Hugging Face's logo

qualcomm
/
MobileNet-v4

Image Classification
PyTorch
backbone
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
b87ecba
·
verified ·
1 Parent(s): 98a4d3d

v0.64.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.64.0 for changelog.

Files changed (3) hide show
  1. LICENSE +1 -0
  2. README.md +175 -0
  3. release_assets.json +51 -0
LICENSE ADDED
@@ -0,0 +1 @@
 
 
1
+ The license of the original trained model can be found at https://github.com/jaiwei98/MobileNetV4-pytorch/blob/main/LICENSE.
README.md ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: pytorch
3
+ license: mit
4
+ tags:
5
+ - backbone
6
+ - real_time
7
+ - android
8
+ pipeline_tag: image-classification
9
+
10
+ ---
11
+
12
+ ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v4/web-assets/model_demo.png)
13
+
14
+ # MobileNet-v4: Optimized for Qualcomm Devices
15
+
16
+ MobileNetV4 is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
17
+
18
+ This is based on the implementation of MobileNet-v4 found [here](https://github.com/jaiwei98/MobileNetV4-pytorch).
19
+ 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/v0.64.0/src/qai_hub_models/models/mobilenet_v4) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
+
21
+ 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.
22
+
23
+ ## Getting Started
24
+ There are two ways to deploy this model on your device:
25
+
26
+ ### Option 1: Download Pre-Exported Models
27
+
28
+ Below are pre-exported model assets ready for deployment.
29
+
30
+ | Runtime | Precision | Chipset | SDK Versions | Download |
31
+ |---|---|---|---|---|
32
+ | 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/mobilenet_v4/releases/v0.64.0/mobilenet_v4-onnx-float.zip)
33
+ | 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/mobilenet_v4/releases/v0.64.0/mobilenet_v4-onnx-w8a8.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v4/releases/v0.64.0/mobilenet_v4-qnn_dlc-float.zip)
35
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v4/releases/v0.64.0/mobilenet_v4-qnn_dlc-w8a8.zip)
36
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v4/releases/v0.64.0/mobilenet_v4-tflite-float.zip)
37
+ | TFLITE | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v4/releases/v0.64.0/mobilenet_v4-tflite-w8a8.zip)
38
+
39
+ For more device-specific assets and performance metrics, visit **[MobileNet-v4 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobilenet_v4)**.
40
+
41
+
42
+ ### Option 2: Export with Custom Configurations
43
+
44
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/mobilenet_v4) Python library to compile and export the model with your own:
45
+ - Custom weights (e.g., fine-tuned checkpoints)
46
+ - Custom input shapes
47
+ - Target device and runtime configurations
48
+
49
+ This option is ideal if you need to customize the model beyond the default configuration provided here.
50
+
51
+ See our repository for [MobileNet-v4 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/mobilenet_v4) for usage instructions.
52
+
53
+ ## Model Details
54
+
55
+ **Model Type:** Model_use_case.image_classification
56
+
57
+ **Model Stats:**
58
+ - Input resolution: 224x224
59
+ - Model checkpoint: Imagenet
60
+ - Model size (float): 37.0 MB
61
+ - Model size (w8a8): 10.2 MB
62
+ - Number of parameters: 9.68M
63
+
64
+ ## Performance Summary
65
+ | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
+ |---|---|---|---|---|---|---
67
+ | MobileNet-v4 | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.444 ms | 0 - 43 MB | NPU
68
+ | MobileNet-v4 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.503 ms | 0 - 39 MB | NPU
69
+ | MobileNet-v4 | ONNX | float | Snapdragon® X2 Elite | 0.379 ms | 2 - 2 MB | NPU
70
+ | MobileNet-v4 | ONNX | float | Snapdragon® X Elite | 0.823 ms | 22 - 22 MB | NPU
71
+ | MobileNet-v4 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.613 ms | 0 - 74 MB | NPU
72
+ | MobileNet-v4 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.436 ms | 0 - 77 MB | NPU
73
+ | MobileNet-v4 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.27 ms | 1 - 5 MB | NPU
74
+ | MobileNet-v4 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.865 ms | 0 - 37 MB | NPU
75
+ | MobileNet-v4 | ONNX | float | Qualcomm® QCS8450 | 1.436 ms | 0 - 77 MB | NPU
76
+ | MobileNet-v4 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.201 ms | 1 - 4 MB | NPU
77
+ | MobileNet-v4 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.823 ms | 22 - 22 MB | NPU
78
+ | MobileNet-v4 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.503 ms | 0 - 39 MB | NPU
79
+ | MobileNet-v4 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.337 ms | 0 - 53 MB | NPU
80
+ | MobileNet-v4 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.367 ms | 0 - 53 MB | NPU
81
+ | MobileNet-v4 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.302 ms | 1 - 1 MB | NPU
82
+ | MobileNet-v4 | ONNX | w8a8 | Snapdragon® X Elite | 0.548 ms | 10 - 10 MB | NPU
83
+ | MobileNet-v4 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.426 ms | 0 - 84 MB | NPU
84
+ | MobileNet-v4 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.778 ms | 0 - 89 MB | NPU
85
+ | MobileNet-v4 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.733 ms | 0 - 3 MB | NPU
86
+ | MobileNet-v4 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.685 ms | 0 - 4 MB | NPU
87
+ | MobileNet-v4 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.578 ms | 0 - 76 MB | NPU
88
+ | MobileNet-v4 | ONNX | w8a8 | Qualcomm® QCS8450 | 0.778 ms | 0 - 89 MB | NPU
89
+ | MobileNet-v4 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.691 ms | 0 - 3 MB | NPU
90
+ | MobileNet-v4 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.548 ms | 10 - 10 MB | NPU
91
+ | MobileNet-v4 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 2.585 ms | 0 - 54 MB | NPU
92
+ | MobileNet-v4 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.616 ms | 0 - 54 MB | NPU
93
+ | MobileNet-v4 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.367 ms | 0 - 53 MB | NPU
94
+ | MobileNet-v4 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.616 ms | 0 - 54 MB | NPU
95
+ | MobileNet-v4 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.526 ms | 1 - 40 MB | NPU
96
+ | MobileNet-v4 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.625 ms | 1 - 38 MB | NPU
97
+ | MobileNet-v4 | QNN_DLC | float | Snapdragon® X2 Elite | 0.582 ms | 1 - 1 MB | NPU
98
+ | MobileNet-v4 | QNN_DLC | float | Snapdragon® X Elite | 1.301 ms | 1 - 1 MB | NPU
99
+ | MobileNet-v4 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.82 ms | 0 - 68 MB | NPU
100
+ | MobileNet-v4 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.128 ms | 0 - 77 MB | NPU
101
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 1.486 ms | 1 - 4 MB | NPU
102
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.18 ms | 1 - 2 MB | NPU
103
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® SA8775P | 1.589 ms | 1 - 42 MB | NPU
104
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® SA8650P | 1.589 ms | 1 - 42 MB | NPU
105
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® SA8255P | 1.589 ms | 1 - 42 MB | NPU
106
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® QCS8450 | 2.128 ms | 0 - 77 MB | NPU
107
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.468 ms | 1 - 3 MB | NPU
108
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.301 ms | 1 - 1 MB | NPU
109
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.625 ms | 1 - 38 MB | NPU
110
+ | MobileNet-v4 | QNN_DLC | float | Qualcomm® SA8295P | 2.05 ms | 0 - 38 MB | NPU
111
+ | MobileNet-v4 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.276 ms | 0 - 49 MB | NPU
112
+ | MobileNet-v4 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.309 ms | 0 - 51 MB | NPU
113
+ | MobileNet-v4 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.347 ms | 0 - 0 MB | NPU
114
+ | MobileNet-v4 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.659 ms | 0 - 0 MB | NPU
115
+ | MobileNet-v4 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.419 ms | 0 - 72 MB | NPU
116
+ | MobileNet-v4 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.77 ms | 0 - 76 MB | NPU
117
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.097 ms | 2 - 4 MB | NPU
118
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.634 ms | 0 - 3 MB | NPU
119
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.563 ms | 0 - 2 MB | NPU
120
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.739 ms | 0 - 52 MB | NPU
121
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.739 ms | 0 - 52 MB | NPU
122
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.739 ms | 0 - 52 MB | NPU
123
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.77 ms | 0 - 76 MB | NPU
124
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.648 ms | 0 - 2 MB | NPU
125
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.659 ms | 0 - 0 MB | NPU
126
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 2.931 ms | 0 - 49 MB | NPU
127
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.698 ms | 0 - 50 MB | NPU
128
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.309 ms | 0 - 51 MB | NPU
129
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.305 ms | 0 - 48 MB | NPU
130
+ | MobileNet-v4 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.998 ms | 0 - 46 MB | NPU
131
+ | MobileNet-v4 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.698 ms | 0 - 50 MB | NPU
132
+ | MobileNet-v4 | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.517 ms | 0 - 52 MB | NPU
133
+ | MobileNet-v4 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.624 ms | 0 - 52 MB | NPU
134
+ | MobileNet-v4 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.802 ms | 0 - 85 MB | NPU
135
+ | MobileNet-v4 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.137 ms | 0 - 95 MB | NPU
136
+ | MobileNet-v4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.476 ms | 0 - 25 MB | NPU
137
+ | MobileNet-v4 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.14 ms | 0 - 2 MB | NPU
138
+ | MobileNet-v4 | TFLITE | float | Qualcomm® SA8775P | 1.597 ms | 0 - 55 MB | NPU
139
+ | MobileNet-v4 | TFLITE | float | Qualcomm® SA8650P | 1.597 ms | 0 - 55 MB | NPU
140
+ | MobileNet-v4 | TFLITE | float | Qualcomm® SA8255P | 1.597 ms | 0 - 55 MB | NPU
141
+ | MobileNet-v4 | TFLITE | float | Qualcomm® QCS8450 | 2.137 ms | 0 - 95 MB | NPU
142
+ | MobileNet-v4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.479 ms | 0 - 25 MB | NPU
143
+ | MobileNet-v4 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.624 ms | 0 - 52 MB | NPU
144
+ | MobileNet-v4 | TFLITE | float | Qualcomm® SA7255P | 4.314 ms | 0 - 52 MB | NPU
145
+ | MobileNet-v4 | TFLITE | float | Qualcomm® SA8295P | 2.067 ms | 0 - 51 MB | NPU
146
+ | MobileNet-v4 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.219 ms | 0 - 46 MB | NPU
147
+ | MobileNet-v4 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.241 ms | 0 - 44 MB | NPU
148
+ | MobileNet-v4 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.297 ms | 0 - 73 MB | NPU
149
+ | MobileNet-v4 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.578 ms | 0 - 81 MB | NPU
150
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.649 ms | 0 - 19 MB | NPU
151
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.485 ms | 0 - 14 MB | NPU
152
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.389 ms | 0 - 5 MB | NPU
153
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.576 ms | 0 - 50 MB | NPU
154
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® SA8650P | 0.576 ms | 0 - 50 MB | NPU
155
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® SA8255P | 0.576 ms | 0 - 50 MB | NPU
156
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.578 ms | 0 - 81 MB | NPU
157
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.489 ms | 0 - 13 MB | NPU
158
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 2.332 ms | 0 - 46 MB | NPU
159
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.529 ms | 0 - 46 MB | NPU
160
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.241 ms | 0 - 44 MB | NPU
161
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® SA7255P | 0.981 ms | 0 - 46 MB | NPU
162
+ | MobileNet-v4 | TFLITE | w8a8 | Qualcomm® SA8295P | 0.806 ms | 0 - 43 MB | NPU
163
+ | MobileNet-v4 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.529 ms | 0 - 46 MB | NPU
164
+
165
+ ## License
166
+ * The license for the original implementation of MobileNet-v4 can be found
167
+ [here](https://github.com/jaiwei98/MobileNetV4-pytorch/blob/main/LICENSE).
168
+
169
+ ## References
170
+ * [MobileNetV4 -- Universal Models for the Mobile Ecosystem](https://arxiv.org/abs/2404.10518)
171
+ * [Source Model Implementation](https://github.com/jaiwei98/MobileNetV4-pytorch)
172
+
173
+ ## Community
174
+ * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
175
+ * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
release_assets.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.64.0",
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/mobilenet_v4/releases/v0.64.0/mobilenet_v4-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/mobilenet_v4/releases/v0.64.0/mobilenet_v4-qnn_dlc-float.zip"
18
+ },
19
+ "tflite": {
20
+ "tool_versions": {
21
+ "qairt": "2.50.0.260828221209"
22
+ },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v4/releases/v0.64.0/mobilenet_v4-tflite-float.zip"
24
+ }
25
+ }
26
+ },
27
+ "w8a8": {
28
+ "universal_assets": {
29
+ "onnx": {
30
+ "tool_versions": {
31
+ "qairt": "2.50.0.260828221209",
32
+ "onnx_runtime": "1.30.0"
33
+ },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v4/releases/v0.64.0/mobilenet_v4-onnx-w8a8.zip"
35
+ },
36
+ "qnn_dlc": {
37
+ "tool_versions": {
38
+ "qairt": "2.50.0.260828221209"
39
+ },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v4/releases/v0.64.0/mobilenet_v4-qnn_dlc-w8a8.zip"
41
+ },
42
+ "tflite": {
43
+ "tool_versions": {
44
+ "qairt": "2.50.0.260828221209"
45
+ },
46
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v4/releases/v0.64.0/mobilenet_v4-tflite-w8a8.zip"
47
+ }
48
+ }
49
+ }
50
+ }
51
+ }