qaihm-bot commited on
Commit
0fdc89f
·
verified ·
1 Parent(s): e89b94b

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

Files changed (1) hide show
  1. README.md +76 -76
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-segmentation
15
  DeepLabXception is a semantic segmentation model supporting multiple backbones like ResNet-101 and Xception, with flexible dataset compatibility including COCO, VOC, and Cityscapes.
16
 
17
  This is based on the implementation of DeepLabXception found [here](https://github.com/LikeLy-Journey/SegmenTron).
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/deeplab_xception) 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/deeplab_xception/releases/v0.48.0/deeplab_xception-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/deeplab_xception/releases/v0.48.0/deeplab_xception-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/deeplab_xception/releases/v0.48.0/deeplab_xception-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/deeplab_xception/releases/v0.48.0/deeplab_xception-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/deeplab_xception/releases/v0.48.0/deeplab_xception-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/deeplab_xception/releases/v0.48.0/deeplab_xception-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[DeepLabXception on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/deeplab_xception)**.
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/deeplab_xception) 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 [DeepLabXception on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/deeplab_xception) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,73 +63,73 @@ See our repository for [DeepLabXception on GitHub](https://github.com/qualcomm/a
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | DeepLabXception | ONNX | float | Snapdragon® X2 Elite | 10.281 ms | 86 - 86 MB | NPU
67
- | DeepLabXception | ONNX | float | Snapdragon® X Elite | 22.717 ms | 85 - 85 MB | NPU
68
- | DeepLabXception | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 16.878 ms | 3 - 368 MB | NPU
69
- | DeepLabXception | ONNX | float | Qualcomm® QCS8550 (Proxy) | 22.395 ms | 0 - 96 MB | NPU
70
- | DeepLabXception | ONNX | float | Qualcomm® QCS9075 | 32.127 ms | 3 - 8 MB | NPU
71
- | DeepLabXception | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.119 ms | 1 - 252 MB | NPU
72
- | DeepLabXception | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.729 ms | 3 - 255 MB | NPU
73
- | DeepLabXception | ONNX | w8a8 | Snapdragon® X2 Elite | 3.341 ms | 44 - 44 MB | NPU
74
- | DeepLabXception | ONNX | w8a8 | Snapdragon® X Elite | 8.009 ms | 44 - 44 MB | NPU
75
- | DeepLabXception | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 5.249 ms | 0 - 388 MB | NPU
76
- | DeepLabXception | ONNX | w8a8 | Qualcomm® QCS6490 | 311.091 ms | 91 - 113 MB | CPU
77
- | DeepLabXception | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 7.436 ms | 0 - 61 MB | NPU
78
- | DeepLabXception | ONNX | w8a8 | Qualcomm® QCS9075 | 7.611 ms | 0 - 4 MB | NPU
79
- | DeepLabXception | ONNX | w8a8 | Qualcomm® QCM6690 | 244.195 ms | 59 - 72 MB | CPU
80
- | DeepLabXception | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 4.239 ms | 0 - 281 MB | NPU
81
- | DeepLabXception | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 229.357 ms | 89 - 102 MB | CPU
82
- | DeepLabXception | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.06 ms | 0 - 292 MB | NPU
83
- | DeepLabXception | QNN_DLC | float | Snapdragon® X2 Elite | 11.208 ms | 3 - 3 MB | NPU
84
- | DeepLabXception | QNN_DLC | float | Snapdragon® X Elite | 22.689 ms | 3 - 3 MB | NPU
85
- | DeepLabXception | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 15.977 ms | 0 - 365 MB | NPU
86
- | DeepLabXception | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 113.17 ms | 0 - 244 MB | NPU
87
- | DeepLabXception | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 21.99 ms | 3 - 5 MB | NPU
88
- | DeepLabXception | QNN_DLC | float | Qualcomm® SA8775P | 30.587 ms | 1 - 245 MB | NPU
89
- | DeepLabXception | QNN_DLC | float | Qualcomm® QCS9075 | 35.269 ms | 3 - 8 MB | NPU
90
- | DeepLabXception | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 45.66 ms | 0 - 360 MB | NPU
91
- | DeepLabXception | QNN_DLC | float | Qualcomm® SA7255P | 113.17 ms | 0 - 244 MB | NPU
92
- | DeepLabXception | QNN_DLC | float | Qualcomm® SA8295P | 38.892 ms | 0 - 242 MB | NPU
93
- | DeepLabXception | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 12.197 ms | 0 - 252 MB | NPU
94
- | DeepLabXception | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 9.228 ms | 3 - 258 MB | NPU
95
- | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 3.85 ms | 1 - 1 MB | NPU
96
- | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® X Elite | 8.543 ms | 1 - 1 MB | NPU
97
- | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 5.561 ms | 1 - 373 MB | NPU
98
- | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 33.733 ms | 1 - 3 MB | NPU
99
- | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 20.353 ms | 1 - 282 MB | NPU
100
- | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 7.912 ms | 1 - 212 MB | NPU
101
- | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® SA8775P | 8.096 ms | 1 - 284 MB | NPU
102
- | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 8.609 ms | 1 - 3 MB | NPU
103
- | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 121.601 ms | 1 - 303 MB | NPU
104
- | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 13.818 ms | 1 - 369 MB | NPU
105
- | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® SA7255P | 20.353 ms | 1 - 282 MB | NPU
106
- | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® SA8295P | 12.655 ms | 1 - 276 MB | NPU
107
- | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 4.362 ms | 0 - 275 MB | NPU
108
- | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 12.1 ms | 1 - 277 MB | NPU
109
- | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.264 ms | 1 - 275 MB | NPU
110
- | DeepLabXception | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 16.186 ms | 0 - 484 MB | NPU
111
- | DeepLabXception | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 113.246 ms | 0 - 358 MB | NPU
112
- | DeepLabXception | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 21.206 ms | 0 - 3 MB | NPU
113
- | DeepLabXception | TFLITE | float | Qualcomm® SA8775P | 30.539 ms | 0 - 358 MB | NPU
114
- | DeepLabXception | TFLITE | float | Qualcomm® QCS9075 | 35.04 ms | 0 - 93 MB | NPU
115
- | DeepLabXception | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 46.675 ms | 1 - 472 MB | NPU
116
- | DeepLabXception | TFLITE | float | Qualcomm® SA7255P | 113.246 ms | 0 - 358 MB | NPU
117
- | DeepLabXception | TFLITE | float | Qualcomm® SA8295P | 38.653 ms | 0 - 348 MB | NPU
118
- | DeepLabXception | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 12.199 ms | 0 - 367 MB | NPU
119
- | DeepLabXception | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 9.22 ms | 0 - 365 MB | NPU
120
- | DeepLabXception | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 4.958 ms | 0 - 372 MB | NPU
121
- | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS6490 | 32.146 ms | 0 - 58 MB | NPU
122
- | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 18.903 ms | 0 - 284 MB | NPU
123
- | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 6.933 ms | 0 - 3 MB | NPU
124
- | DeepLabXception | TFLITE | w8a8 | Qualcomm® SA8775P | 7.217 ms | 0 - 285 MB | NPU
125
- | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS9075 | 7.452 ms | 0 - 47 MB | NPU
126
- | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCM6690 | 91.151 ms | 0 - 295 MB | NPU
127
- | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 11.984 ms | 0 - 366 MB | NPU
128
- | DeepLabXception | TFLITE | w8a8 | Qualcomm® SA7255P | 18.903 ms | 0 - 284 MB | NPU
129
- | DeepLabXception | TFLITE | w8a8 | Qualcomm® SA8295P | 11.552 ms | 0 - 274 MB | NPU
130
- | DeepLabXception | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 3.918 ms | 0 - 273 MB | NPU
131
- | DeepLabXception | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 11.81 ms | 0 - 268 MB | NPU
132
- | DeepLabXception | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 2.899 ms | 0 - 267 MB | NPU
133
 
134
  ## License
135
  * The license for the original implementation of DeepLabXception can be found
 
15
  DeepLabXception is a semantic segmentation model supporting multiple backbones like ResNet-101 and Xception, with flexible dataset compatibility including COCO, VOC, and Cityscapes.
16
 
17
  This is based on the implementation of DeepLabXception found [here](https://github.com/LikeLy-Journey/SegmenTron).
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/deeplab_xception) 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/deeplab_xception/releases/v0.49.1/deeplab_xception-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/deeplab_xception/releases/v0.49.1/deeplab_xception-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/deeplab_xception/releases/v0.49.1/deeplab_xception-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/deeplab_xception/releases/v0.49.1/deeplab_xception-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/deeplab_xception/releases/v0.49.1/deeplab_xception-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/deeplab_xception/releases/v0.49.1/deeplab_xception-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[DeepLabXception on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/deeplab_xception)**.
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/deeplab_xception) 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 [DeepLabXception on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/deeplab_xception) for usage instructions.
51
 
52
  ## Model Details
53
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | DeepLabXception | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.748 ms | 3 - 254 MB | NPU
67
+ | DeepLabXception | ONNX | float | Snapdragon® X2 Elite | 10.317 ms | 86 - 86 MB | NPU
68
+ | DeepLabXception | ONNX | float | Snapdragon® X Elite | 22.693 ms | 85 - 85 MB | NPU
69
+ | DeepLabXception | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 16.739 ms | 0 - 362 MB | NPU
70
+ | DeepLabXception | ONNX | float | Qualcomm® QCS8550 (Proxy) | 22.447 ms | 0 - 375 MB | NPU
71
+ | DeepLabXception | ONNX | float | Qualcomm® QCS9075 | 32.515 ms | 3 - 8 MB | NPU
72
+ | DeepLabXception | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.121 ms | 1 - 241 MB | NPU
73
+ | DeepLabXception | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.06 ms | 0 - 293 MB | NPU
74
+ | DeepLabXception | ONNX | w8a8 | Snapdragon® X2 Elite | 3.351 ms | 44 - 44 MB | NPU
75
+ | DeepLabXception | ONNX | w8a8 | Snapdragon® X Elite | 8.012 ms | 44 - 44 MB | NPU
76
+ | DeepLabXception | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 5.301 ms | 0 - 390 MB | NPU
77
+ | DeepLabXception | ONNX | w8a8 | Qualcomm® QCS6490 | 308.978 ms | 89 - 117 MB | CPU
78
+ | DeepLabXception | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 7.466 ms | 0 - 51 MB | NPU
79
+ | DeepLabXception | ONNX | w8a8 | Qualcomm® QCS9075 | 7.645 ms | 0 - 4 MB | NPU
80
+ | DeepLabXception | ONNX | w8a8 | Qualcomm® QCM6690 | 243.516 ms | 56 - 68 MB | CPU
81
+ | DeepLabXception | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 4.223 ms | 1 - 289 MB | NPU
82
+ | DeepLabXception | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 229.03 ms | 89 - 102 MB | CPU
83
+ | DeepLabXception | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 9.241 ms | 3 - 258 MB | NPU
84
+ | DeepLabXception | QNN_DLC | float | Snapdragon® X2 Elite | 11.169 ms | 3 - 3 MB | NPU
85
+ | DeepLabXception | QNN_DLC | float | Snapdragon® X Elite | 22.764 ms | 3 - 3 MB | NPU
86
+ | DeepLabXception | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 16.091 ms | 0 - 366 MB | NPU
87
+ | DeepLabXception | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 113.166 ms | 2 - 246 MB | NPU
88
+ | DeepLabXception | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 21.892 ms | 3 - 34 MB | NPU
89
+ | DeepLabXception | QNN_DLC | float | Qualcomm® SA8775P | 30.591 ms | 1 - 245 MB | NPU
90
+ | DeepLabXception | QNN_DLC | float | Qualcomm® QCS9075 | 35.246 ms | 3 - 8 MB | NPU
91
+ | DeepLabXception | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 45.546 ms | 0 - 361 MB | NPU
92
+ | DeepLabXception | QNN_DLC | float | Qualcomm® SA7255P | 113.166 ms | 2 - 246 MB | NPU
93
+ | DeepLabXception | QNN_DLC | float | Qualcomm® SA8295P | 38.898 ms | 0 - 242 MB | NPU
94
+ | DeepLabXception | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 12.212 ms | 0 - 252 MB | NPU
95
+ | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.263 ms | 1 - 274 MB | NPU
96
+ | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 3.879 ms | 1 - 1 MB | NPU
97
+ | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® X Elite | 8.535 ms | 1 - 1 MB | NPU
98
+ | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 5.519 ms | 1 - 374 MB | NPU
99
+ | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 33.447 ms | 1 - 3 MB | NPU
100
+ | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 20.344 ms | 1 - 281 MB | NPU
101
+ | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 7.895 ms | 1 - 2 MB | NPU
102
+ | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® SA8775P | 8.092 ms | 1 - 284 MB | NPU
103
+ | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 8.594 ms | 1 - 3 MB | NPU
104
+ | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 94.111 ms | 1 - 303 MB | NPU
105
+ | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 14.188 ms | 1 - 367 MB | NPU
106
+ | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® SA7255P | 20.344 ms | 1 - 281 MB | NPU
107
+ | DeepLabXception | QNN_DLC | w8a8 | Qualcomm® SA8295P | 12.687 ms | 1 - 276 MB | NPU
108
+ | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 4.37 ms | 1 - 274 MB | NPU
109
+ | DeepLabXception | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 12.319 ms | 1 - 276 MB | NPU
110
+ | DeepLabXception | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 9.227 ms | 0 - 369 MB | NPU
111
+ | DeepLabXception | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 16.191 ms | 0 - 481 MB | NPU
112
+ | DeepLabXception | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 113.23 ms | 0 - 358 MB | NPU
113
+ | DeepLabXception | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 21.853 ms | 0 - 3 MB | NPU
114
+ | DeepLabXception | TFLITE | float | Qualcomm® SA8775P | 30.588 ms | 0 - 357 MB | NPU
115
+ | DeepLabXception | TFLITE | float | Qualcomm® QCS9075 | 35.057 ms | 0 - 93 MB | NPU
116
+ | DeepLabXception | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 46.669 ms | 0 - 472 MB | NPU
117
+ | DeepLabXception | TFLITE | float | Qualcomm® SA7255P | 113.23 ms | 0 - 358 MB | NPU
118
+ | DeepLabXception | TFLITE | float | Qualcomm® SA8295P | 38.655 ms | 0 - 349 MB | NPU
119
+ | DeepLabXception | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 12.221 ms | 0 - 365 MB | NPU
120
+ | DeepLabXception | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 2.897 ms | 0 - 268 MB | NPU
121
+ | DeepLabXception | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 4.94 ms | 0 - 373 MB | NPU
122
+ | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS6490 | 32.019 ms | 0 - 58 MB | NPU
123
+ | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 18.892 ms | 0 - 284 MB | NPU
124
+ | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 7.1 ms | 0 - 3 MB | NPU
125
+ | DeepLabXception | TFLITE | w8a8 | Qualcomm® SA8775P | 7.245 ms | 0 - 284 MB | NPU
126
+ | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS9075 | 7.45 ms | 0 - 47 MB | NPU
127
+ | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCM6690 | 91.711 ms | 0 - 295 MB | NPU
128
+ | DeepLabXception | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 11.838 ms | 0 - 360 MB | NPU
129
+ | DeepLabXception | TFLITE | w8a8 | Qualcomm® SA7255P | 18.892 ms | 0 - 284 MB | NPU
130
+ | DeepLabXception | TFLITE | w8a8 | Qualcomm® SA8295P | 11.553 ms | 0 - 273 MB | NPU
131
+ | DeepLabXception | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 3.928 ms | 0 - 274 MB | NPU
132
+ | DeepLabXception | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 11.522 ms | 0 - 268 MB | NPU
133
 
134
  ## License
135
  * The license for the original implementation of DeepLabXception can be found