Hugging Face's logo

qualcomm
/
PidNet

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
2da5547
·
verified ·
1 Parent(s): 28c6de9

v0.58.0

Browse files

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

Files changed (2) hide show
  1. README.md +101 -95
  2. release_assets.json +7 -7
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-segmentation
15
  PIDNet (Proportional-Integral-Derivative Network) is a real-time semantic segmentation model based on PID controllers
16
 
17
  This is based on the implementation of PidNet found [here](https://github.com/XuJiacong/PIDNet).
18
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/pidnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
@@ -28,26 +28,26 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | 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/pidnet/releases/v0.57.3/pidnet-onnx-float.zip)
32
- | 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/pidnet/releases/v0.57.3/pidnet-onnx-w8a8.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.57.3/pidnet-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.57.3/pidnet-qnn_dlc-w8a8.zip)
35
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.57.3/pidnet-tflite-float.zip)
36
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.57.3/pidnet-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[PidNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/pidnet)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/pidnet) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
- See our repository for [PidNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/pidnet) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -65,92 +65,98 @@ See our repository for [PidNet on GitHub](https://github.com/qualcomm/ai-hub-mod
65
  ## Performance Summary
66
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
67
  |---|---|---|---|---|---|---
68
- | PidNet | ONNX | float | Snapdragon® X2 Elite | 13.763 ms | 189 - 189 MB | NPU
69
- | PidNet | ONNX | float | Snapdragon® X Elite | 32.32 ms | 158 - 158 MB | NPU
70
- | PidNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 22.916 ms | 31 - 322 MB | NPU
71
- | PidNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 55.626 ms | 29 - 324 MB | NPU
72
- | PidNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 32.415 ms | 24 - 51 MB | NPU
73
- | PidNet | ONNX | float | Qualcomm® QCS8450 | 55.626 ms | 29 - 324 MB | NPU
74
- | PidNet | ONNX | float | Snapdragon® 8 Elite Mobile | 17.854 ms | 7 - 219 MB | NPU
75
- | PidNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 13.144 ms | 5 - 250 MB | NPU
76
- | PidNet | ONNX | float | Qualcomm® QCS9075 | 47.664 ms | 24 - 93 MB | NPU
77
- | PidNet | ONNX | float | Qualcomm® QCS8750 | 17.854 ms | 7 - 219 MB | NPU
78
- | PidNet | ONNX | float | Qualcomm® QCS7181 | 32.32 ms | 158 - 158 MB | NPU
79
- | PidNet | ONNX | w8a8 | Snapdragon® X2 Elite | 25.958 ms | 207 - 207 MB | NPU
80
- | PidNet | ONNX | w8a8 | Snapdragon® X Elite | 54.825 ms | 175 - 175 MB | NPU
81
- | PidNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 39.101 ms | 7 - 261 MB | NPU
82
- | PidNet | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 57.664 ms | 7 - 263 MB | NPU
83
- | PidNet | ONNX | w8a8 | Qualcomm® QCS6490 | 132.062 ms | 6 - 51 MB | NPU
84
- | PidNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 52.469 ms | 0 - 19 MB | NPU
85
- | PidNet | ONNX | w8a8 | Qualcomm® QCS8450 | 57.664 ms | 7 - 263 MB | NPU
86
- | PidNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 25.794 ms | 2 - 232 MB | NPU
87
- | PidNet | ONNX | w8a8 | Qualcomm® QCM6690 | 215.567 ms | 7 - 222 MB | NPU
88
- | PidNet | ONNX | w8a8 | Qualcomm® QCS9075 | 54.995 ms | 4 - 51 MB | NPU
89
- | PidNet | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 45.245 ms | 2 - 219 MB | NPU
90
- | PidNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 61.984 ms | 7 - 232 MB | NPU
91
- | PidNet | ONNX | w8a8 | Qualcomm® QCS7790 | 61.984 ms | 7 - 232 MB | NPU
92
- | PidNet | ONNX | w8a8 | Qualcomm® QCS8750 | 45.245 ms | 2 - 219 MB | NPU
93
- | PidNet | ONNX | w8a8 | Qualcomm® QCS7181 | 54.825 ms | 175 - 175 MB | NPU
94
- | PidNet | QNN_DLC | float | Snapdragon® X2 Elite | 13.6 ms | 24 - 24 MB | NPU
95
- | PidNet | QNN_DLC | float | Snapdragon® X Elite | 39.147 ms | 24 - 24 MB | NPU
96
- | PidNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 25.783 ms | 23 - 327 MB | NPU
97
- | PidNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 75.878 ms | 24 - 331 MB | NPU
98
- | PidNet | QNN_DLC | float | Qualcomm® QCS8275 | 117.745 ms | 24 - 243 MB | NPU
99
- | PidNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 37.694 ms | 24 - 26 MB | NPU
100
- | PidNet | QNN_DLC | float | Qualcomm® QCS8450 | 75.878 ms | 24 - 331 MB | NPU
101
- | PidNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 18.292 ms | 23 - 269 MB | NPU
102
- | PidNet | QNN_DLC | float | Qualcomm® SA8295P | 52.014 ms | 24 - 252 MB | NPU
103
- | PidNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.969 ms | 18 - 291 MB | NPU
104
- | PidNet | QNN_DLC | float | Qualcomm® SA7255P | 117.745 ms | 24 - 243 MB | NPU
105
- | PidNet | QNN_DLC | float | Qualcomm® QCS9075 | 61.104 ms | 26 - 54 MB | NPU
106
- | PidNet | QNN_DLC | float | Qualcomm® QCS8750 | 18.292 ms | 23 - 269 MB | NPU
107
- | PidNet | QNN_DLC | float | Qualcomm® QCS7181 | 39.147 ms | 24 - 24 MB | NPU
108
- | PidNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 25.202 ms | 6 - 6 MB | NPU
109
- | PidNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 60.613 ms | 6 - 6 MB | NPU
110
- | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 43.114 ms | 6 - 266 MB | NPU
111
- | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 63.839 ms | 6 - 269 MB | NPU
112
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 111.317 ms | 6 - 219 MB | NPU
113
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 57.755 ms | 6 - 158 MB | NPU
114
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 63.839 ms | 6 - 269 MB | NPU
115
- | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 24.591 ms | 6 - 273 MB | NPU
116
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 61.722 ms | 6 - 14 MB | NPU
117
- | PidNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 111.317 ms | 6 - 219 MB | NPU
118
- | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 43.837 ms | 6 - 244 MB | NPU
119
- | PidNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 66.422 ms | 6 - 223 MB | NPU
120
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 43.837 ms | 6 - 244 MB | NPU
121
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 60.613 ms | 6 - 6 MB | NPU
122
- | PidNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 24.938 ms | 2 - 325 MB | NPU
123
- | PidNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 73.971 ms | 4 - 330 MB | NPU
124
- | PidNet | TFLITE | float | Qualcomm® QCS8275 | 116.592 ms | 3 - 232 MB | NPU
125
- | PidNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 36.097 ms | 2 - 172 MB | NPU
126
- | PidNet | TFLITE | float | Qualcomm® SA8775P | 141.849 ms | 3 - 32 MB | GPU
127
- | PidNet | TFLITE | float | Qualcomm® SA8650P | 141.849 ms | 3 - 32 MB | GPU
128
- | PidNet | TFLITE | float | Qualcomm® SA8255P | 141.849 ms | 3 - 32 MB | GPU
129
- | PidNet | TFLITE | float | Qualcomm® QCS8450 | 73.971 ms | 4 - 330 MB | NPU
130
- | PidNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 18.758 ms | 2 - 252 MB | NPU
131
- | PidNet | TFLITE | float | Qualcomm® SA8295P | 51.03 ms | 3 - 245 MB | NPU
132
- | PidNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.676 ms | 2 - 273 MB | NPU
133
- | PidNet | TFLITE | float | Qualcomm® SA7255P | 116.592 ms | 3 - 232 MB | NPU
134
- | PidNet | TFLITE | float | Qualcomm® QCS9075 | 59.506 ms | 0 - 45 MB | NPU
135
- | PidNet | TFLITE | float | Qualcomm® QCS8750 | 18.758 ms | 2 - 252 MB | NPU
136
- | PidNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 37.894 ms | 1 - 265 MB | NPU
137
- | PidNet | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 58.239 ms | 1 - 265 MB | NPU
138
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS6490 | 185.168 ms | 2 - 71 MB | NPU
139
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS8275 | 98.412 ms | 1 - 214 MB | NPU
140
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 50.392 ms | 1 - 3 MB | NPU
141
- | PidNet | TFLITE | w8a8 | Qualcomm® SA8775P | 148.903 ms | 27 - 58 MB | GPU
142
- | PidNet | TFLITE | w8a8 | Qualcomm® SA8650P | 148.903 ms | 27 - 58 MB | GPU
143
- | PidNet | TFLITE | w8a8 | Qualcomm® SA8255P | 148.903 ms | 27 - 58 MB | GPU
144
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS8450 | 58.239 ms | 1 - 265 MB | NPU
145
- | PidNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 22.081 ms | 0 - 267 MB | NPU
146
- | PidNet | TFLITE | w8a8 | Qualcomm® QCM6690 | 236.112 ms | 3 - 234 MB | NPU
147
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS9075 | 53.51 ms | 1 - 17 MB | NPU
148
- | PidNet | TFLITE | w8a8 | Qualcomm® SA7255P | 98.412 ms | 1 - 214 MB | NPU
149
- | PidNet | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 69.966 ms | 1 - 234 MB | NPU
150
- | PidNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 66.736 ms | 5 - 223 MB | NPU
151
- | PidNet | TFLITE | w8a8 | Qualcomm® SA8295P | 57.998 ms | 1 - 218 MB | NPU
152
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS7790 | 66.736 ms | 5 - 223 MB | NPU
153
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS8750 | 69.966 ms | 1 - 234 MB | NPU
 
 
 
 
 
 
154
 
155
  ## License
156
  * The license for the original implementation of PidNet can be found
 
15
  PIDNet (Proportional-Integral-Derivative Network) is a real-time semantic segmentation model based on PID controllers
16
 
17
  This is based on the implementation of PidNet found [here](https://github.com/XuJiacong/PIDNet).
18
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/pidnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | 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/pidnet/releases/v0.58.0/pidnet-onnx-float.zip)
32
+ | 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/pidnet/releases/v0.58.0/pidnet-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.58.0/pidnet-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.58.0/pidnet-qnn_dlc-w8a8.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.58.0/pidnet-tflite-float.zip)
36
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.58.0/pidnet-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[PidNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/pidnet)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/pidnet) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
+ See our repository for [PidNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/pidnet) for usage instructions.
51
 
52
  ## Model Details
53
 
 
65
  ## Performance Summary
66
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
67
  |---|---|---|---|---|---|---
68
+ | PidNet | ONNX | float | Snapdragon® X2 Elite | 13.658 ms | 24 - 24 MB | NPU
69
+ | PidNet | ONNX | float | Snapdragon® X Elite | 32.484 ms | 24 - 24 MB | NPU
70
+ | PidNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 23.002 ms | 25 - 327 MB | NPU
71
+ | PidNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 55.461 ms | 0 - 305 MB | NPU
72
+ | PidNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 32.602 ms | 0 - 23 MB | NPU
73
+ | PidNet | ONNX | float | Qualcomm® QCS8450 | 55.461 ms | 0 - 305 MB | NPU
74
+ | PidNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 42.203 ms | 24 - 51 MB | NPU
75
+ | PidNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 13.277 ms | 5 - 255 MB | NPU
76
+ | PidNet | ONNX | float | Snapdragon® 8 Elite Mobile | 17.785 ms | 7 - 220 MB | NPU
77
+ | PidNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 17.785 ms | 7 - 220 MB | NPU
78
+ | PidNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 32.484 ms | 24 - 24 MB | NPU
79
+ | PidNet | ONNX | w8a8 | Snapdragon® X2 Elite | 25.999 ms | 7 - 7 MB | NPU
80
+ | PidNet | ONNX | w8a8 | Snapdragon® X Elite | 54.861 ms | 7 - 7 MB | NPU
81
+ | PidNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 39.133 ms | 7 - 271 MB | NPU
82
+ | PidNet | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 57.662 ms | 8 - 271 MB | NPU
83
+ | PidNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 157.459 ms | 6 - 9 MB | NPU
84
+ | PidNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 52.503 ms | 6 - 151 MB | NPU
85
+ | PidNet | ONNX | w8a8 | Qualcomm® QCS8450 | 57.662 ms | 8 - 271 MB | NPU
86
+ | PidNet | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 44.94 ms | 1 - 219 MB | NPU
87
+ | PidNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 25.765 ms | 2 - 235 MB | NPU
88
+ | PidNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 53.26 ms | 6 - 9 MB | NPU
89
+ | PidNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 62.673 ms | 7 - 235 MB | NPU
90
+ | PidNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 222.961 ms | 5 - 225 MB | NPU
91
+ | PidNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 62.673 ms | 7 - 235 MB | NPU
92
+ | PidNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 44.94 ms | 1 - 219 MB | NPU
93
+ | PidNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 54.861 ms | 7 - 7 MB | NPU
94
+ | PidNet | QNN_DLC | float | Snapdragon® X2 Elite | 13.488 ms | 24 - 24 MB | NPU
95
+ | PidNet | QNN_DLC | float | Snapdragon® X Elite | 38.861 ms | 24 - 24 MB | NPU
96
+ | PidNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 25.489 ms | 20 - 323 MB | NPU
97
+ | PidNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 76.648 ms | 4 - 311 MB | NPU
98
+ | PidNet | QNN_DLC | float | Qualcomm® QCS8275 | 117.748 ms | 24 - 243 MB | NPU
99
+ | PidNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 37.856 ms | 24 - 26 MB | NPU
100
+ | PidNet | QNN_DLC | float | Qualcomm® SA8775P | 46.629 ms | 24 - 244 MB | NPU
101
+ | PidNet | QNN_DLC | float | Qualcomm® SA8650P | 46.629 ms | 24 - 244 MB | NPU
102
+ | PidNet | QNN_DLC | float | Qualcomm® SA8255P | 46.629 ms | 24 - 244 MB | NPU
103
+ | PidNet | QNN_DLC | float | Qualcomm® QCS8450 | 76.648 ms | 4 - 311 MB | NPU
104
+ | PidNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 47.514 ms | 24 - 52 MB | NPU
105
+ | PidNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.056 ms | 22 - 295 MB | NPU
106
+ | PidNet | QNN_DLC | float | Qualcomm® SA7255P | 117.748 ms | 24 - 243 MB | NPU
107
+ | PidNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 18.382 ms | 24 - 269 MB | NPU
108
+ | PidNet | QNN_DLC | float | Qualcomm® SA8295P | 51.998 ms | 24 - 252 MB | NPU
109
+ | PidNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 18.382 ms | 24 - 269 MB | NPU
110
+ | PidNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 38.861 ms | 24 - 24 MB | NPU
111
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 25.263 ms | 6 - 6 MB | NPU
112
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 60.743 ms | 6 - 6 MB | NPU
113
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 43.015 ms | 6 - 266 MB | NPU
114
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 64.039 ms | 6 - 269 MB | NPU
115
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 111.433 ms | 6 - 219 MB | NPU
116
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 57.903 ms | 6 - 22 MB | NPU
117
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 58.485 ms | 6 - 219 MB | NPU
118
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® SA8650P | 58.485 ms | 6 - 219 MB | NPU
119
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® SA8255P | 58.485 ms | 6 - 219 MB | NPU
120
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 64.039 ms | 6 - 269 MB | NPU
121
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 43.85 ms | 6 - 241 MB | NPU
122
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 24.611 ms | 6 - 273 MB | NPU
123
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 59.208 ms | 6 - 14 MB | NPU
124
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 111.433 ms | 6 - 219 MB | NPU
125
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 66.492 ms | 6 - 223 MB | NPU
126
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 43.85 ms | 6 - 241 MB | NPU
127
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 60.743 ms | 6 - 6 MB | NPU
128
+ | PidNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 24.905 ms | 2 - 322 MB | NPU
129
+ | PidNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 74.351 ms | 0 - 328 MB | NPU
130
+ | PidNet | TFLITE | float | Qualcomm® QCS8275 | 368.384 ms | 3 - 31 MB | GPU
131
+ | PidNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 36.205 ms | 3 - 5 MB | NPU
132
+ | PidNet | TFLITE | float | Qualcomm® SA8775P | 45.287 ms | 2 - 233 MB | NPU
133
+ | PidNet | TFLITE | float | Qualcomm® SA8650P | 45.287 ms | 2 - 233 MB | NPU
134
+ | PidNet | TFLITE | float | Qualcomm® SA8255P | 45.287 ms | 2 - 233 MB | NPU
135
+ | PidNet | TFLITE | float | Qualcomm® QCS8450 | 74.351 ms | 0 - 328 MB | NPU
136
+ | PidNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 46.864 ms | 0 - 45 MB | NPU
137
+ | PidNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.771 ms | 2 - 272 MB | NPU
138
+ | PidNet | TFLITE | float | Qualcomm® SA7255P | 368.384 ms | 3 - 31 MB | GPU
139
+ | PidNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 18.848 ms | 0 - 249 MB | NPU
140
+ | PidNet | TFLITE | float | Qualcomm® SA8295P | 51.022 ms | 3 - 245 MB | NPU
141
+ | PidNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 18.848 ms | 0 - 249 MB | NPU
142
+ | PidNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 38.048 ms | 0 - 264 MB | NPU
143
+ | PidNet | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 58.373 ms | 1 - 266 MB | NPU
144
+ | PidNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 181.186 ms | 2 - 72 MB | NPU
145
+ | PidNet | TFLITE | w8a8 | Qualcomm® QCS8275 | 98.334 ms | 1 - 213 MB | NPU
146
+ | PidNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 50.324 ms | 0 - 3 MB | NPU
147
+ | PidNet | TFLITE | w8a8 | Qualcomm® SA8775P | 51.059 ms | 1 - 214 MB | NPU
148
+ | PidNet | TFLITE | w8a8 | Qualcomm® SA8650P | 51.059 ms | 1 - 214 MB | NPU
149
+ | PidNet | TFLITE | w8a8 | Qualcomm® SA8255P | 51.059 ms | 1 - 214 MB | NPU
150
+ | PidNet | TFLITE | w8a8 | Qualcomm® QCS8450 | 58.373 ms | 1 - 266 MB | NPU
151
+ | PidNet | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 69.465 ms | 1 - 239 MB | NPU
152
+ | PidNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 22.191 ms | 0 - 267 MB | NPU
153
+ | PidNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 55.201 ms | 0 - 17 MB | NPU
154
+ | PidNet | TFLITE | w8a8 | Qualcomm® SA7255P | 98.334 ms | 1 - 213 MB | NPU
155
+ | PidNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 66.722 ms | 4 - 222 MB | NPU
156
+ | PidNet | TFLITE | w8a8 | Qualcomm® SA8295P | 58.022 ms | 1 - 217 MB | NPU
157
+ | PidNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 239.746 ms | 2 - 234 MB | NPU
158
+ | PidNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 66.722 ms | 4 - 222 MB | NPU
159
+ | PidNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 69.465 ms | 1 - 239 MB | NPU
160
 
161
  ## License
162
  * The license for the original implementation of PidNet can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "w8a8": {
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/pidnet/releases/v0.57.3/pidnet-tflite-w8a8.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/pidnet/releases/v0.57.3/pidnet-qnn_dlc-w8a8.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/pidnet/releases/v0.57.3/pidnet-onnx-w8a8.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/pidnet/releases/v0.57.3/pidnet-tflite-float.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/pidnet/releases/v0.57.3/pidnet-qnn_dlc-float.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/pidnet/releases/v0.57.3/pidnet-onnx-float.zip"
49
  }
50
  }
51
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "w8a8": {
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/pidnet/releases/v0.58.0/pidnet-tflite-w8a8.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/pidnet/releases/v0.58.0/pidnet-qnn_dlc-w8a8.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/pidnet/releases/v0.58.0/pidnet-onnx-w8a8.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/pidnet/releases/v0.58.0/pidnet-tflite-float.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/pidnet/releases/v0.58.0/pidnet-qnn_dlc-float.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/pidnet/releases/v0.58.0/pidnet-onnx-float.zip"
49
  }
50
  }
51
  }