Hugging Face's logo

qualcomm
/
DenseNet-121

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
143e1cd
·
verified ·
1 Parent(s): cf1123a

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 +84 -93
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
16
  Densenet 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 DenseNet-121 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.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/densenet121) 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
 
@@ -29,28 +29,27 @@ 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/densenet121/releases/v0.47.0/densenet121-onnx-float.zip)
33
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/densenet121/releases/v0.47.0/densenet121-onnx-w8a16.zip)
34
- | 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/densenet121/releases/v0.47.0/densenet121-onnx-w8a8.zip)
35
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/densenet121/releases/v0.47.0/densenet121-qnn_dlc-float.zip)
36
- | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/densenet121/releases/v0.47.0/densenet121-qnn_dlc-w8a16.zip)
37
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/densenet121/releases/v0.47.0/densenet121-qnn_dlc-w8a8.zip)
38
- | 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/densenet121/releases/v0.47.0/densenet121-tflite-float.zip)
39
- | 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/densenet121/releases/v0.47.0/densenet121-tflite-w8a8.zip)
40
 
41
  For more device-specific assets and performance metrics, visit **[DenseNet-121 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/densenet121)**.
42
 
43
 
44
  ### Option 2: Export with Custom Configurations
45
 
46
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/densenet121) Python library to compile and export the model with your own:
47
  - Custom weights (e.g., fine-tuned checkpoints)
48
  - Custom input shapes
49
  - Target device and runtime configurations
50
 
51
  This option is ideal if you need to customize the model beyond the default configuration provided here.
52
 
53
- See our repository for [DenseNet-121 on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/densenet121) for usage instructions.
54
 
55
  ## Model Details
56
 
@@ -67,89 +66,81 @@ See our repository for [DenseNet-121 on GitHub](https://github.com/quic/ai-hub-m
67
  ## Performance Summary
68
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
69
  |---|---|---|---|---|---|---
70
- | DenseNet-121 | ONNX | float | Snapdragon® X Elite | 1.729 ms | 15 - 15 MB | NPU
71
- | DenseNet-121 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.075 ms | 0 - 95 MB | NPU
72
- | DenseNet-121 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.527 ms | 0 - 18 MB | NPU
73
- | DenseNet-121 | ONNX | float | Qualcomm® QCS9075 | 2.623 ms | 1 - 3 MB | NPU
74
- | DenseNet-121 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.782 ms | 0 - 45 MB | NPU
 
75
  | DenseNet-121 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.679 ms | 0 - 46 MB | NPU
76
- | DenseNet-121 | ONNX | float | Snapdragon® X2 Elite | 0.745 ms | 16 - 16 MB | NPU
77
- | DenseNet-121 | ONNX | w8a16 | Snapdragon® X Elite | 2.59 ms | 25 - 25 MB | NPU
78
- | DenseNet-121 | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.717 ms | 0 - 103 MB | NPU
79
- | DenseNet-121 | ONNX | w8a16 | Qualcomm® QCS6490 | 251.531 ms | 32 - 35 MB | CPU
80
- | DenseNet-121 | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 2.341 ms | 0 - 172 MB | NPU
81
- | DenseNet-121 | ONNX | w8a16 | Qualcomm® QCS9075 | 2.946 ms | 0 - 3 MB | NPU
82
- | DenseNet-121 | ONNX | w8a16 | Qualcomm® QCM6690 | 115.26 ms | 21 - 31 MB | CPU
83
- | DenseNet-121 | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.324 ms | 0 - 77 MB | NPU
84
- | DenseNet-121 | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 103.638 ms | 30 - 41 MB | CPU
85
- | DenseNet-121 | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.129 ms | 0 - 79 MB | NPU
86
- | DenseNet-121 | ONNX | w8a16 | Snapdragon® X2 Elite | 1.235 ms | 27 - 27 MB | NPU
87
- | DenseNet-121 | ONNX | w8a8 | Snapdragon® X Elite | 28.06 ms | 33 - 33 MB | NPU
88
- | DenseNet-121 | ONNX | w8a8 | Qualcomm® QCS6490 | 111.592 ms | 22 - 29 MB | CPU
89
- | DenseNet-121 | ONNX | w8a8 | Qualcomm® QCS9075 | 33.165 ms | 21 - 24 MB | NPU
90
- | DenseNet-121 | ONNX | w8a8 | Qualcomm® QCM6690 | 51.762 ms | 22 - 37 MB | CPU
91
- | DenseNet-121 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 14.159 ms | 22 - 101 MB | NPU
92
- | DenseNet-121 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 45.988 ms | 11 - 27 MB | CPU
93
- | DenseNet-121 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 18.887 ms | 22 - 100 MB | NPU
94
- | DenseNet-121 | ONNX | w8a8 | Snapdragon® X2 Elite | 18.347 ms | 32 - 32 MB | NPU
95
- | DenseNet-121 | QNN_DLC | float | Snapdragon® X Elite | 2.011 ms | 1 - 1 MB | NPU
96
- | DenseNet-121 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.197 ms | 0 - 79 MB | NPU
97
- | DenseNet-121 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 7.77 ms | 1 - 39 MB | NPU
98
- | DenseNet-121 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.783 ms | 0 - 7 MB | NPU
99
- | DenseNet-121 | QNN_DLC | float | Qualcomm® SA8775P | 2.694 ms | 1 - 43 MB | NPU
100
- | DenseNet-121 | QNN_DLC | float | Qualcomm® QCS9075 | 2.791 ms | 1 - 3 MB | NPU
101
- | DenseNet-121 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.312 ms | 0 - 75 MB | NPU
102
- | DenseNet-121 | QNN_DLC | float | Qualcomm® SA7255P | 7.77 ms | 1 - 39 MB | NPU
103
- | DenseNet-121 | QNN_DLC | float | Qualcomm® SA8295P | 3.03 ms | 1 - 36 MB | NPU
104
- | DenseNet-121 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.859 ms | 0 - 39 MB | NPU
105
- | DenseNet-121 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.706 ms | 1 - 44 MB | NPU
106
- | DenseNet-121 | QNN_DLC | float | Snapdragon® X2 Elite | 0.968 ms | 1 - 1 MB | NPU
107
- | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® X Elite | 3.47 ms | 0 - 0 MB | NPU
108
- | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.122 ms | 0 - 89 MB | NPU
109
- | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 6.275 ms | 0 - 62 MB | NPU
110
- | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 3.123 ms | 0 - 86 MB | NPU
111
- | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® SA8775P | 3.51 ms | 0 - 65 MB | NPU
112
- | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 3.406 ms | 0 - 2 MB | NPU
113
- | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 5.033 ms | 0 - 88 MB | NPU
114
- | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® SA7255P | 6.275 ms | 0 - 62 MB | NPU
115
- | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® SA8295P | 5.589 ms | 0 - 61 MB | NPU
116
- | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.754 ms | 0 - 60 MB | NPU
117
- | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.222 ms | 0 - 72 MB | NPU
118
- | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.563 ms | 0 - 0 MB | NPU
119
- | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® X Elite | 2.638 ms | 0 - 0 MB | NPU
120
- | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.703 ms | 0 - 77 MB | NPU
121
- | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 4.889 ms | 0 - 57 MB | NPU
122
- | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.366 ms | 0 - 17 MB | NPU
123
- | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 11.689 ms | 0 - 58 MB | NPU
124
- | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 2.569 ms | 0 - 2 MB | NPU
125
- | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 2.934 ms | 0 - 81 MB | NPU
126
- | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 4.889 ms | 0 - 57 MB | NPU
127
- | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 3.457 ms | 0 - 56 MB | NPU
128
- | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.044 ms | 0 - 59 MB | NPU
129
- | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.897 ms | 0 - 64 MB | NPU
130
- | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 1.187 ms | 0 - 0 MB | NPU
131
- | DenseNet-121 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.205 ms | 0 - 96 MB | NPU
132
- | DenseNet-121 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 7.787 ms | 0 - 55 MB | NPU
133
- | DenseNet-121 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.799 ms | 0 - 3 MB | NPU
134
- | DenseNet-121 | TFLITE | float | Qualcomm® SA8775P | 11.956 ms | 0 - 55 MB | NPU
135
- | DenseNet-121 | TFLITE | float | Qualcomm® QCS9075 | 2.814 ms | 0 - 18 MB | NPU
136
- | DenseNet-121 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.329 ms | 0 - 92 MB | NPU
137
- | DenseNet-121 | TFLITE | float | Qualcomm® SA7255P | 7.787 ms | 0 - 55 MB | NPU
138
- | DenseNet-121 | TFLITE | float | Qualcomm® SA8295P | 3.065 ms | 0 - 52 MB | NPU
139
- | DenseNet-121 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.852 ms | 0 - 59 MB | NPU
140
- | DenseNet-121 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.708 ms | 0 - 59 MB | NPU
141
- | DenseNet-121 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.586 ms | 0 - 83 MB | NPU
142
- | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS6490 | 93.643 ms | 6 - 34 MB | NPU
143
- | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 4.546 ms | 0 - 58 MB | NPU
144
- | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.225 ms | 0 - 115 MB | NPU
145
- | DenseNet-121 | TFLITE | w8a8 | Qualcomm® SA8775P | 2.604 ms | 0 - 61 MB | NPU
146
- | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS9075 | 2.422 ms | 0 - 11 MB | NPU
147
- | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 2.646 ms | 0 - 84 MB | NPU
148
- | DenseNet-121 | TFLITE | w8a8 | Qualcomm® SA7255P | 4.546 ms | 0 - 58 MB | NPU
149
- | DenseNet-121 | TFLITE | w8a8 | Qualcomm® SA8295P | 3.306 ms | 0 - 57 MB | NPU
150
- | DenseNet-121 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.014 ms | 0 - 62 MB | NPU
151
- | DenseNet-121 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 26.804 ms | 6 - 171 MB | NPU
152
- | DenseNet-121 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.861 ms | 0 - 65 MB | NPU
153
 
154
  ## License
155
  * The license for the original implementation of DenseNet-121 can be found
 
16
  Densenet 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 DenseNet-121 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.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/densenet121) 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/densenet121/releases/v0.48.0/densenet121-onnx-float.zip)
33
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/densenet121/releases/v0.48.0/densenet121-onnx-w8a16.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/densenet121/releases/v0.48.0/densenet121-qnn_dlc-float.zip)
35
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/densenet121/releases/v0.48.0/densenet121-qnn_dlc-w8a16.zip)
36
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/densenet121/releases/v0.48.0/densenet121-qnn_dlc-w8a8.zip)
37
+ | 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/densenet121/releases/v0.48.0/densenet121-tflite-float.zip)
38
+ | 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/densenet121/releases/v0.48.0/densenet121-tflite-w8a8.zip)
 
39
 
40
  For more device-specific assets and performance metrics, visit **[DenseNet-121 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/densenet121)**.
41
 
42
 
43
  ### Option 2: Export with Custom Configurations
44
 
45
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/densenet121) Python library to compile and export the model with your own:
46
  - Custom weights (e.g., fine-tuned checkpoints)
47
  - Custom input shapes
48
  - Target device and runtime configurations
49
 
50
  This option is ideal if you need to customize the model beyond the default configuration provided here.
51
 
52
+ See our repository for [DenseNet-121 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/densenet121) for usage instructions.
53
 
54
  ## Model Details
55
 
 
66
  ## Performance Summary
67
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
68
  |---|---|---|---|---|---|---
69
+ | DenseNet-121 | ONNX | float | Snapdragon® X2 Elite | 0.747 ms | 16 - 16 MB | NPU
70
+ | DenseNet-121 | ONNX | float | Snapdragon® X Elite | 1.734 ms | 15 - 15 MB | NPU
71
+ | DenseNet-121 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.082 ms | 0 - 88 MB | NPU
72
+ | DenseNet-121 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.521 ms | 0 - 18 MB | NPU
73
+ | DenseNet-121 | ONNX | float | Qualcomm® QCS9075 | 2.606 ms | 1 - 3 MB | NPU
74
+ | DenseNet-121 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.784 ms | 0 - 46 MB | NPU
75
  | DenseNet-121 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.679 ms | 0 - 46 MB | NPU
76
+ | DenseNet-121 | ONNX | w8a16 | Snapdragon® X2 Elite | 1.239 ms | 27 - 27 MB | NPU
77
+ | DenseNet-121 | ONNX | w8a16 | Snapdragon® X Elite | 2.597 ms | 25 - 25 MB | NPU
78
+ | DenseNet-121 | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.706 ms | 0 - 103 MB | NPU
79
+ | DenseNet-121 | ONNX | w8a16 | Qualcomm® QCS6490 | 255.731 ms | 32 - 35 MB | CPU
80
+ | DenseNet-121 | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 2.348 ms | 0 - 32 MB | NPU
81
+ | DenseNet-121 | ONNX | w8a16 | Qualcomm® QCS9075 | 2.951 ms | 0 - 3 MB | NPU
82
+ | DenseNet-121 | ONNX | w8a16 | Qualcomm® QCM6690 | 115.43 ms | 20 - 31 MB | CPU
83
+ | DenseNet-121 | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.321 ms | 0 - 77 MB | NPU
84
+ | DenseNet-121 | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 103.297 ms | 30 - 41 MB | CPU
85
+ | DenseNet-121 | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.125 ms | 0 - 79 MB | NPU
86
+ | DenseNet-121 | QNN_DLC | float | Snapdragon® X2 Elite | 0.953 ms | 1 - 1 MB | NPU
87
+ | DenseNet-121 | QNN_DLC | float | Snapdragon® X Elite | 2.027 ms | 1 - 1 MB | NPU
88
+ | DenseNet-121 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.192 ms | 0 - 80 MB | NPU
89
+ | DenseNet-121 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 7.774 ms | 1 - 39 MB | NPU
90
+ | DenseNet-121 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.782 ms | 1 - 2 MB | NPU
91
+ | DenseNet-121 | QNN_DLC | float | Qualcomm® SA8775P | 11.875 ms | 1 - 39 MB | NPU
92
+ | DenseNet-121 | QNN_DLC | float | Qualcomm® QCS9075 | 2.767 ms | 1 - 3 MB | NPU
93
+ | DenseNet-121 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.269 ms | 0 - 79 MB | NPU
94
+ | DenseNet-121 | QNN_DLC | float | Qualcomm® SA7255P | 7.774 ms | 1 - 39 MB | NPU
95
+ | DenseNet-121 | QNN_DLC | float | Qualcomm® SA8295P | 3.044 ms | 0 - 36 MB | NPU
96
+ | DenseNet-121 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.862 ms | 0 - 43 MB | NPU
97
+ | DenseNet-121 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.707 ms | 1 - 43 MB | NPU
98
+ | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.584 ms | 0 - 0 MB | NPU
99
+ | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® X Elite | 3.458 ms | 0 - 0 MB | NPU
100
+ | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.146 ms | 0 - 90 MB | NPU
101
+ | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 6.279 ms | 0 - 64 MB | NPU
102
+ | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 3.14 ms | 0 - 2 MB | NPU
103
+ | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® SA8775P | 3.503 ms | 0 - 65 MB | NPU
104
+ | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 3.404 ms | 0 - 2 MB | NPU
105
+ | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 5.048 ms | 0 - 90 MB | NPU
106
+ | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® SA7255P | 6.279 ms | 0 - 64 MB | NPU
107
+ | DenseNet-121 | QNN_DLC | w8a16 | Qualcomm® SA8295P | 5.59 ms | 0 - 61 MB | NPU
108
+ | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.761 ms | 0 - 58 MB | NPU
109
+ | DenseNet-121 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.22 ms | 0 - 72 MB | NPU
110
+ | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 1.15 ms | 0 - 0 MB | NPU
111
+ | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® X Elite | 2.641 ms | 0 - 0 MB | NPU
112
+ | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.695 ms | 0 - 82 MB | NPU
113
+ | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 4.884 ms | 0 - 59 MB | NPU
114
+ | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.38 ms | 0 - 2 MB | NPU
115
+ | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 2.707 ms | 0 - 59 MB | NPU
116
+ | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 2.567 ms | 0 - 2 MB | NPU
117
+ | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 2.862 ms | 0 - 77 MB | NPU
118
+ | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 4.884 ms | 0 - 59 MB | NPU
119
+ | DenseNet-121 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 3.462 ms | 0 - 56 MB | NPU
120
+ | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.046 ms | 0 - 58 MB | NPU
121
+ | DenseNet-121 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.907 ms | 0 - 64 MB | NPU
122
+ | DenseNet-121 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.196 ms | 0 - 96 MB | NPU
123
+ | DenseNet-121 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 7.803 ms | 0 - 55 MB | NPU
124
+ | DenseNet-121 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.804 ms | 0 - 9 MB | NPU
125
+ | DenseNet-121 | TFLITE | float | Qualcomm® SA8775P | 2.726 ms | 0 - 57 MB | NPU
126
+ | DenseNet-121 | TFLITE | float | Qualcomm® QCS9075 | 2.823 ms | 0 - 18 MB | NPU
127
+ | DenseNet-121 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.293 ms | 0 - 92 MB | NPU
128
+ | DenseNet-121 | TFLITE | float | Qualcomm® SA7255P | 7.803 ms | 0 - 55 MB | NPU
129
+ | DenseNet-121 | TFLITE | float | Qualcomm® SA8295P | 3.07 ms | 0 - 53 MB | NPU
130
+ | DenseNet-121 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.85 ms | 0 - 58 MB | NPU
131
+ | DenseNet-121 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.71 ms | 0 - 59 MB | NPU
132
+ | DenseNet-121 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.592 ms | 0 - 85 MB | NPU
133
+ | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS6490 | 87.29 ms | 6 - 34 MB | NPU
134
+ | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 4.538 ms | 0 - 58 MB | NPU
135
+ | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.218 ms | 0 - 2 MB | NPU
136
+ | DenseNet-121 | TFLITE | w8a8 | Qualcomm® SA8775P | 2.602 ms | 0 - 62 MB | NPU
137
+ | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS9075 | 2.425 ms | 0 - 11 MB | NPU
138
+ | DenseNet-121 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 2.647 ms | 0 - 85 MB | NPU
139
+ | DenseNet-121 | TFLITE | w8a8 | Qualcomm® SA7255P | 4.538 ms | 0 - 58 MB | NPU
140
+ | DenseNet-121 | TFLITE | w8a8 | Qualcomm® SA8295P | 3.313 ms | 0 - 57 MB | NPU
141
+ | DenseNet-121 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.009 ms | 0 - 57 MB | NPU
142
+ | DenseNet-121 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 26.363 ms | 6 - 172 MB | NPU
143
+ | DenseNet-121 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.862 ms | 0 - 65 MB | NPU
 
 
 
 
 
 
 
 
 
144
 
145
  ## License
146
  * The license for the original implementation of DenseNet-121 can be found