Hugging Face's logo

qualcomm
/
GPUNet

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
d794ddc
·
verified ·
1 Parent(s): f0363bf

v0.59.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.59.0 for changelog.

Files changed (2) hide show
  1. README.md +134 -140
  2. release_assets.json +26 -28
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
16
  GPUNet 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 GPUNet found [here](https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Classification/GPUNet).
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/v0.58.0/src/qai_hub_models/models/gpunet) 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
 
@@ -29,28 +29,28 @@ Below are pre-exported model assets ready for deployment.
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-onnx-float.zip)
33
- | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-onnx-w8a16.zip)
34
- | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-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/gpunet/releases/v0.58.0/gpunet-qnn_dlc-float.zip)
36
- | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-qnn_dlc-w8a16.zip)
37
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-qnn_dlc-w8a8.zip)
38
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-tflite-float.zip)
39
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-tflite-w8a8.zip)
40
 
41
  For more device-specific assets and performance metrics, visit **[GPUNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/gpunet)**.
42
 
43
 
44
  ### Option 2: Export with Custom Configurations
45
 
46
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/gpunet) Python library to compile and export the model with your own:
47
  - Custom weights (e.g., fine-tuned checkpoints)
48
  - Custom input shapes
49
  - Target device and runtime configurations
50
 
51
  This option is ideal if you need to customize the model beyond the default configuration provided here.
52
 
53
- See our repository for [GPUNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/gpunet) for usage instructions.
54
 
55
  ## Model Details
56
 
@@ -66,138 +66,132 @@ See our repository for [GPUNet on GitHub](https://github.com/qualcomm/ai-hub-mod
66
  ## Performance Summary
67
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
68
  |---|---|---|---|---|---|---
69
- | GPUNet | ONNX | float | Snapdragon® X2 Elite | 0.472 ms | 2 - 2 MB | NPU
70
- | GPUNet | ONNX | float | Snapdragon® X Elite | 0.974 ms | 24 - 24 MB | NPU
71
- | GPUNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.764 ms | 1 - 61 MB | NPU
72
- | GPUNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.703 ms | 1 - 63 MB | NPU
73
- | GPUNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.004 ms | 0 - 29 MB | NPU
74
- | GPUNet | ONNX | float | Qualcomm® QCS8450 | 1.703 ms | 1 - 63 MB | NPU
75
- | GPUNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.519 ms | 0 - 33 MB | NPU
76
- | GPUNet | ONNX | float | Snapdragon® 8 Elite Mobile | 0.601 ms | 0 - 30 MB | NPU
77
- | GPUNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.386 ms | 1 - 3 MB | NPU
78
- | GPUNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.601 ms | 0 - 30 MB | NPU
79
- | GPUNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.974 ms | 24 - 24 MB | NPU
80
- | GPUNet | ONNX | w8a16 | Snapdragon® X2 Elite | 0.382 ms | 1 - 1 MB | NPU
81
- | GPUNet | ONNX | w8a16 | Snapdragon® X Elite | 0.84 ms | 13 - 13 MB | NPU
82
- | GPUNet | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.575 ms | 0 - 65 MB | NPU
83
- | GPUNet | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1.153 ms | 0 - 68 MB | NPU
84
- | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 3.368 ms | 0 - 3 MB | NPU
85
- | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.818 ms | 0 - 16 MB | NPU
86
- | GPUNet | ONNX | w8a16 | Qualcomm® QCS8450 | 1.153 ms | 0 - 68 MB | NPU
87
- | GPUNet | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.434 ms | 0 - 47 MB | NPU
88
- | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1.145 ms | 0 - 3 MB | NPU
89
- | GPUNet | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.059 ms | 0 - 47 MB | NPU
90
- | GPUNet | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.37 ms | 0 - 51 MB | NPU
91
- | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5.769 ms | 0 - 175 MB | NPU
92
- | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 1.059 ms | 0 - 47 MB | NPU
93
- | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.434 ms | 0 - 47 MB | NPU
94
- | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 0.84 ms | 13 - 13 MB | NPU
95
- | GPUNet | ONNX | w8a8 | Snapdragon® X2 Elite | 0.303 ms | 1 - 1 MB | NPU
96
- | GPUNet | ONNX | w8a8 | Snapdragon® X Elite | 0.602 ms | 12 - 12 MB | NPU
97
- | GPUNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.471 ms | 0 - 66 MB | NPU
98
- | GPUNet | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.876 ms | 0 - 66 MB | NPU
99
- | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.138 ms | 0 - 3 MB | NPU
100
- | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.613 ms | 0 - 14 MB | NPU
101
- | GPUNet | ONNX | w8a8 | Qualcomm® QCS8450 | 0.876 ms | 0 - 66 MB | NPU
102
- | GPUNet | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.392 ms | 0 - 46 MB | NPU
103
- | GPUNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.751 ms | 0 - 44 MB | NPU
104
  | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.74 ms | 0 - 3 MB | NPU
105
- | GPUNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.354 ms | 0 - 49 MB | NPU
106
- | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.293 ms | 0 - 48 MB | NPU
107
- | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.751 ms | 0 - 44 MB | NPU
108
- | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.392 ms | 0 - 46 MB | NPU
109
- | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.602 ms | 12 - 12 MB | NPU
110
- | GPUNet | QNN_DLC | float | Snapdragon® X2 Elite | 0.7 ms | 1 - 1 MB | NPU
111
- | GPUNet | QNN_DLC | float | Snapdragon® X Elite | 1.393 ms | 1 - 1 MB | NPU
112
- | GPUNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.91 ms | 0 - 61 MB | NPU
113
- | GPUNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.394 ms | 0 - 63 MB | NPU
114
- | GPUNet | QNN_DLC | float | Qualcomm® QCS8275 | 4.692 ms | 1 - 32 MB | NPU
115
- | GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.27 ms | 1 - 17 MB | NPU
116
- | GPUNet | QNN_DLC | float | Qualcomm® SA8775P | 1.697 ms | 1 - 33 MB | NPU
117
- | GPUNet | QNN_DLC | float | Qualcomm® SA8650P | 1.697 ms | 1 - 33 MB | NPU
118
- | GPUNet | QNN_DLC | float | Qualcomm® SA8255P | 1.697 ms | 1 - 33 MB | NPU
119
- | GPUNet | QNN_DLC | float | Qualcomm® QCS8450 | 2.394 ms | 0 - 63 MB | NPU
120
- | GPUNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.57 ms | 1 - 37 MB | NPU
121
- | GPUNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.713 ms | 0 - 33 MB | NPU
122
- | GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.593 ms | 3 - 5 MB | NPU
123
- | GPUNet | QNN_DLC | float | Qualcomm® SA7255P | 4.692 ms | 1 - 32 MB | NPU
124
- | GPUNet | QNN_DLC | float | Qualcomm® SA8295P | 2.282 ms | 0 - 31 MB | NPU
125
- | GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.713 ms | 0 - 33 MB | NPU
126
- | GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.393 ms | 1 - 1 MB | NPU
127
  | GPUNet | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.56 ms | 0 - 0 MB | NPU
128
- | GPUNet | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.219 ms | 0 - 0 MB | NPU
129
- | GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.76 ms | 0 - 60 MB | NPU
130
- | GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1.424 ms | 0 - 64 MB | NPU
131
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 4.112 ms | 2 - 4 MB | NPU
132
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 2.495 ms | 0 - 44 MB | NPU
133
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.068 ms | 0 - 2 MB | NPU
134
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8775P | 1.276 ms | 0 - 45 MB | NPU
135
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8650P | 1.276 ms | 0 - 45 MB | NPU
136
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8255P | 1.276 ms | 0 - 45 MB | NPU
137
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 1.424 ms | 0 - 64 MB | NPU
138
- | GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.528 ms | 0 - 43 MB | NPU
139
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1.148 ms | 0 - 2 MB | NPU
140
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA7255P | 2.495 ms | 0 - 44 MB | NPU
141
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.667 ms | 0 - 40 MB | NPU
142
- | GPUNet | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.286 ms | 0 - 44 MB | NPU
143
- | GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.441 ms | 0 - 43 MB | NPU
144
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 6.553 ms | 0 - 167 MB | NPU
145
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 1.286 ms | 0 - 44 MB | NPU
146
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.528 ms | 0 - 43 MB | NPU
147
- | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.219 ms | 0 - 0 MB | NPU
148
- | GPUNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.343 ms | 0 - 0 MB | NPU
149
- | GPUNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.718 ms | 0 - 0 MB | NPU
150
- | GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.447 ms | 0 - 57 MB | NPU
151
- | GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.853 ms | 0 - 62 MB | NPU
152
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.256 ms | 2 - 4 MB | NPU
153
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 1.406 ms | 0 - 40 MB | NPU
154
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.608 ms | 0 - 2 MB | NPU
155
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.803 ms | 0 - 42 MB | NPU
156
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.803 ms | 0 - 42 MB | NPU
157
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.803 ms | 0 - 42 MB | NPU
158
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.853 ms | 0 - 62 MB | NPU
159
- | GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.341 ms | 0 - 39 MB | NPU
160
- | GPUNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.789 ms | 0 - 41 MB | NPU
161
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.693 ms | 0 - 2 MB | NPU
162
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.406 ms | 0 - 40 MB | NPU
163
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.104 ms | 0 - 38 MB | NPU
164
- | GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.292 ms | 0 - 43 MB | NPU
165
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.558 ms | 0 - 44 MB | NPU
166
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.789 ms | 0 - 41 MB | NPU
167
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.341 ms | 0 - 39 MB | NPU
168
- | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.718 ms | 0 - 0 MB | NPU
169
- | GPUNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.898 ms | 0 - 73 MB | NPU
170
- | GPUNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.395 ms | 0 - 82 MB | NPU
171
- | GPUNet | TFLITE | float | Qualcomm® QCS8275 | 4.724 ms | 0 - 44 MB | NPU
172
- | GPUNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.271 ms | 0 - 2 MB | NPU
173
- | GPUNet | TFLITE | float | Qualcomm® SA8775P | 1.76 ms | 0 - 47 MB | NPU
174
- | GPUNet | TFLITE | float | Qualcomm® SA8650P | 1.76 ms | 0 - 47 MB | NPU
175
- | GPUNet | TFLITE | float | Qualcomm® SA8255P | 1.76 ms | 0 - 47 MB | NPU
176
- | GPUNet | TFLITE | float | Qualcomm® QCS8450 | 2.395 ms | 0 - 82 MB | NPU
177
- | GPUNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.563 ms | 0 - 47 MB | NPU
178
- | GPUNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.696 ms | 0 - 42 MB | NPU
179
- | GPUNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.882 ms | 0 - 27 MB | NPU
180
- | GPUNet | TFLITE | float | Qualcomm® SA7255P | 4.724 ms | 0 - 44 MB | NPU
181
- | GPUNet | TFLITE | float | Qualcomm® SA8295P | 2.264 ms | 0 - 43 MB | NPU
182
- | GPUNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.696 ms | 0 - 42 MB | NPU
183
  | GPUNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.343 ms | 0 - 55 MB | NPU
184
- | GPUNet | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.686 ms | 0 - 62 MB | NPU
185
- | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.846 ms | 0 - 15 MB | NPU
186
- | GPUNet | TFLITE | w8a8 | Qualcomm® QCS8275 | 1.113 ms | 0 - 40 MB | NPU
187
- | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.426 ms | 0 - 2 MB | NPU
188
- | GPUNet | TFLITE | w8a8 | Qualcomm® SA8775P | 0.639 ms | 0 - 43 MB | NPU
189
- | GPUNet | TFLITE | w8a8 | Qualcomm® SA8650P | 0.639 ms | 0 - 43 MB | NPU
190
- | GPUNet | TFLITE | w8a8 | Qualcomm® SA8255P | 0.639 ms | 0 - 43 MB | NPU
191
- | GPUNet | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.686 ms | 0 - 62 MB | NPU
192
- | GPUNet | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.268 ms | 0 - 39 MB | NPU
193
- | GPUNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.613 ms | 0 - 39 MB | NPU
194
- | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.521 ms | 0 - 14 MB | NPU
195
- | GPUNet | TFLITE | w8a8 | Qualcomm® SA7255P | 1.113 ms | 0 - 40 MB | NPU
196
- | GPUNet | TFLITE | w8a8 | Qualcomm® SA8295P | 0.897 ms | 0 - 37 MB | NPU
197
- | GPUNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.239 ms | 0 - 42 MB | NPU
198
- | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.017 ms | 0 - 40 MB | NPU
199
- | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.613 ms | 0 - 39 MB | NPU
200
- | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.268 ms | 0 - 39 MB | NPU
201
 
202
  ## License
203
  * The license for the original implementation of GPUNet can be found
 
16
  GPUNet 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 GPUNet found [here](https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Classification/GPUNet).
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/v0.59.0/src/qai_hub_models/models/gpunet) 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
 
 
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
+ | 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/gpunet/releases/v0.59.0/gpunet-onnx-float.zip)
33
+ | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.59.0/gpunet-onnx-w8a16.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/gpunet/releases/v0.59.0/gpunet-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/gpunet/releases/v0.59.0/gpunet-qnn_dlc-float.zip)
36
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.59.0/gpunet-qnn_dlc-w8a16.zip)
37
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.59.0/gpunet-qnn_dlc-w8a8.zip)
38
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.59.0/gpunet-tflite-float.zip)
39
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.59.0/gpunet-tflite-w8a8.zip)
40
 
41
  For more device-specific assets and performance metrics, visit **[GPUNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/gpunet)**.
42
 
43
 
44
  ### Option 2: Export with Custom Configurations
45
 
46
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/gpunet) Python library to compile and export the model with your own:
47
  - Custom weights (e.g., fine-tuned checkpoints)
48
  - Custom input shapes
49
  - Target device and runtime configurations
50
 
51
  This option is ideal if you need to customize the model beyond the default configuration provided here.
52
 
53
+ See our repository for [GPUNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/gpunet) for usage instructions.
54
 
55
  ## Model Details
56
 
 
66
  ## Performance Summary
67
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
68
  |---|---|---|---|---|---|---
69
+ | GPUNet | ONNX | float | Snapdragon® X2 Elite | 0.477 ms | 2 - 2 MB | NPU
70
+ | GPUNet | ONNX | float | Snapdragon® X Elite | 0.984 ms | 24 - 24 MB | NPU
71
+ | GPUNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.763 ms | 0 - 61 MB | NPU
72
+ | GPUNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.715 ms | 1 - 63 MB | NPU
73
+ | GPUNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.016 ms | 0 - 62 MB | NPU
74
+ | GPUNet | ONNX | float | Qualcomm® QCS8450 | 1.715 ms | 1 - 63 MB | NPU
75
+ | GPUNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.422 ms | 1 - 3 MB | NPU
76
+ | GPUNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.984 ms | 24 - 24 MB | NPU
77
+ | GPUNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.599 ms | 0 - 32 MB | NPU
78
+ | GPUNet | ONNX | float | Snapdragon® 8 Elite Mobile | 0.599 ms | 0 - 32 MB | NPU
79
+ | GPUNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.519 ms | 0 - 32 MB | NPU
80
+ | GPUNet | ONNX | w8a16 | Snapdragon® X2 Elite | 0.385 ms | 1 - 1 MB | NPU
81
+ | GPUNet | ONNX | w8a16 | Snapdragon® X Elite | 0.832 ms | 12 - 12 MB | NPU
82
+ | GPUNet | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.587 ms | 0 - 70 MB | NPU
83
+ | GPUNet | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1.115 ms | 0 - 69 MB | NPU
84
+ | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 3.4 ms | 0 - 3 MB | NPU
85
+ | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.815 ms | 0 - 16 MB | NPU
86
+ | GPUNet | ONNX | w8a16 | Qualcomm® QCS8450 | 1.115 ms | 0 - 69 MB | NPU
87
+ | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 0.934 ms | 0 - 3 MB | NPU
88
+ | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 0.832 ms | 12 - 12 MB | NPU
89
+ | GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.435 ms | 0 - 51 MB | NPU
90
+ | GPUNet | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.435 ms | 0 - 51 MB | NPU
91
+ | GPUNet | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.367 ms | 0 - 50 MB | NPU
92
+ | GPUNet | ONNX | w8a8 | Snapdragon® X2 Elite | 0.302 ms | 1 - 1 MB | NPU
93
+ | GPUNet | ONNX | w8a8 | Snapdragon® X Elite | 0.598 ms | 12 - 12 MB | NPU
94
+ | GPUNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.467 ms | 0 - 63 MB | NPU
95
+ | GPUNet | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.879 ms | 0 - 66 MB | NPU
96
+ | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.124 ms | 0 - 3 MB | NPU
97
+ | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.623 ms | 0 - 37 MB | NPU
98
+ | GPUNet | ONNX | w8a8 | Qualcomm® QCS8450 | 0.879 ms | 0 - 66 MB | NPU
 
 
 
 
 
99
  | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.74 ms | 0 - 3 MB | NPU
100
+ | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.598 ms | 12 - 12 MB | NPU
101
+ | GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.392 ms | 0 - 43 MB | NPU
102
+ | GPUNet | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.392 ms | 0 - 43 MB | NPU
103
+ | GPUNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.36 ms | 0 - 46 MB | NPU
104
+ | GPUNet | QNN_DLC | float | Snapdragon® X2 Elite | 0.657 ms | 1 - 1 MB | NPU
105
+ | GPUNet | QNN_DLC | float | Snapdragon® X Elite | 1.38 ms | 1 - 1 MB | NPU
106
+ | GPUNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.919 ms | 0 - 57 MB | NPU
107
+ | GPUNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.414 ms | 0 - 63 MB | NPU
108
+ | GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 4.691 ms | 1 - 32 MB | NPU
109
+ | GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.274 ms | 0 - 13 MB | NPU
110
+ | GPUNet | QNN_DLC | float | Qualcomm® SA8775P | 1.72 ms | 1 - 33 MB | NPU
111
+ | GPUNet | QNN_DLC | float | Qualcomm® SA8650P | 1.72 ms | 1 - 33 MB | NPU
112
+ | GPUNet | QNN_DLC | float | Qualcomm® SA8255P | 1.72 ms | 1 - 33 MB | NPU
113
+ | GPUNet | QNN_DLC | float | Qualcomm® QCS8450 | 2.414 ms | 0 - 63 MB | NPU
114
+ | GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.809 ms | 3 - 5 MB | NPU
115
+ | GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.38 ms | 1 - 1 MB | NPU
116
+ | GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.704 ms | 0 - 30 MB | NPU
117
+ | GPUNet | QNN_DLC | float | Qualcomm® SA7255P | 4.691 ms | 1 - 32 MB | NPU
118
+ | GPUNet | QNN_DLC | float | Qualcomm® SA8295P | 2.261 ms | 0 - 32 MB | NPU
119
+ | GPUNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.704 ms | 0 - 30 MB | NPU
120
+ | GPUNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.571 ms | 1 - 32 MB | NPU
 
121
  | GPUNet | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.56 ms | 0 - 0 MB | NPU
122
+ | GPUNet | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.228 ms | 0 - 0 MB | NPU
123
+ | GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.767 ms | 0 - 60 MB | NPU
124
+ | GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1.43 ms | 0 - 65 MB | NPU
125
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 4.069 ms | 0 - 2 MB | NPU
126
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 2.475 ms | 0 - 43 MB | NPU
127
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.068 ms | 0 - 73 MB | NPU
128
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8775P | 1.284 ms | 0 - 45 MB | NPU
129
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8650P | 1.284 ms | 0 - 45 MB | NPU
130
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8255P | 1.284 ms | 0 - 45 MB | NPU
131
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 1.43 ms | 0 - 65 MB | NPU
132
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1.153 ms | 0 - 2 MB | NPU
133
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.228 ms | 0 - 0 MB | NPU
134
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 6.608 ms | 0 - 165 MB | NPU
135
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 1.293 ms | 0 - 44 MB | NPU
136
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.525 ms | 0 - 42 MB | NPU
137
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA7255P | 2.475 ms | 0 - 43 MB | NPU
138
+ | GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.644 ms | 0 - 41 MB | NPU
139
+ | GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.525 ms | 0 - 42 MB | NPU
140
+ | GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.44 ms | 0 - 44 MB | NPU
141
+ | GPUNet | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.293 ms | 0 - 44 MB | NPU
142
+ | GPUNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.34 ms | 0 - 0 MB | NPU
143
+ | GPUNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.699 ms | 0 - 0 MB | NPU
144
+ | GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.461 ms | 0 - 57 MB | NPU
145
+ | GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.852 ms | 0 - 62 MB | NPU
146
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.234 ms | 0 - 2 MB | NPU
147
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8275 | 1.41 ms | 0 - 39 MB | NPU
148
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.614 ms | 0 - 69 MB | NPU
149
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.806 ms | 0 - 42 MB | NPU
150
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.806 ms | 0 - 42 MB | NPU
151
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.806 ms | 0 - 42 MB | NPU
152
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.852 ms | 0 - 62 MB | NPU
153
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.696 ms | 0 - 2 MB | NPU
154
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.699 ms | 0 - 0 MB | NPU
155
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.556 ms | 0 - 43 MB | NPU
156
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.788 ms | 0 - 40 MB | NPU
157
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.341 ms | 0 - 38 MB | NPU
158
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.41 ms | 0 - 39 MB | NPU
159
+ | GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.096 ms | 0 - 38 MB | NPU
160
+ | GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.341 ms | 0 - 38 MB | NPU
161
+ | GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.295 ms | 0 - 46 MB | NPU
162
+ | GPUNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.788 ms | 0 - 40 MB | NPU
163
+ | GPUNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.911 ms | 0 - 74 MB | NPU
164
+ | GPUNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.4 ms | 0 - 81 MB | NPU
165
+ | GPUNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 4.714 ms | 0 - 43 MB | NPU
166
+ | GPUNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.261 ms | 0 - 13 MB | NPU
167
+ | GPUNet | TFLITE | float | Qualcomm® SA8775P | 1.748 ms | 0 - 47 MB | NPU
168
+ | GPUNet | TFLITE | float | Qualcomm® SA8650P | 1.748 ms | 0 - 47 MB | NPU
169
+ | GPUNet | TFLITE | float | Qualcomm® SA8255P | 1.748 ms | 0 - 47 MB | NPU
170
+ | GPUNet | TFLITE | float | Qualcomm® QCS8450 | 2.4 ms | 0 - 81 MB | NPU
171
+ | GPUNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.613 ms | 0 - 27 MB | NPU
172
+ | GPUNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.699 ms | 0 - 43 MB | NPU
173
+ | GPUNet | TFLITE | float | Qualcomm® SA7255P | 4.714 ms | 0 - 43 MB | NPU
174
+ | GPUNet | TFLITE | float | Qualcomm® SA8295P | 2.267 ms | 0 - 44 MB | NPU
175
+ | GPUNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.699 ms | 0 - 43 MB | NPU
176
+ | GPUNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.566 ms | 0 - 47 MB | NPU
177
  | GPUNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.343 ms | 0 - 55 MB | NPU
178
+ | GPUNet | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.685 ms | 0 - 64 MB | NPU
179
+ | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.798 ms | 0 - 15 MB | NPU
180
+ | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8275 | 1.096 ms | 0 - 40 MB | NPU
181
+ | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.429 ms | 0 - 16 MB | NPU
182
+ | GPUNet | TFLITE | w8a8 | Qualcomm® SA8775P | 0.694 ms | 0 - 40 MB | NPU
183
+ | GPUNet | TFLITE | w8a8 | Qualcomm® SA8650P | 0.694 ms | 0 - 40 MB | NPU
184
+ | GPUNet | TFLITE | w8a8 | Qualcomm® SA8255P | 0.694 ms | 0 - 40 MB | NPU
185
+ | GPUNet | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.685 ms | 0 - 64 MB | NPU
186
+ | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.542 ms | 0 - 14 MB | NPU
187
+ | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.023 ms | 0 - 40 MB | NPU
188
+ | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.615 ms | 0 - 39 MB | NPU
189
+ | GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.265 ms | 0 - 39 MB | NPU
190
+ | GPUNet | TFLITE | w8a8 | Qualcomm® SA7255P | 1.096 ms | 0 - 40 MB | NPU
191
+ | GPUNet | TFLITE | w8a8 | Qualcomm® SA8295P | 0.907 ms | 0 - 37 MB | NPU
192
+ | GPUNet | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.265 ms | 0 - 39 MB | NPU
193
+ | GPUNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.24 ms | 0 - 41 MB | NPU
194
+ | GPUNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.615 ms | 0 - 39 MB | NPU
195
 
196
  ## License
197
  * The license for the original implementation of GPUNet can be found
release_assets.json CHANGED
@@ -1,68 +1,66 @@
1
  {
2
- "version": "0.58.0",
3
  "precisions": {
4
- "w8a16": {
5
  "universal_assets": {
 
 
 
 
 
 
 
6
  "qnn_dlc": {
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327"
9
  },
10
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-qnn_dlc-w8a16.zip"
11
  },
12
- "onnx": {
13
  "tool_versions": {
14
- "qairt": "2.45.0.260326154327",
15
- "onnx_runtime": "1.25.0"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-onnx-w8a16.zip"
18
  }
19
  }
20
  },
21
- "w8a8": {
22
  "universal_assets": {
23
- "tflite": {
24
  "tool_versions": {
25
  "qairt": "2.45.0.260326154327",
26
- "litert": "1.4.4"
27
  },
28
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-tflite-w8a8.zip"
29
  },
30
  "qnn_dlc": {
31
  "tool_versions": {
32
  "qairt": "2.45.0.260326154327"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-qnn_dlc-w8a8.zip"
35
- },
36
- "onnx": {
37
- "tool_versions": {
38
- "qairt": "2.45.0.260326154327",
39
- "onnx_runtime": "1.25.0"
40
- },
41
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-onnx-w8a8.zip"
42
  }
43
  }
44
  },
45
- "float": {
46
  "universal_assets": {
47
- "tflite": {
48
  "tool_versions": {
49
  "qairt": "2.45.0.260326154327",
50
- "litert": "1.4.4"
51
  },
52
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-tflite-float.zip"
53
  },
54
  "qnn_dlc": {
55
  "tool_versions": {
56
  "qairt": "2.45.0.260326154327"
57
  },
58
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-qnn_dlc-float.zip"
59
  },
60
- "onnx": {
61
  "tool_versions": {
62
- "qairt": "2.45.0.260326154327",
63
- "onnx_runtime": "1.25.0"
64
  },
65
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.58.0/gpunet-onnx-float.zip"
66
  }
67
  }
68
  }
 
1
  {
2
+ "version": "0.59.0",
3
  "precisions": {
4
+ "float": {
5
  "universal_assets": {
6
+ "onnx": {
7
+ "tool_versions": {
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/gpunet/releases/v0.59.0/gpunet-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/gpunet/releases/v0.59.0/gpunet-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/gpunet/releases/v0.59.0/gpunet-tflite-float.zip"
24
  }
25
  }
26
  },
27
+ "w8a16": {
28
  "universal_assets": {
29
+ "onnx": {
30
  "tool_versions": {
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/gpunet/releases/v0.59.0/gpunet-onnx-w8a16.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/gpunet/releases/v0.59.0/gpunet-qnn_dlc-w8a16.zip"
 
 
 
 
 
 
 
41
  }
42
  }
43
  },
44
+ "w8a8": {
45
  "universal_assets": {
46
+ "onnx": {
47
  "tool_versions": {
48
  "qairt": "2.45.0.260326154327",
49
+ "onnx_runtime": "1.27.1"
50
  },
51
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.59.0/gpunet-onnx-w8a8.zip"
52
  },
53
  "qnn_dlc": {
54
  "tool_versions": {
55
  "qairt": "2.45.0.260326154327"
56
  },
57
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.59.0/gpunet-qnn_dlc-w8a8.zip"
58
  },
59
+ "tflite": {
60
  "tool_versions": {
61
+ "qairt": "2.45.0.260326154327"
 
62
  },
63
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.59.0/gpunet-tflite-w8a8.zip"
64
  }
65
  }
66
  }