Hugging Face's logo

qualcomm
/
DDRNet23-Slim

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
b45d4dc
·
verified ·
1 Parent(s): 33feab9

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +72 -73
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-segmentation
15
  DDRNet23Slim is a machine learning model that segments an image into semantic classes, specifically designed for road-based scenes. It is designed for the application of self-driving cars.
16
 
17
  This is based on the implementation of DDRNet23-Slim found [here](https://github.com/chenjun2hao/DDRNet.pytorch).
18
- 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/ddrnet23_slim) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
@@ -28,26 +28,26 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | 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/ddrnet23_slim/releases/v0.48.0/ddrnet23_slim-onnx-float.zip)
32
- | 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/ddrnet23_slim/releases/v0.48.0/ddrnet23_slim-onnx-w8a8.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddrnet23_slim/releases/v0.48.0/ddrnet23_slim-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddrnet23_slim/releases/v0.48.0/ddrnet23_slim-qnn_dlc-w8a8.zip)
35
- | 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/ddrnet23_slim/releases/v0.48.0/ddrnet23_slim-tflite-float.zip)
36
- | 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/ddrnet23_slim/releases/v0.48.0/ddrnet23_slim-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[DDRNet23-Slim on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/ddrnet23_slim)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/ddrnet23_slim) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
- See our repository for [DDRNet23-Slim on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/ddrnet23_slim) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -65,70 +65,69 @@ See our repository for [DDRNet23-Slim on GitHub](https://github.com/qualcomm/ai-
65
  ## Performance Summary
66
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
67
  |---|---|---|---|---|---|---
68
- | DDRNet23-Slim | ONNX | float | Snapdragon® X2 Elite | 10.937 ms | 22 - 22 MB | NPU
69
- | DDRNet23-Slim | ONNX | float | Snapdragon® X Elite | 27.931 ms | 24 - 24 MB | NPU
70
- | DDRNet23-Slim | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 19.68 ms | 30 - 309 MB | NPU
71
- | DDRNet23-Slim | ONNX | float | Qualcomm® QCS8550 (Proxy) | 28.907 ms | 24 - 27 MB | NPU
72
- | DDRNet23-Slim | ONNX | float | Qualcomm® QCS9075 | 39.526 ms | 24 - 51 MB | NPU
73
- | DDRNet23-Slim | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.576 ms | 3 - 197 MB | NPU
74
- | DDRNet23-Slim | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.474 ms | 30 - 259 MB | NPU
75
- | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® X2 Elite | 44.614 ms | 109 - 109 MB | NPU
76
- | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® X Elite | 87.138 ms | 109 - 109 MB | NPU
77
- | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 43.588 ms | 91 - 333 MB | NPU
78
- | DDRNet23-Slim | ONNX | w8a8 | Qualcomm® QCS6490 | 299.103 ms | 198 - 215 MB | CPU
79
- | DDRNet23-Slim | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 57.741 ms | 86 - 90 MB | NPU
80
- | DDRNet23-Slim | ONNX | w8a8 | Qualcomm® QCS9075 | 64.439 ms | 87 - 89 MB | NPU
81
- | DDRNet23-Slim | ONNX | w8a8 | Qualcomm® QCM6690 | 266.03 ms | 132 - 141 MB | CPU
82
- | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 42.186 ms | 81 - 269 MB | NPU
83
- | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 250.763 ms | 139 - 148 MB | CPU
84
- | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 43.559 ms | 77 - 269 MB | NPU
85
- | DDRNet23-Slim | QNN_DLC | float | Snapdragon® X2 Elite | 11.824 ms | 24 - 24 MB | NPU
86
- | DDRNet23-Slim | QNN_DLC | float | Snapdragon® X Elite | 33.583 ms | 24 - 24 MB | NPU
87
- | DDRNet23-Slim | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 22.45 ms | 22 - 307 MB | NPU
88
- | DDRNet23-Slim | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 98.319 ms | 24 - 222 MB | NPU
89
- | DDRNet23-Slim | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 32.53 ms | 24 - 224 MB | NPU
90
- | DDRNet23-Slim | QNN_DLC | float | Qualcomm® SA8775P | 40.267 ms | 24 - 223 MB | NPU
91
- | DDRNet23-Slim | QNN_DLC | float | Qualcomm® QCS9075 | 53.298 ms | 24 - 52 MB | NPU
92
- | DDRNet23-Slim | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 67.424 ms | 0 - 285 MB | NPU
93
- | DDRNet23-Slim | QNN_DLC | float | Qualcomm® SA7255P | 98.319 ms | 24 - 222 MB | NPU
94
- | DDRNet23-Slim | QNN_DLC | float | Qualcomm® SA8295P | 42.961 ms | 24 - 229 MB | NPU
95
- | DDRNet23-Slim | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 15.218 ms | 23 - 247 MB | NPU
96
- | DDRNet23-Slim | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.374 ms | 12 - 248 MB | NPU
97
- | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 47.73 ms | 6 - 6 MB | NPU
98
- | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® X Elite | 58.745 ms | 6 - 6 MB | NPU
99
- | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 42.01 ms | 6 - 255 MB | NPU
100
- | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 107.806 ms | 6 - 204 MB | NPU
101
- | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 56.2 ms | 6 - 8 MB | NPU
102
- | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® SA8775P | 56.982 ms | 6 - 205 MB | NPU
103
- | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 60.328 ms | 6 - 14 MB | NPU
104
- | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 61.369 ms | 6 - 256 MB | NPU
105
- | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® SA7255P | 107.806 ms | 6 - 204 MB | NPU
106
- | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® SA8295P | 64.388 ms | 6 - 208 MB | NPU
107
- | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 40.548 ms | 6 - 222 MB | NPU
108
- | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 47.033 ms | 6 - 238 MB | NPU
109
- | DDRNet23-Slim | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 22.502 ms | 2 - 297 MB | NPU
110
- | DDRNet23-Slim | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 98.293 ms | 0 - 203 MB | NPU
111
- | DDRNet23-Slim | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 32.944 ms | 2 - 4 MB | NPU
112
- | DDRNet23-Slim | TFLITE | float | Qualcomm® SA8775P | 40.147 ms | 2 - 206 MB | NPU
113
- | DDRNet23-Slim | TFLITE | float | Qualcomm® QCS9075 | 53.893 ms | 0 - 41 MB | NPU
114
- | DDRNet23-Slim | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 67.224 ms | 2 - 299 MB | NPU
115
- | DDRNet23-Slim | TFLITE | float | Qualcomm® SA7255P | 98.293 ms | 0 - 203 MB | NPU
116
- | DDRNet23-Slim | TFLITE | float | Qualcomm® SA8295P | 43.035 ms | 2 - 216 MB | NPU
117
- | DDRNet23-Slim | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 15.22 ms | 1 - 226 MB | NPU
118
- | DDRNet23-Slim | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.328 ms | 2 - 242 MB | NPU
119
- | DDRNet23-Slim | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 36.953 ms | 1 - 249 MB | NPU
120
- | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS6490 | 198.376 ms | 9 - 77 MB | NPU
121
- | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 95.138 ms | 1 - 198 MB | NPU
122
- | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 49.049 ms | 1 - 4 MB | NPU
123
- | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® SA8775P | 49.608 ms | 1 - 199 MB | NPU
124
- | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS9075 | 51.749 ms | 1 - 15 MB | NPU
125
- | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCM6690 | 223.252 ms | 10 - 196 MB | NPU
126
- | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 56.777 ms | 0 - 251 MB | NPU
127
- | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® SA7255P | 95.138 ms | 1 - 198 MB | NPU
128
- | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® SA8295P | 56.049 ms | 1 - 203 MB | NPU
129
- | DDRNet23-Slim | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 65.119 ms | 1 - 215 MB | NPU
130
- | DDRNet23-Slim | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 64.885 ms | 9 - 209 MB | NPU
131
- | DDRNet23-Slim | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 44.865 ms | 1 - 231 MB | NPU
132
 
133
  ## License
134
  * The license for the original implementation of DDRNet23-Slim can be found
 
15
  DDRNet23Slim is a machine learning model that segments an image into semantic classes, specifically designed for road-based scenes. It is designed for the application of self-driving cars.
16
 
17
  This is based on the implementation of DDRNet23-Slim found [here](https://github.com/chenjun2hao/DDRNet.pytorch).
18
+ 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/tree/v0.49.1/qai_hub_models/models/ddrnet23_slim) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | 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/ddrnet23_slim/releases/v0.49.1/ddrnet23_slim-onnx-float.zip)
32
+ | 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/ddrnet23_slim/releases/v0.49.1/ddrnet23_slim-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddrnet23_slim/releases/v0.49.1/ddrnet23_slim-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ddrnet23_slim/releases/v0.49.1/ddrnet23_slim-qnn_dlc-w8a8.zip)
35
+ | 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/ddrnet23_slim/releases/v0.49.1/ddrnet23_slim-tflite-float.zip)
36
+ | 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/ddrnet23_slim/releases/v0.49.1/ddrnet23_slim-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[DDRNet23-Slim on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/ddrnet23_slim)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/ddrnet23_slim) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
+ See our repository for [DDRNet23-Slim on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/ddrnet23_slim) for usage instructions.
51
 
52
  ## Model Details
53
 
 
65
  ## Performance Summary
66
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
67
  |---|---|---|---|---|---|---
68
+ | DDRNet23-Slim | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.464 ms | 31 - 261 MB | NPU
69
+ | DDRNet23-Slim | ONNX | float | Snapdragon® X2 Elite | 10.899 ms | 22 - 22 MB | NPU
70
+ | DDRNet23-Slim | ONNX | float | Snapdragon® X Elite | 28.085 ms | 24 - 24 MB | NPU
71
+ | DDRNet23-Slim | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 19.794 ms | 0 - 277 MB | NPU
72
+ | DDRNet23-Slim | ONNX | float | Qualcomm® QCS8550 (Proxy) | 29.255 ms | 24 - 27 MB | NPU
73
+ | DDRNet23-Slim | ONNX | float | Qualcomm® QCS9075 | 39.446 ms | 24 - 51 MB | NPU
74
+ | DDRNet23-Slim | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.531 ms | 7 - 201 MB | NPU
75
+ | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 44.105 ms | 58 - 250 MB | NPU
76
+ | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® X2 Elite | 45.035 ms | 109 - 109 MB | NPU
77
+ | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® X Elite | 64.712 ms | 109 - 109 MB | NPU
78
+ | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 43.106 ms | 92 - 337 MB | NPU
79
+ | DDRNet23-Slim | ONNX | w8a8 | Qualcomm® QCS6490 | 299.319 ms | 198 - 215 MB | CPU
80
+ | DDRNet23-Slim | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 57.348 ms | 86 - 217 MB | NPU
81
+ | DDRNet23-Slim | ONNX | w8a8 | Qualcomm® QCS9075 | 65.461 ms | 86 - 89 MB | NPU
82
+ | DDRNet23-Slim | ONNX | w8a8 | Qualcomm® QCM6690 | 266.19 ms | 207 - 216 MB | CPU
83
+ | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 42.08 ms | 81 - 269 MB | NPU
84
+ | DDRNet23-Slim | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 250.665 ms | 141 - 150 MB | CPU
85
+ | DDRNet23-Slim | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.368 ms | 12 - 248 MB | NPU
86
+ | DDRNet23-Slim | QNN_DLC | float | Snapdragon® X2 Elite | 11.788 ms | 24 - 24 MB | NPU
87
+ | DDRNet23-Slim | QNN_DLC | float | Snapdragon® X Elite | 33.664 ms | 24 - 24 MB | NPU
88
+ | DDRNet23-Slim | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 22.364 ms | 23 - 306 MB | NPU
89
+ | DDRNet23-Slim | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 98.295 ms | 24 - 222 MB | NPU
90
+ | DDRNet23-Slim | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 32.594 ms | 24 - 26 MB | NPU
91
+ | DDRNet23-Slim | QNN_DLC | float | Qualcomm® SA8775P | 40.269 ms | 24 - 223 MB | NPU
92
+ | DDRNet23-Slim | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 66.847 ms | 5 - 290 MB | NPU
93
+ | DDRNet23-Slim | QNN_DLC | float | Qualcomm® SA7255P | 98.295 ms | 24 - 222 MB | NPU
94
+ | DDRNet23-Slim | QNN_DLC | float | Qualcomm® SA8295P | 42.992 ms | 24 - 230 MB | NPU
95
+ | DDRNet23-Slim | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 15.419 ms | 23 - 246 MB | NPU
96
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 46.991 ms | 6 - 238 MB | NPU
97
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 47.765 ms | 6 - 6 MB | NPU
98
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® X Elite | 58.793 ms | 6 - 6 MB | NPU
99
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 41.852 ms | 6 - 257 MB | NPU
100
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 107.874 ms | 6 - 205 MB | NPU
101
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 56.064 ms | 6 - 8 MB | NPU
102
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® SA8775P | 56.885 ms | 6 - 205 MB | NPU
103
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 60.444 ms | 6 - 14 MB | NPU
104
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 61.535 ms | 6 - 257 MB | NPU
105
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® SA7255P | 107.874 ms | 6 - 205 MB | NPU
106
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Qualcomm® SA8295P | 64.37 ms | 6 - 208 MB | NPU
107
+ | DDRNet23-Slim | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 40.531 ms | 6 - 222 MB | NPU
108
+ | DDRNet23-Slim | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.336 ms | 2 - 242 MB | NPU
109
+ | DDRNet23-Slim | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 22.47 ms | 2 - 294 MB | NPU
110
+ | DDRNet23-Slim | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 98.31 ms | 3 - 206 MB | NPU
111
+ | DDRNet23-Slim | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 32.619 ms | 2 - 5 MB | NPU
112
+ | DDRNet23-Slim | TFLITE | float | Qualcomm® SA8775P | 40.119 ms | 2 - 206 MB | NPU
113
+ | DDRNet23-Slim | TFLITE | float | Qualcomm® QCS9075 | 53.826 ms | 0 - 41 MB | NPU
114
+ | DDRNet23-Slim | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 68.162 ms | 0 - 295 MB | NPU
115
+ | DDRNet23-Slim | TFLITE | float | Qualcomm® SA7255P | 98.31 ms | 3 - 206 MB | NPU
116
+ | DDRNet23-Slim | TFLITE | float | Qualcomm® SA8295P | 43.006 ms | 2 - 216 MB | NPU
117
+ | DDRNet23-Slim | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 15.283 ms | 2 - 228 MB | NPU
118
+ | DDRNet23-Slim | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 44.914 ms | 1 - 232 MB | NPU
119
+ | DDRNet23-Slim | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 37.128 ms | 1 - 253 MB | NPU
120
+ | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS6490 | 200.523 ms | 10 - 78 MB | NPU
121
+ | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 95.166 ms | 0 - 197 MB | NPU
122
+ | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 49.099 ms | 1 - 3 MB | NPU
123
+ | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® SA8775P | 49.614 ms | 1 - 198 MB | NPU
124
+ | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS9075 | 51.926 ms | 0 - 15 MB | NPU
125
+ | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCM6690 | 210.792 ms | 9 - 195 MB | NPU
126
+ | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 56.178 ms | 1 - 253 MB | NPU
127
+ | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® SA7255P | 95.166 ms | 0 - 197 MB | NPU
128
+ | DDRNet23-Slim | TFLITE | w8a8 | Qualcomm® SA8295P | 56.011 ms | 1 - 203 MB | NPU
129
+ | DDRNet23-Slim | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 65.077 ms | 1 - 215 MB | NPU
130
+ | DDRNet23-Slim | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 66.779 ms | 11 - 211 MB | NPU
 
131
 
132
  ## License
133
  * The license for the original implementation of DDRNet23-Slim can be found