Hugging Face's logo

qualcomm
/
Unet-Segmentation

Image Segmentation
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
fce60c5
·
verified ·
1 Parent(s): bf0cdd9

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 +76 -74
README.md CHANGED
@@ -17,7 +17,7 @@ pipeline_tag: image-segmentation
17
  UNet is a machine learning model that produces a segmentation mask for an image. The most basic use case will label each pixel in the image as being in the foreground or the background. More advanced usage will assign a class label to each pixel. This version of the model was trained on the data from Kaggle's Carvana Image Masking Challenge (see https://www.kaggle.com/c/carvana-image-masking-challenge) and is used for vehicle segmentation.
18
 
19
  This is based on the implementation of Unet-Segmentation found [here](https://github.com/milesial/Pytorch-UNet).
20
- 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/unet_segmentation) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
21
 
22
  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.
23
 
@@ -30,26 +30,26 @@ Below are pre-exported model assets ready for deployment.
30
 
31
  | Runtime | Precision | Chipset | SDK Versions | Download |
32
  |---|---|---|---|---|
33
- | 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/unet_segmentation/releases/v0.47.0/unet_segmentation-onnx-float.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/unet_segmentation/releases/v0.47.0/unet_segmentation-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/unet_segmentation/releases/v0.47.0/unet_segmentation-qnn_dlc-float.zip)
36
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.47.0/unet_segmentation-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/unet_segmentation/releases/v0.47.0/unet_segmentation-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/unet_segmentation/releases/v0.47.0/unet_segmentation-tflite-w8a8.zip)
39
 
40
  For more device-specific assets and performance metrics, visit **[Unet-Segmentation on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/unet_segmentation)**.
41
 
42
 
43
  ### Option 2: Export with Custom Configurations
44
 
45
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/unet_segmentation) 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 [Unet-Segmentation on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/unet_segmentation) for usage instructions.
53
 
54
  ## Model Details
55
 
@@ -66,71 +66,73 @@ See our repository for [Unet-Segmentation on GitHub](https://github.com/quic/ai-
66
  ## Performance Summary
67
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
68
  |---|---|---|---|---|---|---
69
- | Unet-Segmentation | ONNX | float | Snapdragon® X Elite | 139.479 ms | 53 - 53 MB | NPU
70
- | Unet-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 110.033 ms | 2 - 538 MB | NPU
71
- | Unet-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 149.746 ms | 0 - 57 MB | NPU
72
- | Unet-Segmentation | ONNX | float | Qualcomm® QCS9075 | 254.819 ms | 9 - 21 MB | NPU
73
- | Unet-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 88.65 ms | 15 - 330 MB | NPU
74
- | Unet-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 70.141 ms | 24 - 344 MB | NPU
75
- | Unet-Segmentation | ONNX | float | Snapdragon® X2 Elite | 75.136 ms | 53 - 53 MB | NPU
76
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® X Elite | 39.056 ms | 29 - 29 MB | NPU
77
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 30.222 ms | 6 - 338 MB | NPU
78
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCS6490 | 4647.573 ms | 942 - 1000 MB | CPU
79
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 41.711 ms | 4 - 6 MB | NPU
80
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCS9075 | 35.615 ms | 4 - 7 MB | NPU
81
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCM6690 | 4142.982 ms | 836 - 842 MB | CPU
82
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 24.867 ms | 3 - 191 MB | NPU
83
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3886.757 ms | 834 - 842 MB | CPU
84
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.251 ms | 0 - 185 MB | NPU
85
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® X2 Elite | 20.144 ms | 29 - 29 MB | NPU
86
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 132.389 ms | 9 - 9 MB | NPU
87
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 101.504 ms | 9 - 547 MB | NPU
88
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 953.65 ms | 0 - 322 MB | NPU
89
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 135.421 ms | 10 - 13 MB | NPU
90
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 240.476 ms | 0 - 324 MB | NPU
91
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 248.263 ms | 9 - 27 MB | NPU
92
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 274.543 ms | 7 - 549 MB | NPU
93
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 953.65 ms | 0 - 322 MB | NPU
94
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 274.502 ms | 0 - 322 MB | NPU
95
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 82.334 ms | 0 - 331 MB | NPU
96
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 65.76 ms | 9 - 350 MB | NPU
97
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 71.586 ms | 9 - 9 MB | NPU
98
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® X Elite | 35.715 ms | 2 - 2 MB | NPU
99
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 26.079 ms | 2 - 321 MB | NPU
100
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 267.761 ms | 2 - 8 MB | NPU
101
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 35.233 ms | 2 - 35 MB | NPU
102
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8775P | 32.227 ms | 1 - 180 MB | NPU
103
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 34.981 ms | 2 - 8 MB | NPU
104
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 1232.21 ms | 3 - 522 MB | NPU
105
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 57.992 ms | 2 - 320 MB | NPU
106
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8295P | 63.705 ms | 0 - 180 MB | NPU
107
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 21.942 ms | 2 - 191 MB | NPU
108
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 78.791 ms | 2 - 268 MB | NPU
109
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 15.788 ms | 2 - 197 MB | NPU
110
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 18.916 ms | 2 - 2 MB | NPU
111
- | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 102.428 ms | 0 - 535 MB | NPU
112
- | Unet-Segmentation | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 953.609 ms | 0 - 325 MB | NPU
113
- | Unet-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 156.101 ms | 6 - 443 MB | NPU
114
- | Unet-Segmentation | TFLITE | float | Qualcomm® SA8775P | 240.55 ms | 6 - 331 MB | NPU
115
- | Unet-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 248.108 ms | 0 - 80 MB | NPU
116
- | Unet-Segmentation | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 277.793 ms | 7 - 552 MB | NPU
117
- | Unet-Segmentation | TFLITE | float | Qualcomm® SA7255P | 953.609 ms | 0 - 325 MB | NPU
118
- | Unet-Segmentation | TFLITE | float | Qualcomm® SA8295P | 274.559 ms | 6 - 329 MB | NPU
119
- | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 81.817 ms | 4 - 337 MB | NPU
120
- | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 67.608 ms | 5 - 351 MB | NPU
121
- | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 26.281 ms | 0 - 318 MB | NPU
122
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS6490 | 267.819 ms | 0 - 40 MB | NPU
123
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 121.596 ms | 2 - 181 MB | NPU
124
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 34.978 ms | 0 - 651 MB | NPU
125
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8775P | 32.263 ms | 2 - 181 MB | NPU
126
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS9075 | 34.225 ms | 1 - 38 MB | NPU
127
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCM6690 | 1238.794 ms | 0 - 519 MB | NPU
128
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 58.357 ms | 2 - 321 MB | NPU
129
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA7255P | 121.596 ms | 2 - 181 MB | NPU
130
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8295P | 63.788 ms | 2 - 180 MB | NPU
131
- | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 21.845 ms | 1 - 187 MB | NPU
132
- | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 78.641 ms | 2 - 266 MB | NPU
133
- | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 15.774 ms | 7 - 202 MB | NPU
 
 
134
 
135
  ## License
136
  * The license for the original implementation of Unet-Segmentation can be found
 
17
  UNet is a machine learning model that produces a segmentation mask for an image. The most basic use case will label each pixel in the image as being in the foreground or the background. More advanced usage will assign a class label to each pixel. This version of the model was trained on the data from Kaggle's Carvana Image Masking Challenge (see https://www.kaggle.com/c/carvana-image-masking-challenge) and is used for vehicle segmentation.
18
 
19
  This is based on the implementation of Unet-Segmentation found [here](https://github.com/milesial/Pytorch-UNet).
20
+ 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/unet_segmentation) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
21
 
22
  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.
23
 
 
30
 
31
  | Runtime | Precision | Chipset | SDK Versions | Download |
32
  |---|---|---|---|---|
33
+ | 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/unet_segmentation/releases/v0.48.0/unet_segmentation-onnx-float.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/unet_segmentation/releases/v0.48.0/unet_segmentation-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/unet_segmentation/releases/v0.48.0/unet_segmentation-qnn_dlc-float.zip)
36
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.48.0/unet_segmentation-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/unet_segmentation/releases/v0.48.0/unet_segmentation-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/unet_segmentation/releases/v0.48.0/unet_segmentation-tflite-w8a8.zip)
39
 
40
  For more device-specific assets and performance metrics, visit **[Unet-Segmentation on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/unet_segmentation)**.
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/unet_segmentation) 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 [Unet-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/unet_segmentation) 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
+ | Unet-Segmentation | ONNX | float | Snapdragon® X2 Elite | 75.129 ms | 53 - 53 MB | NPU
70
+ | Unet-Segmentation | ONNX | float | Snapdragon® X Elite | 139.574 ms | 53 - 53 MB | NPU
71
+ | Unet-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 109.506 ms | 25 - 562 MB | NPU
72
+ | Unet-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 144.021 ms | 0 - 58 MB | NPU
73
+ | Unet-Segmentation | ONNX | float | Qualcomm® QCS9075 | 254.662 ms | 9 - 21 MB | NPU
74
+ | Unet-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 89.057 ms | 14 - 330 MB | NPU
75
+ | Unet-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 66.983 ms | 4 - 327 MB | NPU
76
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® X2 Elite | 20.038 ms | 29 - 29 MB | NPU
77
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® X Elite | 39.087 ms | 29 - 29 MB | NPU
78
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 30.409 ms | 6 - 338 MB | NPU
79
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCS6490 | 4677.804 ms | 943 - 1000 MB | CPU
80
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 39.501 ms | 0 - 12 MB | NPU
81
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCS9075 | 35.587 ms | 4 - 7 MB | NPU
82
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCM6690 | 4143.656 ms | 835 - 842 MB | CPU
83
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 24.647 ms | 3 - 189 MB | NPU
84
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3886.063 ms | 833 - 840 MB | CPU
85
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.357 ms | 6 - 189 MB | NPU
86
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 72.06 ms | 9 - 9 MB | NPU
87
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 132.493 ms | 9 - 9 MB | NPU
88
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 101.922 ms | 9 - 542 MB | NPU
89
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 953.451 ms | 0 - 323 MB | NPU
90
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 137.283 ms | 10 - 12 MB | NPU
91
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 240.471 ms | 0 - 323 MB | NPU
92
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 248.401 ms | 9 - 27 MB | NPU
93
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 277.158 ms | 9 - 548 MB | NPU
94
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 953.451 ms | 0 - 323 MB | NPU
95
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 274.522 ms | 0 - 322 MB | NPU
96
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 82.983 ms | 0 - 332 MB | NPU
97
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 63.074 ms | 9 - 350 MB | NPU
98
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 18.867 ms | 2 - 2 MB | NPU
99
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® X Elite | 35.686 ms | 2 - 2 MB | NPU
100
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 26.305 ms | 2 - 321 MB | NPU
101
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 267.84 ms | 2 - 8 MB | NPU
102
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 121.511 ms | 1 - 180 MB | NPU
103
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 34.694 ms | 2 - 4 MB | NPU
104
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8775P | 32.223 ms | 1 - 180 MB | NPU
105
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 34.299 ms | 2 - 8 MB | NPU
106
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 1243.995 ms | 2 - 521 MB | NPU
107
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 60.657 ms | 3 - 321 MB | NPU
108
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA7255P | 121.511 ms | 1 - 180 MB | NPU
109
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8295P | 63.73 ms | 0 - 180 MB | NPU
110
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 21.615 ms | 2 - 190 MB | NPU
111
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 78.746 ms | 2 - 268 MB | NPU
112
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 15.738 ms | 2 - 198 MB | NPU
113
+ | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 103.433 ms | 6 - 543 MB | NPU
114
+ | Unet-Segmentation | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 953.42 ms | 0 - 325 MB | NPU
115
+ | Unet-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 136.873 ms | 6 - 308 MB | NPU
116
+ | Unet-Segmentation | TFLITE | float | Qualcomm® SA8775P | 1126.415 ms | 5 - 330 MB | NPU
117
+ | Unet-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 248.066 ms | 0 - 80 MB | NPU
118
+ | Unet-Segmentation | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 278.634 ms | 7 - 551 MB | NPU
119
+ | Unet-Segmentation | TFLITE | float | Qualcomm® SA7255P | 953.42 ms | 0 - 325 MB | NPU
120
+ | Unet-Segmentation | TFLITE | float | Qualcomm® SA8295P | 274.503 ms | 0 - 322 MB | NPU
121
+ | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 82.529 ms | 0 - 331 MB | NPU
122
+ | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 62.584 ms | 6 - 353 MB | NPU
123
+ | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 26.332 ms | 14 - 333 MB | NPU
124
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS6490 | 267.765 ms | 0 - 40 MB | NPU
125
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 121.634 ms | 2 - 181 MB | NPU
126
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 32.145 ms | 2 - 623 MB | NPU
127
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8775P | 32.24 ms | 2 - 181 MB | NPU
128
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS9075 | 34.234 ms | 0 - 37 MB | NPU
129
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCM6690 | 1238.061 ms | 0 - 519 MB | NPU
130
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 60.326 ms | 2 - 320 MB | NPU
131
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA7255P | 121.634 ms | 2 - 181 MB | NPU
132
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8295P | 63.769 ms | 2 - 180 MB | NPU
133
+ | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 21.825 ms | 1 - 187 MB | NPU
134
+ | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 78.773 ms | 1 - 269 MB | NPU
135
+ | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 15.695 ms | 7 - 202 MB | NPU
136
 
137
  ## License
138
  * The license for the original implementation of Unet-Segmentation can be found