Image Segmentation
PyTorch
android
qaihm-bot commited on
Commit
4136b44
·
verified ·
1 Parent(s): 81d075c

See https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.

Files changed (2) hide show
  1. README.md +105 -99
  2. release_assets.json +7 -7
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/v0.57.3/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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.57.3/fcn_resnet50-onnx-float.zip)
31
- | 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/fcn_resnet50/releases/v0.57.3/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/v0.57.3/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/v0.57.3/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/v0.57.3/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/v0.57.3/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/v0.57.3/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/v0.57.3/src/qai_hub_models/models/fcn_resnet50) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -63,96 +63,102 @@ 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 | 22.125 ms | 209 - 209 MB | NPU
67
- | FCN-ResNet50 | ONNX | float | Snapdragon® X Elite | 43.533 ms | 146 - 146 MB | NPU
68
- | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 32.689 ms | 0 - 370 MB | NPU
69
- | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 83.156 ms | 4 - 265 MB | NPU
70
- | FCN-ResNet50 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 43.4 ms | 3 - 7 MB | NPU
71
- | FCN-ResNet50 | ONNX | float | Qualcomm® QCS8450 | 83.156 ms | 4 - 265 MB | NPU
72
- | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Elite Mobile | 26.745 ms | 2 - 310 MB | NPU
73
- | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 20.957 ms | 1 - 322 MB | NPU
74
- | FCN-ResNet50 | ONNX | float | Qualcomm® QCS9075 | 76.114 ms | 3 - 48 MB | NPU
75
- | FCN-ResNet50 | ONNX | float | Qualcomm® QCS8750 | 26.745 ms | 2 - 310 MB | NPU
76
- | FCN-ResNet50 | ONNX | float | Qualcomm® QCS7181 | 43.533 ms | 146 - 146 MB | NPU
77
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® X2 Elite | 7.284 ms | 212 - 212 MB | NPU
78
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® X Elite | 13.768 ms | 153 - 153 MB | NPU
79
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 10.036 ms | 1 - 267 MB | NPU
80
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 20.949 ms | 1 - 262 MB | NPU
81
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS6490 | 92.479 ms | 1 - 47 MB | NPU
82
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 13.656 ms | 0 - 54 MB | NPU
83
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS8450 | 20.949 ms | 1 - 262 MB | NPU
84
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.437 ms | 1 - 248 MB | NPU
85
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 25.994 ms | 1 - 279 MB | NPU
86
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCM6690 | 412.098 ms | 0 - 380 MB | NPU
87
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS9075 | 15.091 ms | 1 - 47 MB | NPU
88
- | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 8.757 ms | 0 - 204 MB | NPU
89
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS7790 | 25.994 ms | 1 - 279 MB | NPU
90
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS8750 | 8.757 ms | 0 - 204 MB | NPU
91
- | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS7181 | 13.768 ms | 153 - 153 MB | NPU
92
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 22.755 ms | 3 - 3 MB | NPU
93
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® X Elite | 44.686 ms | 3 - 3 MB | NPU
94
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 33.313 ms | 1 - 377 MB | NPU
95
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 83.727 ms | 4 - 274 MB | NPU
96
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS8275 | 273.613 ms | 1 - 309 MB | NPU
97
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 44.404 ms | 3 - 6 MB | NPU
98
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS8450 | 83.727 ms | 4 - 274 MB | NPU
99
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 26.58 ms | 3 - 324 MB | NPU
100
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 77.798 ms | 1 - 219 MB | NPU
101
- | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 21.314 ms | 3 - 337 MB | NPU
102
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 273.613 ms | 1 - 309 MB | NPU
103
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS9075 | 78.48 ms | 3 - 8 MB | NPU
104
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS8750 | 26.58 ms | 3 - 324 MB | NPU
105
- | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS7181 | 44.686 ms | 3 - 3 MB | NPU
106
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 7.791 ms | 1 - 1 MB | NPU
107
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 15.214 ms | 1 - 1 MB | NPU
108
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.283 ms | 1 - 265 MB | NPU
109
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 24.389 ms | 1 - 264 MB | NPU
110
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 93.458 ms | 1 - 3 MB | NPU
111
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 39.493 ms | 1 - 207 MB | NPU
112
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 14.868 ms | 1 - 153 MB | NPU
113
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 24.389 ms | 1 - 264 MB | NPU
114
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.446 ms | 1 - 248 MB | NPU
115
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 26.055 ms | 1 - 280 MB | NPU
116
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 418.038 ms | 1 - 385 MB | NPU
117
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 17.531 ms | 3 - 5 MB | NPU
118
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 39.493 ms | 1 - 207 MB | NPU
119
- | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 8.942 ms | 1 - 202 MB | NPU
120
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 21.902 ms | 1 - 210 MB | NPU
121
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 26.055 ms | 1 - 280 MB | NPU
122
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 8.942 ms | 1 - 202 MB | NPU
123
- | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 15.214 ms | 1 - 1 MB | NPU
124
- | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.916 ms | 0 - 426 MB | NPU
125
- | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 84.005 ms | 1 - 321 MB | NPU
126
- | FCN-ResNet50 | TFLITE | float | Qualcomm® QCS8275 | 273.522 ms | 1 - 354 MB | NPU
127
- | FCN-ResNet50 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 43.898 ms | 0 - 3 MB | NPU
128
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8775P | 2273.537 ms | 20 - 41 MB | CPU
129
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8650P | 2273.537 ms | 20 - 41 MB | CPU
130
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8255P | 2273.537 ms | 20 - 41 MB | CPU
131
- | FCN-ResNet50 | TFLITE | float | Qualcomm® QCS8450 | 84.005 ms | 1 - 321 MB | NPU
132
- | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Mobile | 26.944 ms | 0 - 356 MB | NPU
133
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8295P | 77.801 ms | 0 - 267 MB | NPU
134
- | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 20.83 ms | 0 - 373 MB | NPU
135
- | FCN-ResNet50 | TFLITE | float | Qualcomm® SA7255P | 273.522 ms | 1 - 354 MB | NPU
136
- | FCN-ResNet50 | TFLITE | float | Qualcomm® QCS9075 | 77.883 ms | 0 - 71 MB | NPU
137
- | FCN-ResNet50 | TFLITE | float | Qualcomm® QCS8750 | 26.944 ms | 0 - 356 MB | NPU
138
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.003 ms | 0 - 267 MB | NPU
139
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 23.133 ms | 0 - 266 MB | NPU
140
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS6490 | 95.208 ms | 0 - 39 MB | NPU
141
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8275 | 38.242 ms | 0 - 207 MB | NPU
142
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 14.291 ms | 0 - 3 MB | NPU
143
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8775P | 550.194 ms | 6 - 30 MB | CPU
144
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8650P | 550.194 ms | 6 - 30 MB | CPU
145
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8255P | 550.194 ms | 6 - 30 MB | CPU
146
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8450 | 23.133 ms | 0 - 266 MB | NPU
147
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.385 ms | 0 - 246 MB | NPU
148
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 28.01 ms | 0 - 297 MB | NPU
149
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCM6690 | 442.766 ms | 0 - 389 MB | NPU
150
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS9075 | 15.251 ms | 0 - 35 MB | NPU
151
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA7255P | 38.242 ms | 0 - 207 MB | NPU
152
- | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 8.615 ms | 0 - 198 MB | NPU
153
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8295P | 21.28 ms | 0 - 210 MB | NPU
154
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS7790 | 28.01 ms | 0 - 297 MB | NPU
155
- | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8750 | 8.615 ms | 0 - 198 MB | NPU
 
 
 
 
 
 
156
 
157
  ## License
158
  * 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/v0.58.0/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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.58.0/fcn_resnet50-onnx-float.zip)
31
+ | 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/fcn_resnet50/releases/v0.58.0/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/v0.58.0/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/v0.58.0/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/v0.58.0/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/v0.58.0/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/v0.58.0/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/v0.58.0/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® X2 Elite | 22.222 ms | 3 - 3 MB | NPU
67
+ | FCN-ResNet50 | ONNX | float | Snapdragon® X Elite | 43.532 ms | 63 - 63 MB | NPU
68
+ | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 32.587 ms | 0 - 379 MB | NPU
69
+ | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 82.782 ms | 1 - 272 MB | NPU
70
+ | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 43.104 ms | 3 - 6 MB | NPU
71
+ | FCN-ResNet50 | ONNX | float | Qualcomm® QCS8450 | 82.782 ms | 1 - 272 MB | NPU
72
+ | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 72.659 ms | 3 - 9 MB | NPU
73
+ | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 21.073 ms | 2 - 327 MB | NPU
74
+ | FCN-ResNet50 | ONNX | float | Snapdragon® 8 Elite Mobile | 26.846 ms | 1 - 309 MB | NPU
75
+ | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 26.846 ms | 1 - 309 MB | NPU
76
+ | FCN-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 43.532 ms | 63 - 63 MB | NPU
77
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® X2 Elite | 7.292 ms | 2 - 2 MB | NPU
78
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® X Elite | 13.797 ms | 32 - 32 MB | NPU
79
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 10.009 ms | 0 - 277 MB | NPU
80
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 21.169 ms | 1 - 273 MB | NPU
81
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 121.883 ms | 1 - 4 MB | NPU
82
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.581 ms | 0 - 41 MB | NPU
83
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® QCS8450 | 21.169 ms | 1 - 273 MB | NPU
84
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 8.733 ms | 1 - 204 MB | NPU
85
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 25.598 ms | 1 - 284 MB | NPU
86
+ | FCN-ResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.458 ms | 0 - 249 MB | NPU
87
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 14.246 ms | 1 - 4 MB | NPU
88
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 426.035 ms | 0 - 389 MB | NPU
89
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 25.598 ms | 1 - 284 MB | NPU
90
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.733 ms | 1 - 204 MB | NPU
91
+ | FCN-ResNet50 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 13.797 ms | 32 - 32 MB | NPU
92
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 22.909 ms | 3 - 3 MB | NPU
93
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® X Elite | 44.618 ms | 3 - 3 MB | NPU
94
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 33.223 ms | 3 - 378 MB | NPU
95
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 83.567 ms | 0 - 270 MB | NPU
96
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS8275 | 273.677 ms | 1 - 309 MB | NPU
97
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 44.6 ms | 3 - 380 MB | NPU
98
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8775P | 72.833 ms | 1 - 309 MB | NPU
99
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8650P | 72.833 ms | 1 - 309 MB | NPU
100
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8255P | 72.833 ms | 1 - 309 MB | NPU
101
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® QCS8450 | 83.567 ms | 0 - 270 MB | NPU
102
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 73.397 ms | 5 - 10 MB | NPU
103
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 21.481 ms | 3 - 336 MB | NPU
104
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 273.677 ms | 1 - 309 MB | NPU
105
+ | FCN-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 26.379 ms | 0 - 319 MB | NPU
106
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 77.815 ms | 0 - 216 MB | NPU
107
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 26.379 ms | 0 - 319 MB | NPU
108
+ | FCN-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 44.618 ms | 3 - 3 MB | NPU
109
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 7.846 ms | 1 - 1 MB | NPU
110
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 15.148 ms | 1 - 1 MB | NPU
111
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.197 ms | 1 - 262 MB | NPU
112
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 24.41 ms | 0 - 264 MB | NPU
113
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 122.789 ms | 3 - 5 MB | NPU
114
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 39.463 ms | 1 - 207 MB | NPU
115
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.845 ms | 1 - 3 MB | NPU
116
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 14.711 ms | 1 - 216 MB | NPU
117
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 14.711 ms | 1 - 216 MB | NPU
118
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 14.711 ms | 1 - 216 MB | NPU
119
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 24.41 ms | 0 - 264 MB | NPU
120
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 8.939 ms | 1 - 200 MB | NPU
121
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 26.009 ms | 1 - 280 MB | NPU
122
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.468 ms | 1 - 250 MB | NPU
123
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 14.654 ms | 1 - 3 MB | NPU
124
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 396.277 ms | 1 - 384 MB | NPU
125
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 39.463 ms | 1 - 207 MB | NPU
126
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 21.873 ms | 1 - 209 MB | NPU
127
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 26.009 ms | 1 - 280 MB | NPU
128
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.939 ms | 1 - 200 MB | NPU
129
+ | FCN-ResNet50 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 15.148 ms | 1 - 1 MB | NPU
130
+ | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 33.257 ms | 0 - 428 MB | NPU
131
+ | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 83.981 ms | 1 - 323 MB | NPU
132
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® QCS8275 | 273.512 ms | 1 - 354 MB | NPU
133
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 44.374 ms | 0 - 3 MB | NPU
134
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8775P | 72.797 ms | 1 - 353 MB | NPU
135
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8650P | 72.797 ms | 1 - 353 MB | NPU
136
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8255P | 72.797 ms | 1 - 353 MB | NPU
137
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® QCS8450 | 83.981 ms | 1 - 323 MB | NPU
138
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 72.468 ms | 0 - 71 MB | NPU
139
+ | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 20.991 ms | 0 - 372 MB | NPU
140
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA7255P | 273.512 ms | 1 - 354 MB | NPU
141
+ | FCN-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Mobile | 27.121 ms | 0 - 358 MB | NPU
142
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® SA8295P | 77.786 ms | 0 - 268 MB | NPU
143
+ | FCN-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 27.121 ms | 0 - 358 MB | NPU
144
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 10.959 ms | 0 - 266 MB | NPU
145
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 23.196 ms | 0 - 265 MB | NPU
146
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 123.903 ms | 0 - 39 MB | NPU
147
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8275 | 38.24 ms | 0 - 207 MB | NPU
148
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.271 ms | 0 - 3 MB | NPU
149
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8775P | 14.696 ms | 0 - 206 MB | NPU
150
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8650P | 14.696 ms | 0 - 206 MB | NPU
151
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8255P | 14.696 ms | 0 - 206 MB | NPU
152
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® QCS8450 | 23.196 ms | 0 - 265 MB | NPU
153
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 8.591 ms | 0 - 199 MB | NPU
154
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 28.075 ms | 0 - 280 MB | NPU
155
+ | FCN-ResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.41 ms | 0 - 245 MB | NPU
156
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 14.737 ms | 0 - 35 MB | NPU
157
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 423.536 ms | 1 - 380 MB | NPU
158
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA7255P | 38.24 ms | 0 - 207 MB | NPU
159
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® SA8295P | 21.289 ms | 0 - 209 MB | NPU
160
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 28.075 ms | 0 - 280 MB | NPU
161
+ | FCN-ResNet50 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.591 ms | 0 - 199 MB | NPU
162
 
163
  ## License
164
  * The license for the original implementation of FCN-ResNet50 can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,20 +8,20 @@
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.57.3/fcn_resnet50-tflite-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/v0.57.3/fcn_resnet50-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.57.3/fcn_resnet50-onnx-float.zip"
25
  }
26
  }
27
  },
@@ -32,20 +32,20 @@
32
  "qairt": "2.45.0.260326154327",
33
  "litert": "1.4.4"
34
  },
35
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.57.3/fcn_resnet50-tflite-w8a8.zip"
36
  },
37
  "qnn_dlc": {
38
  "tool_versions": {
39
  "qairt": "2.45.0.260326154327"
40
  },
41
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.57.3/fcn_resnet50-qnn_dlc-w8a8.zip"
42
  },
43
  "onnx": {
44
  "tool_versions": {
45
  "qairt": "2.45.0.260326154327",
46
  "onnx_runtime": "1.25.0"
47
  },
48
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.57.3/fcn_resnet50-onnx-w8a8.zip"
49
  }
50
  }
51
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.58.0/fcn_resnet50-tflite-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/v0.58.0/fcn_resnet50-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.58.0/fcn_resnet50-onnx-float.zip"
25
  }
26
  }
27
  },
 
32
  "qairt": "2.45.0.260326154327",
33
  "litert": "1.4.4"
34
  },
35
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.58.0/fcn_resnet50-tflite-w8a8.zip"
36
  },
37
  "qnn_dlc": {
38
  "tool_versions": {
39
  "qairt": "2.45.0.260326154327"
40
  },
41
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.58.0/fcn_resnet50-qnn_dlc-w8a8.zip"
42
  },
43
  "onnx": {
44
  "tool_versions": {
45
  "qairt": "2.45.0.260326154327",
46
  "onnx_runtime": "1.25.0"
47
  },
48
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fcn_resnet50/releases/v0.58.0/fcn_resnet50-onnx-w8a8.zip"
49
  }
50
  }
51
  }