet101 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.957 ms | 0 - 70 MB | NPU
107
+ | ResNet101 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.926 ms | 0 - 68 MB | NPU
108
+ | ResNet101 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.781 ms | 0 - 68 MB | NPU
109
+ | ResNet101 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.803 ms | 0 - 80 MB | NPU
110
+ | ResNet101 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.744 ms | 0 - 72 MB | NPU
111
+ | ResNet101 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.384 ms | 0 - 190 MB | NPU
112
+ | ResNet101 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 18.223 ms | 0 - 124 MB | NPU
113
+ | ResNet101 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.316 ms | 0 - 2 MB | NPU
114
+ | ResNet101 | TFLITE | float | Qualcomm® SA8775P | 23.558 ms | 0 - 124 MB | NPU
115
+ | ResNet101 | TFLITE | float | Qualcomm® QCS9075 | 5.286 ms | 0 - 88 MB | NPU
116
+ | ResNet101 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.898 ms | 0 - 157 MB | NPU
117
+ | ResNet101 | TFLITE | float | Qualcomm® SA7255P | 18.223 ms | 0 - 124 MB | NPU
118
+ | ResNet101 | TFLITE | float | Qualcomm® SA8295P | 5.615 ms | 0 - 97 MB | NPU
119
+ | ResNet101 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.924 ms | 0 - 129 MB | NPU
120
+ | ResNet101 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.625 ms | 0 - 128 MB | NPU
121
+ | ResNet101 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.86 ms | 0 - 134 MB | NPU
122
+ | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS6490 | 4.23 ms | 0 - 45 MB | NPU
123
+ | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.733 ms | 0 - 69 MB | NPU
124
+ | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.145 ms | 0 - 2 MB | NPU
125
+ | ResNet101 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.423 ms | 0 - 71 MB | NPU
126
+ | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS9075 | 1.17 ms | 0 - 45 MB | NPU
127
+ | ResNet101 | TFLITE | w8a8 | Qualcomm® QCM6690 | 11.801 ms | 0 - 190 MB | NPU
128
+ | ResNet101 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.656 ms | 0 - 131 MB | NPU
129
+ | ResNet101 | TFLITE | w8a8 | Qualcomm® SA7255P | 2.733 ms | 0 - 69 MB | NPU
130
+ | ResNet101 | TFLITE | w8a8 | Qualcomm® SA8295P | 1.786 ms | 0 - 67 MB | NPU
131
+ | ResNet101 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.736 ms | 0 - 70 MB | NPU
132
+ | ResNet101 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.66 ms | 0 - 76 MB | NPU
133
+ | ResNet101 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.693 ms | 0 - 70 MB | NPU
 
134
 
135
  ## License
136
  * The license for the original implementation of ResNet101 can be found