Hugging Face's logo

qualcomm
/
FCN-ResNet50

Image Segmentation
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
a9d4e8d
·
verified ·
1 Parent(s): c91047e

v0.63.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.

Files changed (2) hide show
  1. README.md +99 -107
  2. release_assets.json +13 -13
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-segmentation
14
  FCN_ResNet50 is a machine learning model that can segment images from the COCO dataset. It uses ResNet50 as a backbone.
15
 
16
  This is based on the implementation of FCN-ResNet50 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/fcn.py).
17
- 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/v0.62.2/src/qai_hub_models/models/fcn_resnet50) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
 
19
  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.
20
 
@@ -27,26 +27,26 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | 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/fcn_resnet50/releases/v0.62.2/fcn_resnet50-onnx-float.zip)
31
- | 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/fcn_resnet50/releases/v0.62.2/fcn_resnet50-onnx-w8a8.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.62.2/fcn_resnet50-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.62.2/fcn_resnet50-qnn_dlc-w8a8.zip)
34
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.62.2/fcn_resnet50-tflite-float.zip)
35
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.62.2/fcn_resnet50-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[FCN-ResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fcn_resnet50)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/fcn_resnet50) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
- See our repository for [FCN-ResNet50 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/fcn_resnet50) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -63,104 +63,96 @@ See our repository for [FCN-ResNet50 on GitHub](https://github.com/qualcomm/ai-h
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | FCN-ResNet50 | ONNX | float | Snapdragon® X2 Elite | 22.251 ms | 3 - 3 MB | NPU
67
- | FCN-ResNet50 | ONNX | float | Snapdragon® X Elite | 43.628 ms | 63 - 63 MB | NPU
68
- | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 32.577 ms | 0 - 379 MB | NPU
69
- | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 83.138 ms | 2 - 272 MB | NPU
70
- | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 82.224 ms | 3 - 10 MB | NPU
71
- | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 43.57 ms | 0 - 413 MB | NPU
72
- | FCN-ResNet50 | ONNX | float | Qualcomm® QCS8450 | 83.138 ms | 2 - 272 MB | NPU
73
- | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 72.757 ms | 3 - 9 MB | NPU
74
- | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 43.628 ms | 63 - 63 MB | NPU
75
- | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 26.911 ms | 1 - 309 MB | NPU
76
- | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Elite Mobile | 26.911 ms | 1 - 309 MB | NPU
77
- | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 21.076 ms | 1 - 330 MB | NPU
78
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® X2 Elite | 7.279 ms | 2 - 2 MB | NPU
79
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® X Elite | 13.893 ms | 33 - 33 MB | NPU
80
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 10.185 ms | 1 - 278 MB | NPU
81
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 21.01 ms | 0 - 270 MB | NPU
82
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 122.061 ms | 1 - 4 MB | NPU
83
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 14.38 ms | 1 - 5 MB | NPU
84
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.58 ms | 0 - 278 MB | NPU
85
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS8450 | 21.01 ms | 0 - 270 MB | NPU
86
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 14.325 ms | 1 - 4 MB | NPU
87
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 13.893 ms | 33 - 33 MB | NPU
88
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 402.43 ms | 2 - 390 MB | NPU
89
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 25.654 ms | 1 - 283 MB | NPU
90
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.754 ms | 0 - 203 MB | NPU
91
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 8.754 ms | 0 - 203 MB | NPU
92
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.463 ms | 0 - 250 MB | NPU
93
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 25.654 ms | 1 - 283 MB | NPU
94
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 22.982 ms | 3 - 3 MB | NPU
95
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® X Elite | 44.751 ms | 3 - 3 MB | NPU
96
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 33.241 ms | 2 - 379 MB | NPU
97
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 83.801 ms | 3 - 272 MB | NPU
98
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 82.447 ms | 3 - 9 MB | NPU
99
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 43.929 ms | 3 - 5 MB | NPU
100
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8775P | 72.875 ms | 1 - 310 MB | NPU
101
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8650P | 72.875 ms | 1 - 310 MB | NPU
102
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8255P | 72.875 ms | 1 - 310 MB | NPU
103
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS8450 | 83.801 ms | 3 - 272 MB | NPU
104
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 72.927 ms | 3 - 8 MB | NPU
105
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 44.751 ms | 3 - 3 MB | NPU
106
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 26.313 ms | 3 - 323 MB | NPU
107
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 273.761 ms | 0 - 310 MB | NPU
108
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 77.818 ms | 0 - 218 MB | NPU
109
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 26.313 ms | 3 - 323 MB | NPU
110
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 21.411 ms | 3 - 339 MB | NPU
111
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 7.859 ms | 1 - 1 MB | NPU
112
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 15.253 ms | 1 - 1 MB | NPU
113
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.243 ms | 1 - 261 MB | NPU
114
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 24.394 ms | 1 - 265 MB | NPU
115
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 122.943 ms | 1 - 3 MB | NPU
116
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 15.665 ms | 1 - 4 MB | NPU
117
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.905 ms | 1 - 3 MB | NPU
118
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 14.712 ms | 1 - 216 MB | NPU
119
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 14.712 ms | 1 - 216 MB | NPU
120
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 14.712 ms | 1 - 216 MB | NPU
121
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 24.394 ms | 1 - 265 MB | NPU
122
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 14.918 ms | 0 - 3 MB | NPU
123
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 15.253 ms | 1 - 1 MB | NPU
124
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 409.568 ms | 1 - 385 MB | NPU
125
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 26.47 ms | 1 - 279 MB | NPU
126
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.924 ms | 1 - 201 MB | NPU
127
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 39.465 ms | 1 - 206 MB | NPU
128
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 21.882 ms | 0 - 208 MB | NPU
129
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 8.924 ms | 1 - 201 MB | NPU
130
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.469 ms | 1 - 246 MB | NPU
131
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 26.47 ms | 1 - 279 MB | NPU
132
- | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.898 ms | 0 - 426 MB | NPU
133
- | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 83.601 ms | 0 - 322 MB | NPU
134
- | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 81.991 ms | 0 - 72 MB | NPU
135
- | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 44.39 ms | 0 - 3 MB | NPU
136
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8775P | 72.919 ms | 1 - 354 MB | NPU
137
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8650P | 72.919 ms | 1 - 354 MB | NPU
138
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8255P | 72.919 ms | 1 - 354 MB | NPU
139
- | FCN-ResNet50 | TFLITE | float | Qualcomm® QCS8450 | 83.601 ms | 0 - 322 MB | NPU
140
- | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 72.977 ms | 0 - 71 MB | NPU
141
- | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 27.26 ms | 0 - 357 MB | NPU
142
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA7255P | 273.546 ms | 1 - 353 MB | NPU
143
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8295P | 77.769 ms | 1 - 267 MB | NPU
144
- | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Mobile | 27.26 ms | 0 - 357 MB | NPU
145
- | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 20.932 ms | 0 - 367 MB | NPU
146
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 10.99 ms | 0 - 268 MB | NPU
147
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 23.228 ms | 0 - 266 MB | NPU
148
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 124.071 ms | 0 - 39 MB | NPU
149
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 15.073 ms | 0 - 36 MB | NPU
150
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.267 ms | 0 - 3 MB | NPU
151
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8775P | 14.708 ms | 0 - 208 MB | NPU
152
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8650P | 14.708 ms | 0 - 208 MB | NPU
153
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8255P | 14.708 ms | 0 - 208 MB | NPU
154
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8450 | 23.228 ms | 0 - 266 MB | NPU
155
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 14.811 ms | 0 - 35 MB | NPU
156
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 436.452 ms | 0 - 388 MB | NPU
157
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 27.863 ms | 0 - 280 MB | NPU
158
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.58 ms | 0 - 197 MB | NPU
159
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA7255P | 38.226 ms | 0 - 207 MB | NPU
160
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8295P | 21.306 ms | 0 - 208 MB | NPU
161
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 8.58 ms | 0 - 197 MB | NPU
162
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.399 ms | 0 - 245 MB | NPU
163
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 27.863 ms | 0 - 280 MB | NPU
164
 
165
  ## License
166
  * The license for the original implementation of FCN-ResNet50 can be found
 
14
  FCN_ResNet50 is a machine learning model that can segment images from the COCO dataset. It uses ResNet50 as a backbone.
15
 
16
  This is based on the implementation of FCN-ResNet50 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/fcn.py).
17
+ 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/v0.63.0/src/qai_hub_models/models/fcn_resnet50) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
 
19
  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.
20
 
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.63.0/fcn_resnet50-onnx-float.zip)
31
+ | ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.63.0/fcn_resnet50-onnx-w8a8.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.63.0/fcn_resnet50-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.63.0/fcn_resnet50-qnn_dlc-w8a8.zip)
34
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.63.0/fcn_resnet50-tflite-float.zip)
35
+ | TFLITE | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.63.0/fcn_resnet50-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[FCN-ResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fcn_resnet50)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/fcn_resnet50) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
+ See our repository for [FCN-ResNet50 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/fcn_resnet50) for usage instructions.
50
 
51
  ## Model Details
52
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 30.994 ms | 2 - 408 MB | NPU
67
+ | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.473 ms | 1 - 358 MB | NPU
68
+ | FCN-ResNet50 | ONNX | float | Snapdragon® X2 Elite | 28.317 ms | 3 - 3 MB | NPU
69
+ | FCN-ResNet50 | ONNX | float | Snapdragon® X Elite | 43.827 ms | 65 - 65 MB | NPU
70
+ | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 32.575 ms | 0 - 448 MB | NPU
71
+ | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 85.977 ms | 4 - 302 MB | NPU
72
+ | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 82.565 ms | 3 - 10 MB | NPU
73
+ | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 43.558 ms | 0 - 114 MB | NPU
74
+ | FCN-ResNet50 | ONNX | float | Qualcomm® QCS8450 | 85.977 ms | 4 - 302 MB | NPU
75
+ | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 72.537 ms | 3 - 9 MB | NPU
76
+ | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 43.827 ms | 65 - 65 MB | NPU
77
+ | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 27.473 ms | 1 - 358 MB | NPU
78
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.293 ms | 0 - 240 MB | NPU
79
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.951 ms | 0 - 193 MB | NPU
80
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® X2 Elite | 6.545 ms | 2 - 2 MB | NPU
81
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® X Elite | 13.243 ms | 33 - 33 MB | NPU
82
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 9.67 ms | 0 - 274 MB | NPU
83
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 15.605 ms | 0 - 262 MB | NPU
84
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 106.333 ms | 1 - 5 MB | NPU
85
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 13.598 ms | 1 - 5 MB | NPU
86
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.998 ms | 0 - 44 MB | NPU
87
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS8450 | 15.605 ms | 0 - 262 MB | NPU
88
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 13.416 ms | 1 - 5 MB | NPU
89
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 13.243 ms | 33 - 33 MB | NPU
90
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 477.652 ms | 1 - 329 MB | NPU
91
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 25.587 ms | 1 - 310 MB | NPU
92
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 7.951 ms | 0 - 193 MB | NPU
93
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 25.587 ms | 1 - 310 MB | NPU
94
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 31.651 ms | 3 - 413 MB | NPU
95
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.55 ms | 3 - 397 MB | NPU
96
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 29.182 ms | 3 - 3 MB | NPU
97
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® X Elite | 57.972 ms | 3 - 3 MB | NPU
98
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 45.487 ms | 0 - 496 MB | NPU
99
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 87.792 ms | 1 - 303 MB | NPU
100
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 99.12 ms | 3 - 9 MB | NPU
101
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 60.116 ms | 3 - 6 MB | NPU
102
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS8450 | 87.792 ms | 1 - 303 MB | NPU
103
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 88.509 ms | 3 - 9 MB | NPU
104
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 57.972 ms | 3 - 3 MB | NPU
105
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 38.55 ms | 3 - 397 MB | NPU
106
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 94.577 ms | 0 - 253 MB | NPU
107
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.482 ms | 1 - 237 MB | NPU
108
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 8.249 ms | 1 - 190 MB | NPU
109
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 7.063 ms | 1 - 1 MB | NPU
110
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 13.955 ms | 1 - 1 MB | NPU
111
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 10.249 ms | 1 - 270 MB | NPU
112
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 17.298 ms | 1 - 253 MB | NPU
113
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 107.164 ms | 1 - 4 MB | NPU
114
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 14.416 ms | 1 - 5 MB | NPU
115
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.434 ms | 1 - 12 MB | NPU
116
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 17.298 ms | 1 - 253 MB | NPU
117
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 14.154 ms | 1 - 4 MB | NPU
118
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 13.955 ms | 1 - 1 MB | NPU
119
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 463.769 ms | 1 - 314 MB | NPU
120
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 25.506 ms | 1 - 304 MB | NPU
121
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.249 ms | 1 - 190 MB | NPU
122
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 20.192 ms | 1 - 214 MB | NPU
123
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 25.506 ms | 1 - 304 MB | NPU
124
+ | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 31.662 ms | 0 - 436 MB | NPU
125
+ | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.553 ms | 0 - 414 MB | NPU
126
+ | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 46.496 ms | 0 - 524 MB | NPU
127
+ | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 87.875 ms | 1 - 354 MB | NPU
128
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 99.273 ms | 0 - 74 MB | NPU
129
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 60.58 ms | 0 - 4 MB | NPU
130
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8775P | 86.886 ms | 0 - 413 MB | NPU
131
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8650P | 86.886 ms | 0 - 413 MB | NPU
132
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8255P | 86.886 ms | 0 - 413 MB | NPU
133
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® QCS8450 | 87.875 ms | 1 - 354 MB | NPU
134
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 87.244 ms | 0 - 73 MB | NPU
135
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 38.553 ms | 0 - 414 MB | NPU
136
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA7255P | 3264.719 ms | 1 - 22 MB | CPU
137
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8295P | 94.484 ms | 1 - 302 MB | NPU
138
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.196 ms | 0 - 237 MB | NPU
139
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.869 ms | 0 - 191 MB | NPU
140
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 9.483 ms | 0 - 267 MB | NPU
141
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 15.619 ms | 0 - 258 MB | NPU
142
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 117.366 ms | 0 - 37 MB | NPU
143
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 13.48 ms | 0 - 37 MB | NPU
144
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.643 ms | 0 - 3 MB | NPU
145
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8775P | 13.129 ms | 0 - 210 MB | NPU
146
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8650P | 13.129 ms | 0 - 210 MB | NPU
147
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8255P | 13.129 ms | 0 - 210 MB | NPU
148
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8450 | 15.619 ms | 0 - 258 MB | NPU
149
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 13.201 ms | 0 - 36 MB | NPU
150
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 485.503 ms | 0 - 314 MB | NPU
151
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 25.974 ms | 0 - 303 MB | NPU
152
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 7.869 ms | 0 - 191 MB | NPU
153
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA7255P | 36.455 ms | 0 - 205 MB | NPU
154
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8295P | 19.256 ms | 0 - 208 MB | NPU
155
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 25.974 ms | 0 - 303 MB | NPU
 
 
 
 
 
 
 
 
156
 
157
  ## License
158
  * The license for the original implementation of FCN-ResNet50 can be found
release_assets.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "version": "0.62.2",
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/fcn_resnet50/releases/v0.62.2/fcn_resnet50-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/fcn_resnet50/releases/v0.62.2/fcn_resnet50-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/fcn_resnet50/releases/v0.62.2/fcn_resnet50-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -28,22 +28,22 @@
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/fcn_resnet50/releases/v0.62.2/fcn_resnet50-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/fcn_resnet50/releases/v0.62.2/fcn_resnet50-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/fcn_resnet50/releases/v0.62.2/fcn_resnet50-tflite-w8a8.zip"
47
  }
48
  }
49
  }
 
1
  {
2
+ "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
+ "qairt": "2.50.0.260828221209",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.63.0/fcn_resnet50-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/fcn_resnet50/releases/v0.63.0/fcn_resnet50-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/fcn_resnet50/releases/v0.63.0/fcn_resnet50-tflite-float.zip"
24
  }
25
  }
26
  },
 
28
  "universal_assets": {
29
  "onnx": {
30
  "tool_versions": {
31
+ "qairt": "2.50.0.260828221209",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.63.0/fcn_resnet50-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/fcn_resnet50/releases/v0.63.0/fcn_resnet50-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/fcn_resnet50/releases/v0.63.0/fcn_resnet50-tflite-w8a8.zip"
47
  }
48
  }
49
  }