Hugging Face's logo

qualcomm
/
U2Net-Segmentation

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
c32fd17
·
verified ·
1 Parent(s): 6bd63e2

v0.65.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.65.0 for changelog.

Files changed (3) hide show
  1. LICENSE +1 -0
  2. README.md +173 -0
  3. release_assets.json +53 -0
LICENSE ADDED
@@ -0,0 +1 @@
 
 
1
+ The license of the original trained model can be found at https://github.com/xuebinqin/U-2-Net/blob/master/LICENSE.
README.md ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: pytorch
3
+ license: apache-2.0
4
+ tags:
5
+ - real_time
6
+ - android
7
+ pipeline_tag: image-segmentation
8
+
9
+ ---
10
+
11
+ ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/web-assets/model_demo.png)
12
+
13
+ # U2Net-Segmentation: Optimized for Qualcomm Devices
14
+
15
+ U2-Net is a machine learning model for salient object detection and foreground extraction. It uses a two-level nested U-structure (RSU blocks) to capture both local and global context at multiple scales, producing high-quality binary foreground masks. The model is trained on the DUTS dataset and is well-suited for background removal, portrait segmentation, and object extraction on mobile and edge devices.
16
+
17
+ This is based on the implementation of U2Net-Segmentation found [here](https://github.com/xuebinqin/U-2-Net).
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/v0.65.0/src/qai_hub_models/models/u2net_segmentation) 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
+
22
+ ## Getting Started
23
+ There are two ways to deploy this model on your device:
24
+
25
+ ### Option 1: Download Pre-Exported Models
26
+
27
+ Below are pre-exported model assets ready for deployment.
28
+
29
+ | Runtime | Precision | Chipset | SDK Versions | Download |
30
+ |---|---|---|---|---|
31
+ | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-onnx-float.zip)
32
+ | ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-qnn_dlc-w8a8.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-tflite-float.zip)
36
+ | TFLITE | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-tflite-w8a8.zip)
37
+
38
+ For more device-specific assets and performance metrics, visit **[U2Net-Segmentation on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/u2net_segmentation)**.
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/v0.65.0/src/qai_hub_models/models/u2net_segmentation) 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 [U2Net-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.65.0/src/qai_hub_models/models/u2net_segmentation) for usage instructions.
51
+
52
+ ## Model Details
53
+
54
+ **Model Type:** Model_use_case.semantic_segmentation
55
+
56
+ **Model Stats:**
57
+ - Input resolution: 320x320
58
+ - Model checkpoint: u2net.pth
59
+ - Number of output classes: 1 (salient foreground mask)
60
+ - Number of parameters: 44.0M
61
+
62
+ ## Performance Summary
63
+ | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
+ |---|---|---|---|---|---|---
65
+ | U2Net-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.344 ms | 0 - 193 MB | NPU
66
+ | U2Net-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 9.486 ms | 2 - 193 MB | NPU
67
+ | U2Net-Segmentation | ONNX | float | Snapdragon® X2 Elite | 8.186 ms | 1 - 1 MB | NPU
68
+ | U2Net-Segmentation | ONNX | float | Snapdragon® X Elite | 17.587 ms | 86 - 86 MB | NPU
69
+ | U2Net-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 28.489 ms | 0 - 247 MB | NPU
70
+ | U2Net-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 30.342 ms | 1 - 6 MB | NPU
71
+ | U2Net-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 17.31 ms | 0 - 432 MB | NPU
72
+ | U2Net-Segmentation | ONNX | float | Qualcomm® QCS8450 | 28.489 ms | 0 - 247 MB | NPU
73
+ | U2Net-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 28.636 ms | 1 - 6 MB | NPU
74
+ | U2Net-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 17.587 ms | 86 - 86 MB | NPU
75
+ | U2Net-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 9.486 ms | 2 - 193 MB | NPU
76
+ | U2Net-Segmentation | ONNX | float | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 6.329 ms | 2 - 192 MB | NPU
77
+ | U2Net-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 6 Mobile | 7.987 ms | 2 - 194 MB | NPU
78
+ | U2Net-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.013 ms | 0 - 204 MB | NPU
79
+ | U2Net-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 3.664 ms | 0 - 197 MB | NPU
80
+ | U2Net-Segmentation | ONNX | w8a8 | Snapdragon® X2 Elite | 3.038 ms | 1 - 1 MB | NPU
81
+ | U2Net-Segmentation | ONNX | w8a8 | Snapdragon® X Elite | 6.735 ms | 44 - 44 MB | NPU
82
+ | U2Net-Segmentation | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 8.142 ms | 0 - 287 MB | NPU
83
+ | U2Net-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 28.686 ms | 0 - 4 MB | NPU
84
+ | U2Net-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 6.745 ms | 0 - 5 MB | NPU
85
+ | U2Net-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.6 ms | 0 - 50 MB | NPU
86
+ | U2Net-Segmentation | ONNX | w8a8 | Qualcomm® QCS8450 | 8.142 ms | 0 - 287 MB | NPU
87
+ | U2Net-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 6.633 ms | 0 - 4 MB | NPU
88
+ | U2Net-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 6.735 ms | 44 - 44 MB | NPU
89
+ | U2Net-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 103.558 ms | 1 - 239 MB | NPU
90
+ | U2Net-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 10.048 ms | 0 - 235 MB | NPU
91
+ | U2Net-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 3.664 ms | 0 - 197 MB | NPU
92
+ | U2Net-Segmentation | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 10.048 ms | 0 - 235 MB | NPU
93
+ | U2Net-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 2.542 ms | 0 - 201 MB | NPU
94
+ | U2Net-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Gen 6 Mobile | 3.007 ms | 0 - 233 MB | NPU
95
+ | U2Net-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 8.339 ms | 1 - 184 MB | NPU
96
+ | U2Net-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 10.844 ms | 1 - 182 MB | NPU
97
+ | U2Net-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 9.668 ms | 1 - 1 MB | NPU
98
+ | U2Net-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 20.574 ms | 1 - 1 MB | NPU
99
+ | U2Net-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 30.94 ms | 1 - 235 MB | NPU
100
+ | U2Net-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 31.916 ms | 1 - 6 MB | NPU
101
+ | U2Net-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.855 ms | 1 - 3 MB | NPU
102
+ | U2Net-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 30.94 ms | 1 - 235 MB | NPU
103
+ | U2Net-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 30.684 ms | 1 - 5 MB | NPU
104
+ | U2Net-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 20.574 ms | 1 - 1 MB | NPU
105
+ | U2Net-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 10.844 ms | 1 - 182 MB | NPU
106
+ | U2Net-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 32.736 ms | 1 - 180 MB | NPU
107
+ | U2Net-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 7.08 ms | 1 - 182 MB | NPU
108
+ | U2Net-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 6 Mobile | 8.969 ms | 1 - 185 MB | NPU
109
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.091 ms | 0 - 187 MB | NPU
110
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 3.908 ms | 0 - 184 MB | NPU
111
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 3.501 ms | 0 - 0 MB | NPU
112
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Snapdragon® X Elite | 7.473 ms | 0 - 0 MB | NPU
113
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 8.777 ms | 0 - 267 MB | NPU
114
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 30.537 ms | 0 - 3 MB | NPU
115
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 7.138 ms | 0 - 3 MB | NPU
116
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.035 ms | 0 - 2 MB | NPU
117
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 8.777 ms | 0 - 267 MB | NPU
118
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 7.179 ms | 2 - 5 MB | NPU
119
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 7.473 ms | 0 - 0 MB | NPU
120
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 106.917 ms | 0 - 224 MB | NPU
121
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 10.524 ms | 0 - 222 MB | NPU
122
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 3.908 ms | 0 - 184 MB | NPU
123
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA7255P | 18.541 ms | 0 - 181 MB | NPU
124
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8295P | 10.962 ms | 0 - 186 MB | NPU
125
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 10.524 ms | 0 - 222 MB | NPU
126
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 2.587 ms | 0 - 187 MB | NPU
127
+ | U2Net-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 6 Mobile | 3.221 ms | 0 - 219 MB | NPU
128
+ | U2Net-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 8.34 ms | 0 - 186 MB | NPU
129
+ | U2Net-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 10.846 ms | 0 - 187 MB | NPU
130
+ | U2Net-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 30.775 ms | 1 - 311 MB | NPU
131
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 31.843 ms | 0 - 91 MB | NPU
132
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 20.097 ms | 0 - 3 MB | NPU
133
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® SA8775P | 30.386 ms | 1 - 183 MB | NPU
134
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® SA8650P | 30.386 ms | 1 - 183 MB | NPU
135
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® SA8255P | 30.386 ms | 1 - 183 MB | NPU
136
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 30.775 ms | 1 - 311 MB | NPU
137
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 30.238 ms | 0 - 90 MB | NPU
138
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 10.846 ms | 0 - 187 MB | NPU
139
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® SA7255P | 105.055 ms | 1 - 181 MB | NPU
140
+ | U2Net-Segmentation | TFLITE | float | Qualcomm® SA8295P | 32.742 ms | 1 - 187 MB | NPU
141
+ | U2Net-Segmentation | TFLITE | float | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 7.072 ms | 0 - 189 MB | NPU
142
+ | U2Net-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 6 Mobile | 8.978 ms | 0 - 188 MB | NPU
143
+ | U2Net-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.766 ms | 0 - 188 MB | NPU
144
+ | U2Net-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 3.485 ms | 0 - 183 MB | NPU
145
+ | U2Net-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 8.131 ms | 0 - 268 MB | NPU
146
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 33.338 ms | 1 - 56 MB | NPU
147
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 6.531 ms | 0 - 47 MB | NPU
148
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.247 ms | 0 - 3 MB | NPU
149
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® SA8775P | 6.674 ms | 0 - 182 MB | NPU
150
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® SA8650P | 6.674 ms | 0 - 182 MB | NPU
151
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® SA8255P | 6.674 ms | 0 - 182 MB | NPU
152
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8450 | 8.131 ms | 0 - 268 MB | NPU
153
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 6.49 ms | 0 - 46 MB | NPU
154
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 102.05 ms | 1 - 223 MB | NPU
155
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 11.541 ms | 1 - 219 MB | NPU
156
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 3.485 ms | 0 - 183 MB | NPU
157
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® SA7255P | 17.147 ms | 0 - 180 MB | NPU
158
+ | U2Net-Segmentation | TFLITE | w8a8 | Qualcomm® SA8295P | 10.18 ms | 0 - 185 MB | NPU
159
+ | U2Net-Segmentation | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 11.541 ms | 1 - 219 MB | NPU
160
+ | U2Net-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Extreme Gen 6 Mobile | 2.325 ms | 0 - 187 MB | NPU
161
+ | U2Net-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 6 Mobile | 2.859 ms | 0 - 219 MB | NPU
162
+
163
+ ## License
164
+ * The license for the original implementation of U2Net-Segmentation can be found
165
+ [here](https://github.com/xuebinqin/U-2-Net/blob/master/LICENSE).
166
+
167
+ ## References
168
+ * [U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://arxiv.org/abs/2005.09007)
169
+ * [Source Model Implementation](https://github.com/xuebinqin/U-2-Net)
170
+
171
+ ## Community
172
+ * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
173
+ * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
release_assets.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.65.0",
3
+ "precisions": {
4
+ "float": {
5
+ "universal_assets": {
6
+ "onnx": {
7
+ "tool_versions": {
8
+ "qairt": "2.50.0.260828221209",
9
+ "onnx_runtime": "1.30.0"
10
+ },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-onnx-float.zip"
12
+ },
13
+ "qnn_dlc": {
14
+ "tool_versions": {
15
+ "qairt": "2.50.0.260828221209"
16
+ },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-qnn_dlc-float.zip"
18
+ },
19
+ "tflite": {
20
+ "tool_versions": {
21
+ "qairt": "2.50.0.260828221209",
22
+ "litert": "1.4.2"
23
+ },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-tflite-float.zip"
25
+ }
26
+ }
27
+ },
28
+ "w8a8": {
29
+ "universal_assets": {
30
+ "onnx": {
31
+ "tool_versions": {
32
+ "qairt": "2.50.0.260828221209",
33
+ "onnx_runtime": "1.30.0"
34
+ },
35
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-onnx-w8a8.zip"
36
+ },
37
+ "qnn_dlc": {
38
+ "tool_versions": {
39
+ "qairt": "2.50.0.260828221209"
40
+ },
41
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-qnn_dlc-w8a8.zip"
42
+ },
43
+ "tflite": {
44
+ "tool_versions": {
45
+ "qairt": "2.50.0.260828221209",
46
+ "litert": "1.4.2"
47
+ },
48
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/u2net_segmentation/releases/v0.65.0/u2net_segmentation-tflite-w8a8.zip"
49
+ }
50
+ }
51
+ }
52
+ }
53
+ }