Hugging Face's logo

qualcomm
/
ResNet18

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
1614cd9
·
verified ·
1 Parent(s): 0daa545

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 +105 -99
  2. release_assets.json +7 -7
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
16
  ResNet18 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 ResNet18 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/v0.57.3/src/qai_hub_models/models/resnet18) 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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.57.3/resnet18-onnx-float.zip)
33
- | 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/resnet18/releases/v0.57.3/resnet18-onnx-w8a8.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.57.3/resnet18-qnn_dlc-float.zip)
35
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.57.3/resnet18-qnn_dlc-w8a8.zip)
36
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.57.3/resnet18-tflite-float.zip)
37
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.57.3/resnet18-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[ResNet18 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet18)**.
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/v0.57.3/src/qai_hub_models/models/resnet18) 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 [ResNet18 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/resnet18) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -64,96 +64,102 @@ See our repository for [ResNet18 on GitHub](https://github.com/qualcomm/ai-hub-m
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
- | ResNet18 | ONNX | float | Snapdragon® X2 Elite | 0.513 ms | 212 - 212 MB | NPU
68
- | ResNet18 | ONNX | float | Snapdragon® X Elite | 1.022 ms | 181 - 181 MB | NPU
69
- | ResNet18 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.779 ms | 1 - 25 MB | NPU
70
- | ResNet18 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.839 ms | 1 - 28 MB | NPU
71
- | ResNet18 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.049 ms | 1 - 4 MB | NPU
72
- | ResNet18 | ONNX | float | Qualcomm® QCS8450 | 1.839 ms | 1 - 28 MB | NPU
73
- | ResNet18 | ONNX | float | Snapdragon® 8 Elite Mobile | 0.616 ms | 0 - 27 MB | NPU
74
- | ResNet18 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.552 ms | 1 - 23 MB | NPU
75
- | ResNet18 | ONNX | float | Qualcomm® QCS9075 | 1.803 ms | 1 - 46 MB | NPU
76
- | ResNet18 | ONNX | float | Qualcomm® QCS8750 | 0.616 ms | 0 - 27 MB | NPU
77
- | ResNet18 | ONNX | float | Qualcomm® QCS7181 | 1.022 ms | 181 - 181 MB | NPU
78
- | ResNet18 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.265 ms | 181 - 181 MB | NPU
79
- | ResNet18 | ONNX | w8a8 | Snapdragon® X Elite | 0.494 ms | 181 - 181 MB | NPU
80
- | ResNet18 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.41 ms | 0 - 38 MB | NPU
81
- | ResNet18 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.748 ms | 0 - 45 MB | NPU
82
- | ResNet18 | ONNX | w8a8 | Qualcomm® QCS6490 | 1.688 ms | 0 - 45 MB | NPU
83
- | ResNet18 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.55 ms | 0 - 79 MB | NPU
84
- | ResNet18 | ONNX | w8a8 | Qualcomm® QCS8450 | 0.748 ms | 0 - 45 MB | NPU
85
- | ResNet18 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.344 ms | 0 - 25 MB | NPU
86
- | ResNet18 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.65 ms | 0 - 29 MB | NPU
87
- | ResNet18 | ONNX | w8a8 | Qualcomm® QCM6690 | 3.125 ms | 0 - 31 MB | NPU
88
- | ResNet18 | ONNX | w8a8 | Qualcomm® QCS9075 | 0.667 ms | 0 - 45 MB | NPU
89
- | ResNet18 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.374 ms | 0 - 28 MB | NPU
90
- | ResNet18 | ONNX | w8a8 | Qualcomm® QCS7790 | 0.65 ms | 0 - 29 MB | NPU
91
- | ResNet18 | ONNX | w8a8 | Qualcomm® QCS8750 | 0.374 ms | 0 - 28 MB | NPU
92
- | ResNet18 | ONNX | w8a8 | Qualcomm® QCS7181 | 0.494 ms | 181 - 181 MB | NPU
93
- | ResNet18 | QNN_DLC | float | Snapdragon® X2 Elite | 0.66 ms | 1 - 1 MB | NPU
94
- | ResNet18 | QNN_DLC | float | Snapdragon® X Elite | 1.449 ms | 1 - 1 MB | NPU
95
- | ResNet18 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.92 ms | 0 - 35 MB | NPU
96
- | ResNet18 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.423 ms | 0 - 38 MB | NPU
97
- | ResNet18 | QNN_DLC | float | Qualcomm® QCS8275 | 5.875 ms | 1 - 24 MB | NPU
98
- | ResNet18 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.319 ms | 1 - 2 MB | NPU
99
- | ResNet18 | QNN_DLC | float | Qualcomm® QCS8450 | 2.423 ms | 0 - 38 MB | NPU
100
- | ResNet18 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.706 ms | 0 - 26 MB | NPU
101
- | ResNet18 | QNN_DLC | float | Qualcomm® SA8295P | 2.316 ms | 0 - 20 MB | NPU
102
- | ResNet18 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.593 ms | 1 - 29 MB | NPU
103
- | ResNet18 | QNN_DLC | float | Qualcomm® SA7255P | 5.875 ms | 1 - 24 MB | NPU
104
- | ResNet18 | QNN_DLC | float | Qualcomm® QCS9075 | 2.064 ms | 1 - 3 MB | NPU
105
- | ResNet18 | QNN_DLC | float | Qualcomm® QCS8750 | 0.706 ms | 0 - 26 MB | NPU
106
- | ResNet18 | QNN_DLC | float | Qualcomm® QCS7181 | 1.449 ms | 1 - 1 MB | NPU
107
- | ResNet18 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.302 ms | 0 - 0 MB | NPU
108
- | ResNet18 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.604 ms | 0 - 0 MB | NPU
109
- | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.417 ms | 0 - 48 MB | NPU
110
- | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.74 ms | 0 - 53 MB | NPU
111
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 1.814 ms | 0 - 2 MB | NPU
112
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 1.315 ms | 0 - 25 MB | NPU
113
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.543 ms | 0 - 11 MB | NPU
114
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.74 ms | 0 - 53 MB | NPU
115
- | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.266 ms | 0 - 24 MB | NPU
116
- | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.678 ms | 0 - 32 MB | NPU
117
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 3.238 ms | 0 - 33 MB | NPU
118
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.618 ms | 2 - 4 MB | NPU
119
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.315 ms | 0 - 25 MB | NPU
120
- | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.31 ms | 0 - 27 MB | NPU
121
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.97 ms | 0 - 22 MB | NPU
122
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 0.678 ms | 0 - 32 MB | NPU
123
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 0.31 ms | 0 - 27 MB | NPU
124
- | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 0.604 ms | 0 - 0 MB | NPU
125
- | ResNet18 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.919 ms | 0 - 55 MB | NPU
126
- | ResNet18 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.456 ms | 0 - 58 MB | NPU
127
- | ResNet18 | TFLITE | float | Qualcomm® QCS8275 | 5.871 ms | 0 - 26 MB | NPU
128
- | ResNet18 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.316 ms | 0 - 2 MB | NPU
129
- | ResNet18 | TFLITE | float | Qualcomm® SA8775P | 10.831 ms | 0 - 19 MB | GPU
130
- | ResNet18 | TFLITE | float | Qualcomm® SA8650P | 10.831 ms | 0 - 19 MB | GPU
131
- | ResNet18 | TFLITE | float | Qualcomm® SA8255P | 10.831 ms | 0 - 19 MB | GPU
132
- | ResNet18 | TFLITE | float | Qualcomm® QCS8450 | 2.456 ms | 0 - 58 MB | NPU
133
- | ResNet18 | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.702 ms | 0 - 26 MB | NPU
134
- | ResNet18 | TFLITE | float | Qualcomm® SA8295P | 2.294 ms | 0 - 22 MB | NPU
135
- | ResNet18 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.587 ms | 0 - 27 MB | NPU
136
- | ResNet18 | TFLITE | float | Qualcomm® SA7255P | 5.871 ms | 0 - 26 MB | NPU
137
- | ResNet18 | TFLITE | float | Qualcomm® QCS9075 | 2.037 ms | 0 - 25 MB | NPU
138
- | ResNet18 | TFLITE | float | Qualcomm® QCS8750 | 0.702 ms | 0 - 26 MB | NPU
139
- | ResNet18 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.298 ms | 0 - 53 MB | NPU
140
- | ResNet18 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.608 ms | 0 - 48 MB | NPU
141
- | ResNet18 | TFLITE | w8a8 | Qualcomm® QCS6490 | 1.541 ms | 0 - 13 MB | NPU
142
- | ResNet18 | TFLITE | w8a8 | Qualcomm® QCS8275 | 1.043 ms | 0 - 23 MB | NPU
143
- | ResNet18 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.389 ms | 0 - 2 MB | NPU
144
- | ResNet18 | TFLITE | w8a8 | Qualcomm® SA8775P | 11.13 ms | 1 - 22 MB | GPU
145
- | ResNet18 | TFLITE | w8a8 | Qualcomm® SA8650P | 11.13 ms | 1 - 22 MB | GPU
146
- | ResNet18 | TFLITE | w8a8 | Qualcomm® SA8255P | 11.13 ms | 1 - 22 MB | GPU
147
- | ResNet18 | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.608 ms | 0 - 48 MB | NPU
148
- | ResNet18 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.229 ms | 0 - 23 MB | NPU
149
- | ResNet18 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.549 ms | 0 - 31 MB | NPU
150
- | ResNet18 | TFLITE | w8a8 | Qualcomm® QCM6690 | 2.792 ms | 0 - 32 MB | NPU
151
- | ResNet18 | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.476 ms | 0 - 13 MB | NPU
152
- | ResNet18 | TFLITE | w8a8 | Qualcomm® SA7255P | 1.043 ms | 0 - 23 MB | NPU
153
- | ResNet18 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.241 ms | 0 - 27 MB | NPU
154
- | ResNet18 | TFLITE | w8a8 | Qualcomm® SA8295P | 0.769 ms | 0 - 21 MB | NPU
155
- | ResNet18 | TFLITE | w8a8 | Qualcomm® QCS7790 | 0.549 ms | 0 - 31 MB | NPU
156
- | ResNet18 | TFLITE | w8a8 | Qualcomm® QCS8750 | 0.241 ms | 0 - 27 MB | NPU
 
 
 
 
 
 
157
 
158
  ## License
159
  * The license for the original implementation of ResNet18 can be found
 
16
  ResNet18 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 ResNet18 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/v0.58.0/src/qai_hub_models/models/resnet18) 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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.58.0/resnet18-onnx-float.zip)
33
+ | 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/resnet18/releases/v0.58.0/resnet18-onnx-w8a8.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.58.0/resnet18-qnn_dlc-float.zip)
35
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.58.0/resnet18-qnn_dlc-w8a8.zip)
36
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.58.0/resnet18-tflite-float.zip)
37
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet18/releases/v0.58.0/resnet18-tflite-w8a8.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[ResNet18 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet18)**.
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/v0.58.0/src/qai_hub_models/models/resnet18) 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 [ResNet18 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/resnet18) 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
+ | ResNet18 | ONNX | float | Snapdragon® X2 Elite | 0.513 ms | 2 - 2 MB | NPU
68
+ | ResNet18 | ONNX | float | Snapdragon® X Elite | 1.019 ms | 22 - 22 MB | NPU
69
+ | ResNet18 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.775 ms | 0 - 38 MB | NPU
70
+ | ResNet18 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.839 ms | 1 - 39 MB | NPU
71
+ | ResNet18 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.051 ms | 0 - 142 MB | NPU
72
+ | ResNet18 | ONNX | float | Qualcomm® QCS8450 | 1.839 ms | 1 - 39 MB | NPU
73
+ | ResNet18 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.696 ms | 1 - 3 MB | NPU
74
+ | ResNet18 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.557 ms | 0 - 28 MB | NPU
75
+ | ResNet18 | ONNX | float | Snapdragon® 8 Elite Mobile | 0.616 ms | 0 - 24 MB | NPU
76
+ | ResNet18 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.616 ms | 0 - 24 MB | NPU
77
+ | ResNet18 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.019 ms | 22 - 22 MB | NPU
78
+ | ResNet18 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.308 ms | 1 - 1 MB | NPU
79
+ | ResNet18 | ONNX | w8a8 | Snapdragon® X Elite | 0.497 ms | 11 - 11 MB | NPU
80
+ | ResNet18 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.414 ms | 0 - 54 MB | NPU
81
+ | ResNet18 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.75 ms | 0 - 54 MB | NPU
82
+ | ResNet18 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.91 ms | 0 - 3 MB | NPU
83
+ | ResNet18 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.546 ms | 0 - 102 MB | NPU
84
+ | ResNet18 | ONNX | w8a8 | Qualcomm® QCS8450 | 0.75 ms | 0 - 54 MB | NPU
85
+ | ResNet18 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.359 ms | 0 - 24 MB | NPU
86
+ | ResNet18 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.646 ms | 0 - 33 MB | NPU
87
+ | ResNet18 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.342 ms | 0 - 25 MB | NPU
88
+ | ResNet18 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.655 ms | 0 - 3 MB | NPU
89
+ | ResNet18 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.114 ms | 0 - 36 MB | NPU
90
+ | ResNet18 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.646 ms | 0 - 33 MB | NPU
91
+ | ResNet18 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.359 ms | 0 - 24 MB | NPU
92
+ | ResNet18 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.497 ms | 11 - 11 MB | NPU
93
+ | ResNet18 | QNN_DLC | float | Snapdragon® X2 Elite | 0.661 ms | 1 - 1 MB | NPU
94
+ | ResNet18 | QNN_DLC | float | Snapdragon® X Elite | 1.443 ms | 1 - 1 MB | NPU
95
+ | ResNet18 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.91 ms | 0 - 34 MB | NPU
96
+ | ResNet18 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.433 ms | 0 - 37 MB | NPU
97
+ | ResNet18 | QNN_DLC | float | Qualcomm® QCS8275 | 5.839 ms | 1 - 24 MB | NPU
98
+ | ResNet18 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.322 ms | 1 - 40 MB | NPU
99
+ | ResNet18 | QNN_DLC | float | Qualcomm® SA8775P | 1.932 ms | 1 - 25 MB | NPU
100
+ | ResNet18 | QNN_DLC | float | Qualcomm® SA8650P | 1.932 ms | 1 - 25 MB | NPU
101
+ | ResNet18 | QNN_DLC | float | Qualcomm® SA8255P | 1.932 ms | 1 - 25 MB | NPU
102
+ | ResNet18 | QNN_DLC | float | Qualcomm® QCS8450 | 2.433 ms | 0 - 37 MB | NPU
103
+ | ResNet18 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.816 ms | 1 - 3 MB | NPU
104
+ | ResNet18 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.599 ms | 1 - 25 MB | NPU
105
+ | ResNet18 | QNN_DLC | float | Qualcomm® SA7255P | 5.839 ms | 1 - 24 MB | NPU
106
+ | ResNet18 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.707 ms | 1 - 24 MB | NPU
107
+ | ResNet18 | QNN_DLC | float | Qualcomm® SA8295P | 2.32 ms | 1 - 20 MB | NPU
108
+ | ResNet18 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.707 ms | 1 - 24 MB | NPU
109
+ | ResNet18 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.443 ms | 1 - 1 MB | NPU
110
+ | ResNet18 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.304 ms | 0 - 0 MB | NPU
111
+ | ResNet18 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.616 ms | 0 - 0 MB | NPU
112
+ | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.41 ms | 0 - 47 MB | NPU
113
+ | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.741 ms | 0 - 53 MB | NPU
114
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.035 ms | 2 - 4 MB | NPU
115
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 1.327 ms | 0 - 24 MB | NPU
116
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.543 ms | 0 - 3 MB | NPU
117
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.722 ms | 0 - 26 MB | NPU
118
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.722 ms | 0 - 26 MB | NPU
119
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.722 ms | 0 - 26 MB | NPU
120
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.741 ms | 0 - 53 MB | NPU
121
+ | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.308 ms | 0 - 22 MB | NPU
122
+ | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.677 ms | 0 - 32 MB | NPU
123
+ | ResNet18 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.276 ms | 0 - 24 MB | NPU
124
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.615 ms | 2 - 4 MB | NPU
125
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.228 ms | 0 - 33 MB | NPU
126
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.327 ms | 0 - 24 MB | NPU
127
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.962 ms | 0 - 22 MB | NPU
128
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.677 ms | 0 - 32 MB | NPU
129
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.308 ms | 0 - 22 MB | NPU
130
+ | ResNet18 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.616 ms | 0 - 0 MB | NPU
131
+ | ResNet18 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.919 ms | 0 - 59 MB | NPU
132
+ | ResNet18 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.457 ms | 0 - 60 MB | NPU
133
+ | ResNet18 | TFLITE | float | Qualcomm® QCS8275 | 5.829 ms | 0 - 26 MB | NPU
134
+ | ResNet18 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.319 ms | 0 - 3 MB | NPU
135
+ | ResNet18 | TFLITE | float | Qualcomm® SA8775P | 1.918 ms | 0 - 29 MB | NPU
136
+ | ResNet18 | TFLITE | float | Qualcomm® SA8650P | 1.918 ms | 0 - 29 MB | NPU
137
+ | ResNet18 | TFLITE | float | Qualcomm® SA8255P | 1.918 ms | 0 - 29 MB | NPU
138
+ | ResNet18 | TFLITE | float | Qualcomm® QCS8450 | 2.457 ms | 0 - 60 MB | NPU
139
+ | ResNet18 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.79 ms | 0 - 25 MB | NPU
140
+ | ResNet18 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.591 ms | 0 - 27 MB | NPU
141
+ | ResNet18 | TFLITE | float | Qualcomm® SA7255P | 5.829 ms | 0 - 26 MB | NPU
142
+ | ResNet18 | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.704 ms | 0 - 25 MB | NPU
143
+ | ResNet18 | TFLITE | float | Qualcomm® SA8295P | 2.279 ms | 0 - 21 MB | NPU
144
+ | ResNet18 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.704 ms | 0 - 25 MB | NPU
145
+ | ResNet18 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.294 ms | 0 - 47 MB | NPU
146
+ | ResNet18 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.603 ms | 0 - 51 MB | NPU
147
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.738 ms | 0 - 13 MB | NPU
148
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® QCS8275 | 1.031 ms | 0 - 23 MB | NPU
149
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.386 ms | 0 - 1 MB | NPU
150
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.558 ms | 0 - 25 MB | NPU
151
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® SA8650P | 0.558 ms | 0 - 25 MB | NPU
152
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® SA8255P | 0.558 ms | 0 - 25 MB | NPU
153
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.603 ms | 0 - 51 MB | NPU
154
+ | ResNet18 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.245 ms | 0 - 22 MB | NPU
155
+ | ResNet18 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.546 ms | 0 - 31 MB | NPU
156
+ | ResNet18 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.221 ms | 0 - 24 MB | NPU
157
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.468 ms | 0 - 13 MB | NPU
158
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 2.797 ms | 0 - 31 MB | NPU
159
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® SA7255P | 1.031 ms | 0 - 23 MB | NPU
160
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® SA8295P | 0.777 ms | 0 - 21 MB | NPU
161
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.546 ms | 0 - 31 MB | NPU
162
+ | ResNet18 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.245 ms | 0 - 22 MB | NPU
163
 
164
  ## License
165
  * The license for the original implementation of ResNet18 can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "w8a8": {
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/resnet18/releases/v0.57.3/resnet18-tflite-w8a8.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/resnet18/releases/v0.57.3/resnet18-qnn_dlc-w8a8.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/resnet18/releases/v0.57.3/resnet18-onnx-w8a8.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/resnet18/releases/v0.57.3/resnet18-tflite-float.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/resnet18/releases/v0.57.3/resnet18-qnn_dlc-float.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/resnet18/releases/v0.57.3/resnet18-onnx-float.zip"
49
  }
50
  }
51
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "w8a8": {
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/resnet18/releases/v0.58.0/resnet18-tflite-w8a8.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/resnet18/releases/v0.58.0/resnet18-qnn_dlc-w8a8.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/resnet18/releases/v0.58.0/resnet18-onnx-w8a8.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/resnet18/releases/v0.58.0/resnet18-tflite-float.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/resnet18/releases/v0.58.0/resnet18-qnn_dlc-float.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/resnet18/releases/v0.58.0/resnet18-onnx-float.zip"
49
  }
50
  }
51
  }