Hugging Face's logo

qualcomm
/
ResNet50

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
ca8727c
·
verified ·
1 Parent(s): 49ca8f8

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 +75 -75
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
16
  ResNet50 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 ResNet50 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/resnet50) 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/resnet50/releases/v0.47.0/resnet50-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/resnet50/releases/v0.47.0/resnet50-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/resnet50/releases/v0.47.0/resnet50-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/resnet50/releases/v0.47.0/resnet50-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/resnet50/releases/v0.47.0/resnet50-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/resnet50/releases/v0.47.0/resnet50-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[ResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet50)**.
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/resnet50) 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 [ResNet50 on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/resnet50) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -64,73 +64,73 @@ See our repository for [ResNet50 on GitHub](https://github.com/quic/ai-hub-model
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
- | ResNet50 | ONNX | float | Snapdragon® X Elite | 2.093 ms | 49 - 49 MB | NPU
68
- | ResNet50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.487 ms | 0 - 80 MB | NPU
69
- | ResNet50 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.993 ms | 1 - 3 MB | NPU
70
- | ResNet50 | ONNX | float | Qualcomm® QCS9075 | 3.173 ms | 0 - 4 MB | NPU
71
- | ResNet50 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.242 ms | 0 - 54 MB | NPU
72
- | ResNet50 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.062 ms | 1 - 75 MB | NPU
73
- | ResNet50 | ONNX | float | Snapdragon® X2 Elite | 0.99 ms | 49 - 49 MB | NPU
74
- | ResNet50 | ONNX | w8a8 | Snapdragon® X Elite | 0.972 ms | 25 - 25 MB | NPU
75
- | ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.683 ms | 0 - 78 MB | NPU
76
- | ResNet50 | ONNX | w8a8 | Qualcomm® QCS6490 | 31.67 ms | 9 - 28 MB | CPU
77
- | ResNet50 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.9 ms | 0 - 30 MB | NPU
78
- | ResNet50 | ONNX | w8a8 | Qualcomm® QCS9075 | 0.973 ms | 0 - 3 MB | NPU
79
- | ResNet50 | ONNX | w8a8 | Qualcomm® QCM6690 | 23.437 ms | 6 - 15 MB | CPU
80
- | ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.597 ms | 0 - 48 MB | NPU
81
- | ResNet50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 17.748 ms | 11 - 19 MB | CPU
82
- | ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.555 ms | 0 - 44 MB | NPU
83
- | ResNet50 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.423 ms | 25 - 25 MB | NPU
84
- | ResNet50 | QNN_DLC | float | Snapdragon® X Elite | 2.328 ms | 1 - 1 MB | NPU
85
- | ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.598 ms | 0 - 77 MB | NPU
86
- | ResNet50 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 10.61 ms | 1 - 46 MB | NPU
 
87
  | ResNet50 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.192 ms | 1 - 2 MB | NPU
88
- | ResNet50 | QNN_DLC | float | Qualcomm® SA8775P | 3.365 ms | 1 - 47 MB | NPU
89
- | ResNet50 | QNN_DLC | float | Qualcomm® QCS9075 | 3.321 ms | 1 - 3 MB | NPU
90
- | ResNet50 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.759 ms | 0 - 62 MB | NPU
91
- | ResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 10.61 ms | 1 - 46 MB | NPU
92
- | ResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 3.663 ms | 0 - 30 MB | NPU
93
- | ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.259 ms | 0 - 48 MB | NPU
94
- | ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.083 ms | 1 - 51 MB | NPU
95
- | ResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 1.265 ms | 1 - 1 MB | NPU
96
- | ResNet50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.963 ms | 0 - 0 MB | NPU
97
- | ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.679 ms | 0 - 71 MB | NPU
98
- | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.981 ms | 2 - 4 MB | NPU
99
- | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.983 ms | 0 - 41 MB | NPU
100
- | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.897 ms | 0 - 35 MB | NPU
101
- | ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.106 ms | 0 - 44 MB | NPU
102
- | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.973 ms | 2 - 4 MB | NPU
103
- | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 6.5 ms | 0 - 161 MB | NPU
104
- | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.193 ms | 0 - 72 MB | NPU
105
- | ResNet50 | QNN_DLC | w8a8 | Qualcomm�� SA7255P | 1.983 ms | 0 - 41 MB | NPU
106
- | ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.427 ms | 0 - 38 MB | NPU
107
- | ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.532 ms | 0 - 42 MB | NPU
108
- | ResNet50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.236 ms | 0 - 48 MB | NPU
109
- | ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.485 ms | 0 - 42 MB | NPU
110
- | ResNet50 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.471 ms | 0 - 0 MB | NPU
111
- | ResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.579 ms | 0 - 118 MB | NPU
112
- | ResNet50 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 10.521 ms | 0 - 80 MB | NPU
113
- | ResNet50 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.209 ms | 0 - 2 MB | NPU
114
- | ResNet50 | TFLITE | float | Qualcomm® SA8775P | 3.372 ms | 0 - 81 MB | NPU
115
- | ResNet50 | TFLITE | float | Qualcomm® QCS9075 | 3.364 ms | 0 - 52 MB | NPU
116
- | ResNet50 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.738 ms | 0 - 107 MB | NPU
117
- | ResNet50 | TFLITE | float | Qualcomm® SA7255P | 10.521 ms | 0 - 80 MB | NPU
118
- | ResNet50 | TFLITE | float | Qualcomm® SA8295P | 3.635 ms | 0 - 67 MB | NPU
119
- | ResNet50 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.263 ms | 0 - 82 MB | NPU
120
- | ResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.085 ms | 0 - 83 MB | NPU
121
- | ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.592 ms | 0 - 73 MB | NPU
122
- | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.729 ms | 0 - 27 MB | NPU
123
- | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.748 ms | 0 - 40 MB | NPU
124
- | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.762 ms | 0 - 7 MB | NPU
125
- | ResNet50 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.983 ms | 0 - 43 MB | NPU
126
- | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.825 ms | 0 - 27 MB | NPU
127
- | ResNet50 | TFLITE | w8a8 | Qualcomm® QCM6690 | 6.238 ms | 0 - 159 MB | NPU
128
- | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.039 ms | 0 - 73 MB | NPU
129
- | ResNet50 | TFLITE | w8a8 | Qualcomm® SA7255P | 1.748 ms | 0 - 40 MB | NPU
130
- | ResNet50 | TFLITE | w8a8 | Qualcomm® SA8295P | 1.284 ms | 0 - 38 MB | NPU
131
- | ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.509 ms | 0 - 42 MB | NPU
132
- | ResNet50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.083 ms | 0 - 46 MB | NPU
133
- | ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.444 ms | 0 - 42 MB | NPU
134
 
135
  ## License
136
  * The license for the original implementation of ResNet50 can be found
 
16
  ResNet50 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 ResNet50 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/resnet50) 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/resnet50/releases/v0.48.0/resnet50-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/resnet50/releases/v0.48.0/resnet50-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/resnet50/releases/v0.48.0/resnet50-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/resnet50/releases/v0.48.0/resnet50-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/resnet50/releases/v0.48.0/resnet50-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/resnet50/releases/v0.48.0/resnet50-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[ResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet50)**.
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/resnet50) 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 [ResNet50 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/resnet50) 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
+ | ResNet50 | ONNX | float | Snapdragon® X2 Elite | 0.998 ms | 49 - 49 MB | NPU
68
+ | ResNet50 | ONNX | float | Snapdragon® X Elite | 2.088 ms | 49 - 49 MB | NPU
69
+ | ResNet50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.477 ms | 0 - 86 MB | NPU
70
+ | ResNet50 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.991 ms | 0 - 4 MB | NPU
71
+ | ResNet50 | ONNX | float | Qualcomm® QCS9075 | 3.172 ms | 1 - 4 MB | NPU
72
+ | ResNet50 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.246 ms | 0 - 44 MB | NPU
73
+ | ResNet50 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.059 ms | 1 - 75 MB | NPU
74
+ | ResNet50 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.417 ms | 25 - 25 MB | NPU
75
+ | ResNet50 | ONNX | w8a8 | Snapdragon® X Elite | 0.97 ms | 25 - 25 MB | NPU
76
+ | ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.676 ms | 0 - 79 MB | NPU
77
+ | ResNet50 | ONNX | w8a8 | Qualcomm® QCS6490 | 31.854 ms | 9 - 28 MB | CPU
78
+ | ResNet50 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.897 ms | 0 - 31 MB | NPU
79
+ | ResNet50 | ONNX | w8a8 | Qualcomm® QCS9075 | 0.968 ms | 0 - 3 MB | NPU
80
+ | ResNet50 | ONNX | w8a8 | Qualcomm® QCM6690 | 23.355 ms | 7 - 15 MB | CPU
81
+ | ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.578 ms | 0 - 42 MB | NPU
82
+ | ResNet50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 17.932 ms | 6 - 15 MB | CPU
83
+ | ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.554 ms | 0 - 44 MB | NPU
84
+ | ResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 1.254 ms | 1 - 1 MB | NPU
85
+ | ResNet50 | QNN_DLC | float | Snapdragon® X Elite | 2.317 ms | 1 - 1 MB | NPU
86
+ | ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.607 ms | 0 - 77 MB | NPU
87
+ | ResNet50 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 10.626 ms | 1 - 46 MB | NPU
88
  | ResNet50 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.192 ms | 1 - 2 MB | NPU
89
+ | ResNet50 | QNN_DLC | float | Qualcomm® SA8775P | 3.361 ms | 1 - 47 MB | NPU
90
+ | ResNet50 | QNN_DLC | float | Qualcomm® QCS9075 | 3.35 ms | 3 - 5 MB | NPU
91
+ | ResNet50 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.761 ms | 0 - 62 MB | NPU
92
+ | ResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 10.626 ms | 1 - 46 MB | NPU
93
+ | ResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 3.668 ms | 1 - 30 MB | NPU
94
+ | ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.262 ms | 1 - 48 MB | NPU
95
+ | ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.084 ms | 1 - 51 MB | NPU
96
+ | ResNet50 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.467 ms | 0 - 0 MB | NPU
97
+ | ResNet50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.962 ms | 0 - 0 MB | NPU
98
+ | ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.683 ms | 0 - 70 MB | NPU
99
+ | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 3.008 ms | 0 - 2 MB | NPU
100
+ | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.976 ms | 0 - 40 MB | NPU
101
+ | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.895 ms | 0 - 2 MB | NPU
102
+ | ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.096 ms | 0 - 44 MB | NPU
103
+ | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.972 ms | 0 - 2 MB | NPU
104
+ | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 6.477 ms | 0 - 161 MB | NPU
105
+ | ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.194 ms | 0 - 72 MB | NPU
106
+ | ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.976 ms | 0 - 40 MB | NPU
107
+ | ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.436 ms | 0 - 38 MB | NPU
108
+ | ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.531 ms | 0 - 39 MB | NPU
109
+ | ResNet50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.238 ms | 0 - 48 MB | NPU
110
+ | ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.481 ms | 0 - 42 MB | NPU
111
+ | ResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.584 ms | 0 - 120 MB | NPU
112
+ | ResNet50 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 10.491 ms | 0 - 80 MB | NPU
113
+ | ResNet50 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.2 ms | 0 - 2 MB | NPU
114
+ | ResNet50 | TFLITE | float | Qualcomm® SA8775P | 3.39 ms | 0 - 81 MB | NPU
115
+ | ResNet50 | TFLITE | float | Qualcomm® QCS9075 | 3.35 ms | 0 - 52 MB | NPU
116
+ | ResNet50 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.723 ms | 0 - 105 MB | NPU
117
+ | ResNet50 | TFLITE | float | Qualcomm® SA7255P | 10.491 ms | 0 - 80 MB | NPU
118
+ | ResNet50 | TFLITE | float | Qualcomm® SA8295P | 3.614 ms | 0 - 61 MB | NPU
119
+ | ResNet50 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.26 ms | 0 - 85 MB | NPU
120
+ | ResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.084 ms | 0 - 83 MB | NPU
121
+ | ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.586 ms | 0 - 78 MB | NPU
122
+ | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS6490 | 2.581 ms | 0 - 27 MB | NPU
123
+ | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.746 ms | 0 - 40 MB | NPU
124
+ | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.759 ms | 0 - 145 MB | NPU
125
+ | ResNet50 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.977 ms | 0 - 43 MB | NPU
126
+ | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.826 ms | 0 - 27 MB | NPU
127
+ | ResNet50 | TFLITE | w8a8 | Qualcomm® QCM6690 | 6.208 ms | 0 - 159 MB | NPU
128
+ | ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.052 ms | 0 - 73 MB | NPU
129
+ | ResNet50 | TFLITE | w8a8 | Qualcomm® SA7255P | 1.746 ms | 0 - 40 MB | NPU
130
+ | ResNet50 | TFLITE | w8a8 | Qualcomm® SA8295P | 1.28 ms | 0 - 37 MB | NPU
131
+ | ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.481 ms | 0 - 38 MB | NPU
132
+ | ResNet50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.086 ms | 0 - 46 MB | NPU
133
+ | ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.446 ms | 0 - 42 MB | NPU
 
134
 
135
  ## License
136
  * The license for the original implementation of ResNet50 can be found