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
8276a63
·
verified ·
1 Parent(s): 4fabbe2

v0.60.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.

Files changed (2) hide show
  1. README.md +114 -105
  2. release_assets.json +7 -7
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/qualcomm/ai-hub-models/blob/v0.59.0/src/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
 
@@ -30,135 +30,144 @@ Below are pre-exported model assets ready for deployment.
30
 
31
  | Runtime | Precision | Chipset | SDK Versions | Download |
32
  |---|---|---|---|---|
33
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-onnx-float.zip)
34
- | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-onnx-w8a8.zip)
35
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-qnn_dlc-float.zip)
36
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-qnn_dlc-w8a8.zip)
37
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-tflite-float.zip)
38
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/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/v0.59.0/src/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/v0.59.0/src/qai_hub_models/models/unet_segmentation) for usage instructions.
53
 
54
  ## Model Details
55
 
56
  **Model Type:** Model_use_case.semantic_segmentation
57
 
58
  **Model Stats:**
59
- - Model checkpoint: unet_carvana_scale1.0_epoch2
60
  - Input resolution: 640x1280
61
- - Number of output classes: 2 (foreground / background)
62
- - Number of parameters: 31.0M
63
  - Model size (float): 118 MB
64
  - Model size (w8a8): 29.8 MB
 
 
65
 
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 | 74.926 ms | 17 - 17 MB | NPU
70
- | Unet-Segmentation | ONNX | float | Snapdragon® X Elite | 142.497 ms | 54 - 54 MB | NPU
71
- | Unet-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 114.579 ms | 23 - 546 MB | NPU
72
- | Unet-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 289.805 ms | 1 - 549 MB | NPU
73
- | Unet-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 159.65 ms | 0 - 57 MB | NPU
74
- | Unet-Segmentation | ONNX | float | Qualcomm® QCS8450 | 289.805 ms | 1 - 549 MB | NPU
75
- | Unet-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 249.85 ms | 9 - 21 MB | NPU
76
- | Unet-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 142.497 ms | 54 - 54 MB | NPU
77
- | Unet-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 91.522 ms | 15 - 334 MB | NPU
78
- | Unet-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 91.522 ms | 15 - 334 MB | NPU
79
- | Unet-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 66.985 ms | 14 - 343 MB | NPU
80
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® X2 Elite | 18.89 ms | 5 - 5 MB | NPU
81
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® X Elite | 37.719 ms | 29 - 29 MB | NPU
82
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 29.764 ms | 6 - 340 MB | NPU
83
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 68.38 ms | 6 - 342 MB | NPU
84
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 299.862 ms | 3 - 8 MB | NPU
85
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 38.042 ms | 0 - 32 MB | NPU
86
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCS8450 | 68.38 ms | 6 - 342 MB | NPU
87
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 35.708 ms | 4 - 7 MB | NPU
88
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 37.719 ms | 29 - 29 MB | NPU
89
- | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 24.393 ms | 3 - 189 MB | NPU
90
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 24.393 ms | 3 - 189 MB | NPU
91
- | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.406 ms | 3 - 192 MB | NPU
92
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 71.644 ms | 9 - 9 MB | NPU
93
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 132.325 ms | 9 - 9 MB | NPU
94
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 102.166 ms | 139 - 655 MB | NPU
95
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 283.41 ms | 5 - 540 MB | NPU
96
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 953.564 ms | 1 - 324 MB | NPU
97
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 138.073 ms | 9 - 13 MB | NPU
98
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 240.435 ms | 2 - 325 MB | NPU
99
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 240.435 ms | 2 - 325 MB | NPU
100
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 240.435 ms | 2 - 325 MB | NPU
101
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 283.41 ms | 5 - 540 MB | NPU
102
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 239.046 ms | 9 - 27 MB | NPU
103
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 132.325 ms | 9 - 9 MB | NPU
104
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 81.754 ms | 0 - 332 MB | NPU
105
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 953.564 ms | 1 - 324 MB | NPU
106
- | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 274.424 ms | 0 - 322 MB | NPU
107
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 81.754 ms | 0 - 332 MB | NPU
108
- | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 61.146 ms | 0 - 345 MB | NPU
109
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 18.842 ms | 2 - 2 MB | NPU
110
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® X Elite | 35.723 ms | 2 - 2 MB | NPU
111
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 26.201 ms | 2 - 320 MB | NPU
112
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 58.741 ms | 2 - 318 MB | NPU
113
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 287.899 ms | 4 - 9 MB | NPU
114
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8275 | 121.487 ms | 1 - 180 MB | NPU
115
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 34.563 ms | 3 - 31 MB | NPU
116
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8775P | 32.187 ms | 1 - 181 MB | NPU
117
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8650P | 32.187 ms | 1 - 181 MB | NPU
118
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8255P | 32.187 ms | 1 - 181 MB | NPU
119
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 58.741 ms | 2 - 318 MB | NPU
120
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 32.544 ms | 1 - 7 MB | NPU
121
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 35.723 ms | 2 - 2 MB | NPU
122
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1233.117 ms | 31 - 551 MB | NPU
123
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 79.054 ms | 2 - 267 MB | NPU
124
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 21.707 ms | 2 - 188 MB | NPU
125
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA7255P | 121.487 ms | 1 - 180 MB | NPU
126
- | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8295P | 63.726 ms | 0 - 180 MB | NPU
127
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 21.707 ms | 2 - 188 MB | NPU
128
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 15.858 ms | 2 - 200 MB | NPU
129
- | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 79.054 ms | 2 - 267 MB | NPU
130
- | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 104.617 ms | 6 - 576 MB | NPU
131
- | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 278.817 ms | 7 - 589 MB | NPU
132
- | Unet-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 953.52 ms | 0 - 324 MB | NPU
133
- | Unet-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 144.104 ms | 6 - 443 MB | NPU
134
- | Unet-Segmentation | TFLITE | float | Qualcomm® SA8775P | 240.471 ms | 7 - 330 MB | NPU
135
- | Unet-Segmentation | TFLITE | float | Qualcomm® SA8650P | 240.471 ms | 7 - 330 MB | NPU
136
- | Unet-Segmentation | TFLITE | float | Qualcomm® SA8255P | 240.471 ms | 7 - 330 MB | NPU
137
- | Unet-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 278.817 ms | 7 - 589 MB | NPU
138
- | Unet-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 239.448 ms | 6 - 86 MB | NPU
139
- | Unet-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 82.942 ms | 0 - 332 MB | NPU
140
- | Unet-Segmentation | TFLITE | float | Qualcomm® SA7255P | 953.52 ms | 0 - 324 MB | NPU
141
- | Unet-Segmentation | TFLITE | float | Qualcomm® SA8295P | 274.445 ms | 7 - 329 MB | NPU
142
- | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 82.942 ms | 0 - 332 MB | NPU
143
- | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 64.672 ms | 0 - 340 MB | NPU
144
- | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 26.23 ms | 1 - 316 MB | NPU
145
- | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 60.694 ms | 2 - 319 MB | NPU
146
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 288.767 ms | 1 - 41 MB | NPU
147
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8275 | 121.558 ms | 2 - 181 MB | NPU
148
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 33.929 ms | 2 - 624 MB | NPU
149
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8775P | 32.204 ms | 2 - 180 MB | NPU
150
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8650P | 32.204 ms | 2 - 180 MB | NPU
151
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8255P | 32.204 ms | 2 - 180 MB | NPU
152
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8450 | 60.694 ms | 2 - 319 MB | NPU
153
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 32.211 ms | 1 - 38 MB | NPU
154
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1213.903 ms | 0 - 519 MB | NPU
155
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 78.724 ms | 1 - 270 MB | NPU
156
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 21.596 ms | 2 - 189 MB | NPU
157
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA7255P | 121.558 ms | 2 - 181 MB | NPU
158
- | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8295P | 63.743 ms | 2 - 180 MB | NPU
159
- | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 21.596 ms | 2 - 189 MB | NPU
160
- | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.061 ms | 1 - 199 MB | NPU
161
- | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 78.724 ms | 1 - 270 MB | NPU
 
 
 
 
 
 
 
 
 
162
 
163
  ## License
164
  * 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/v0.60.0/src/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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-onnx-float.zip)
34
+ | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-onnx-w8a8.zip)
35
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-qnn_dlc-float.zip)
36
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-qnn_dlc-w8a8.zip)
37
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-tflite-float.zip)
38
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/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/v0.60.0/src/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/v0.60.0/src/qai_hub_models/models/unet_segmentation) for usage instructions.
53
 
54
  ## Model Details
55
 
56
  **Model Type:** Model_use_case.semantic_segmentation
57
 
58
  **Model Stats:**
 
59
  - Input resolution: 640x1280
60
+ - Model checkpoint: unet_carvana_scale1.0_epoch2
 
61
  - Model size (float): 118 MB
62
  - Model size (w8a8): 29.8 MB
63
+ - Number of output classes: 2 (foreground / background)
64
+ - Number of parameters: 31.0M
65
 
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 | 74.864 ms | 17 - 17 MB | NPU
70
+ | Unet-Segmentation | ONNX | float | Snapdragon® X Elite | 142.616 ms | 54 - 54 MB | NPU
71
+ | Unet-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 113.914 ms | 2 - 523 MB | NPU
72
+ | Unet-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 329.318 ms | 1 - 549 MB | NPU
73
+ | Unet-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 286.177 ms | 9 - 22 MB | NPU
74
+ | Unet-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 154.1 ms | 0 - 56 MB | NPU
75
+ | Unet-Segmentation | ONNX | float | Qualcomm® QCS8450 | 329.318 ms | 1 - 549 MB | NPU
76
+ | Unet-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 250.143 ms | 9 - 22 MB | NPU
77
+ | Unet-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 142.616 ms | 54 - 54 MB | NPU
78
+ | Unet-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 91.494 ms | 14 - 334 MB | NPU
79
+ | Unet-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 91.494 ms | 14 - 334 MB | NPU
80
+ | Unet-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 67.754 ms | 16 - 345 MB | NPU
81
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® X2 Elite | 18.817 ms | 4 - 4 MB | NPU
82
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® X Elite | 37.721 ms | 29 - 29 MB | NPU
83
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 30.3 ms | 6 - 339 MB | NPU
84
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 66.487 ms | 6 - 341 MB | NPU
85
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 299.506 ms | 3 - 8 MB | NPU
86
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 40.791 ms | 4 - 7 MB | NPU
87
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 38.194 ms | 0 - 32 MB | NPU
88
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® QCS8450 | 66.487 ms | 6 - 341 MB | NPU
89
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 35.942 ms | 4 - 7 MB | NPU
90
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 37.721 ms | 29 - 29 MB | NPU
91
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1180.481 ms | 0 - 539 MB | NPU
92
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 81.721 ms | 6 - 279 MB | NPU
93
+ | Unet-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 24.452 ms | 3 - 189 MB | NPU
94
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 24.452 ms | 3 - 189 MB | NPU
95
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.691 ms | 3 - 191 MB | NPU
96
+ | Unet-Segmentation | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 81.721 ms | 6 - 279 MB | NPU
97
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 71.892 ms | 9 - 9 MB | NPU
98
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 132.372 ms | 9 - 9 MB | NPU
99
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 101.671 ms | 9 - 523 MB | NPU
100
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 293.677 ms | 9 - 545 MB | NPU
101
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 273.715 ms | 9 - 27 MB | NPU
102
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 954.506 ms | 0 - 323 MB | NPU
103
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 139.982 ms | 9 - 798 MB | NPU
104
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 240.406 ms | 0 - 324 MB | NPU
105
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 240.406 ms | 0 - 324 MB | NPU
106
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 240.406 ms | 0 - 324 MB | NPU
107
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 293.677 ms | 9 - 545 MB | NPU
108
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 238.779 ms | 9 - 27 MB | NPU
109
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 132.372 ms | 9 - 9 MB | NPU
110
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 82.938 ms | 9 - 340 MB | NPU
111
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 954.506 ms | 0 - 323 MB | NPU
112
+ | Unet-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 274.445 ms | 0 - 323 MB | NPU
113
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 82.938 ms | 9 - 340 MB | NPU
114
+ | Unet-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 62.092 ms | 9 - 356 MB | NPU
115
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 18.849 ms | 2 - 2 MB | NPU
116
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® X Elite | 35.788 ms | 2 - 2 MB | NPU
117
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 26.232 ms | 2 - 320 MB | NPU
118
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 59.234 ms | 2 - 318 MB | NPU
119
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 288.685 ms | 2 - 8 MB | NPU
120
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 37.375 ms | 2 - 9 MB | NPU
121
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 121.501 ms | 1 - 180 MB | NPU
122
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 34.674 ms | 2 - 4 MB | NPU
123
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8775P | 32.153 ms | 0 - 180 MB | NPU
124
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8650P | 32.153 ms | 0 - 180 MB | NPU
125
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8255P | 32.153 ms | 0 - 180 MB | NPU
126
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 59.234 ms | 2 - 318 MB | NPU
127
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 32.918 ms | 2 - 7 MB | NPU
128
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 35.788 ms | 2 - 2 MB | NPU
129
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1220.752 ms | 2 - 524 MB | NPU
130
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 79.02 ms | 2 - 267 MB | NPU
131
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 21.814 ms | 2 - 188 MB | NPU
132
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA7255P | 121.501 ms | 1 - 180 MB | NPU
133
+ | Unet-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8295P | 63.741 ms | 2 - 182 MB | NPU
134
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 21.814 ms | 2 - 188 MB | NPU
135
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.062 ms | 2 - 200 MB | NPU
136
+ | Unet-Segmentation | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 79.02 ms | 2 - 267 MB | NPU
137
+ | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 105.529 ms | 5 - 578 MB | NPU
138
+ | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 291.085 ms | 7 - 590 MB | NPU
139
+ | Unet-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 274.112 ms | 0 - 81 MB | NPU
140
+ | Unet-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 953.338 ms | 0 - 324 MB | NPU
141
+ | Unet-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 144.959 ms | 7 - 218 MB | NPU
142
+ | Unet-Segmentation | TFLITE | float | Qualcomm® SA8775P | 240.498 ms | 11 - 335 MB | NPU
143
+ | Unet-Segmentation | TFLITE | float | Qualcomm® SA8650P | 240.498 ms | 11 - 335 MB | NPU
144
+ | Unet-Segmentation | TFLITE | float | Qualcomm® SA8255P | 240.498 ms | 11 - 335 MB | NPU
145
+ | Unet-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 291.085 ms | 7 - 590 MB | NPU
146
+ | Unet-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 239.338 ms | 0 - 80 MB | NPU
147
+ | Unet-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 82.576 ms | 5 - 337 MB | NPU
148
+ | Unet-Segmentation | TFLITE | float | Qualcomm® SA7255P | 953.338 ms | 0 - 324 MB | NPU
149
+ | Unet-Segmentation | TFLITE | float | Qualcomm® SA8295P | 274.491 ms | 7 - 329 MB | NPU
150
+ | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 82.576 ms | 5 - 337 MB | NPU
151
+ | Unet-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 62.625 ms | 6 - 353 MB | NPU
152
+ | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 26.029 ms | 1 - 318 MB | NPU
153
+ | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 60.008 ms | 2 - 318 MB | NPU
154
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 288.425 ms | 1 - 41 MB | NPU
155
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 37.164 ms | 2 - 39 MB | NPU
156
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 121.602 ms | 2 - 181 MB | NPU
157
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 33.858 ms | 2 - 4 MB | NPU
158
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8775P | 32.214 ms | 2 - 180 MB | NPU
159
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8650P | 32.214 ms | 2 - 180 MB | NPU
160
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8255P | 32.214 ms | 2 - 180 MB | NPU
161
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8450 | 60.008 ms | 2 - 318 MB | NPU
162
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 33.275 ms | 1 - 38 MB | NPU
163
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1249.429 ms | 0 - 522 MB | NPU
164
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 78.318 ms | 2 - 268 MB | NPU
165
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 21.934 ms | 1 - 187 MB | NPU
166
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA7255P | 121.602 ms | 2 - 181 MB | NPU
167
+ | Unet-Segmentation | TFLITE | w8a8 | Qualcomm® SA8295P | 63.753 ms | 2 - 180 MB | NPU
168
+ | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 21.934 ms | 1 - 187 MB | NPU
169
+ | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 16.07 ms | 1 - 196 MB | NPU
170
+ | Unet-Segmentation | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 78.318 ms | 2 - 268 MB | NPU
171
 
172
  ## License
173
  * The license for the original implementation of Unet-Segmentation can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.59.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-onnx-float.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/unet_segmentation/releases/v0.59.0/unet_segmentation-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,19 +31,19 @@
31
  "qairt": "2.45.0.260326154327",
32
  "onnx_runtime": "1.27.1"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-onnx-w8a8.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.45.0.260326154327"
39
  },
40
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-qnn_dlc-w8a8.zip"
41
  },
42
  "tflite": {
43
  "tool_versions": {
44
  "qairt": "2.45.0.260326154327"
45
  },
46
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.59.0/unet_segmentation-tflite-w8a8.zip"
47
  }
48
  }
49
  }
 
1
  {
2
+ "version": "0.60.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-onnx-float.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/unet_segmentation/releases/v0.60.0/unet_segmentation-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-tflite-float.zip"
24
  }
25
  }
26
  },
 
31
  "qairt": "2.45.0.260326154327",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-onnx-w8a8.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.45.0.260326154327"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-qnn_dlc-w8a8.zip"
41
  },
42
  "tflite": {
43
  "tool_versions": {
44
  "qairt": "2.45.0.260326154327"
45
  },
46
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/unet_segmentation/releases/v0.60.0/unet_segmentation-tflite-w8a8.zip"
47
  }
48
  }
49
  }