Hugging Face's logo

qualcomm
/
PidNet

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
72de392
·
verified ·
1 Parent(s): 279e908

v0.48.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

Files changed (1) hide show
  1. README.md +73 -73
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/quic/ai-hub-models/blob/main/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.47.0/pidnet-onnx-float.zip)
32
- | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.47.0/pidnet-onnx-w8a8.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.47.0/pidnet-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.47.0/pidnet-qnn_dlc-w8a8.zip)
35
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.47.0/pidnet-tflite-float.zip)
36
- | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.47.0/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/quic/ai-hub-models/blob/main/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/quic/ai-hub-models/blob/main/qai_hub_models/models/pidnet) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -65,70 +65,70 @@ See our repository for [PidNet on GitHub](https://github.com/quic/ai-hub-models/
65
  ## Performance Summary
66
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
67
  |---|---|---|---|---|---|---
68
- | PidNet | ONNX | float | Snapdragon® X Elite | 34.015 ms | 24 - 24 MB | NPU
69
- | PidNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 24.112 ms | 29 - 342 MB | NPU
70
- | PidNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 35.064 ms | 24 - 27 MB | NPU
71
- | PidNet | ONNX | float | Qualcomm® QCS9075 | 47.377 ms | 24 - 51 MB | NPU
72
- | PidNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 17.658 ms | 5 - 224 MB | NPU
73
- | PidNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 13.393 ms | 30 - 298 MB | NPU
74
- | PidNet | ONNX | float | Snapdragon® X2 Elite | 14.124 ms | 22 - 22 MB | NPU
75
- | PidNet | ONNX | w8a8 | Snapdragon® X Elite | 87.113 ms | 133 - 133 MB | NPU
76
- | PidNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 45.811 ms | 109 - 369 MB | NPU
77
- | PidNet | ONNX | w8a8 | Qualcomm® QCS6490 | 387.425 ms | 197 - 216 MB | CPU
78
- | PidNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 59.747 ms | 103 - 107 MB | NPU
79
- | PidNet | ONNX | w8a8 | Qualcomm® QCS9075 | 67.759 ms | 104 - 107 MB | NPU
80
- | PidNet | ONNX | w8a8 | Qualcomm® QCM6690 | 347.832 ms | 162 - 170 MB | CPU
81
- | PidNet | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 43.964 ms | 103 - 314 MB | NPU
82
- | PidNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 328.18 ms | 214 - 223 MB | CPU
83
- | PidNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 45.73 ms | 109 - 334 MB | NPU
84
- | PidNet | ONNX | w8a8 | Snapdragon® X2 Elite | 46.995 ms | 134 - 134 MB | NPU
85
- | PidNet | QNN_DLC | float | Snapdragon® X Elite | 40.278 ms | 24 - 24 MB | NPU
86
- | PidNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 27.05 ms | 23 - 340 MB | NPU
87
- | PidNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 121.017 ms | 24 - 244 MB | NPU
88
- | PidNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 39.08 ms | 24 - 305 MB | NPU
89
- | PidNet | QNN_DLC | float | Qualcomm® SA8775P | 48.162 ms | 24 - 244 MB | NPU
90
- | PidNet | QNN_DLC | float | Qualcomm® QCS9075 | 61.73 ms | 24 - 52 MB | NPU
91
- | PidNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 75.854 ms | 0 - 330 MB | NPU
92
- | PidNet | QNN_DLC | float | Qualcomm® SA7255P | 121.017 ms | 24 - 244 MB | NPU
93
- | PidNet | QNN_DLC | float | Qualcomm® SA8295P | 52.915 ms | 24 - 260 MB | NPU
94
- | PidNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 19.303 ms | 17 - 262 MB | NPU
95
- | PidNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.288 ms | 14 - 285 MB | NPU
96
- | PidNet | QNN_DLC | float | Snapdragon® X2 Elite | 13.939 ms | 24 - 24 MB | NPU
97
- | PidNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 60.437 ms | 6 - 6 MB | NPU
98
- | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 43.247 ms | 6 - 271 MB | NPU
99
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 111.149 ms | 6 - 217 MB | NPU
100
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 57.761 ms | 6 - 39 MB | NPU
101
- | PidNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 58.412 ms | 6 - 218 MB | NPU
102
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 61.598 ms | 6 - 14 MB | NPU
103
- | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 64.081 ms | 6 - 271 MB | NPU
104
- | PidNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 111.149 ms | 6 - 217 MB | NPU
105
- | PidNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 66.477 ms | 6 - 220 MB | NPU
106
- | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 41.449 ms | 6 - 242 MB | NPU
107
- | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 47.509 ms | 6 - 270 MB | NPU
108
- | PidNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 48.329 ms | 6 - 6 MB | NPU
109
- | PidNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 26.686 ms | 1 - 332 MB | NPU
110
- | PidNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 121.024 ms | 3 - 232 MB | NPU
111
- | PidNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 39.163 ms | 3 - 5 MB | NPU
112
- | PidNet | TFLITE | float | Qualcomm® SA8775P | 48.049 ms | 2 - 232 MB | NPU
113
- | PidNet | TFLITE | float | Qualcomm® QCS9075 | 61.728 ms | 0 - 45 MB | NPU
114
- | PidNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 76.279 ms | 2 - 341 MB | NPU
115
- | PidNet | TFLITE | float | Qualcomm® SA7255P | 121.024 ms | 3 - 232 MB | NPU
116
- | PidNet | TFLITE | float | Qualcomm® SA8295P | 52.947 ms | 2 - 244 MB | NPU
117
- | PidNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 19.493 ms | 1 - 254 MB | NPU
118
- | PidNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.243 ms | 2 - 276 MB | NPU
119
- | PidNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 38.024 ms | 1 - 267 MB | NPU
120
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS6490 | 206.162 ms | 3 - 73 MB | NPU
121
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 98.59 ms | 1 - 212 MB | NPU
122
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 50.375 ms | 1 - 3 MB | NPU
123
- | PidNet | TFLITE | w8a8 | Qualcomm® SA8775P | 242.178 ms | 0 - 212 MB | NPU
124
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS9075 | 53.962 ms | 1 - 17 MB | NPU
125
- | PidNet | TFLITE | w8a8 | Qualcomm® QCM6690 | 237.035 ms | 1 - 194 MB | NPU
126
- | PidNet | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 58.806 ms | 0 - 268 MB | NPU
127
- | PidNet | TFLITE | w8a8 | Qualcomm® SA7255P | 98.59 ms | 1 - 212 MB | NPU
128
- | PidNet | TFLITE | w8a8 | Qualcomm® SA8295P | 58.306 ms | 1 - 215 MB | NPU
129
- | PidNet | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 38.39 ms | 1 - 234 MB | NPU
130
- | PidNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 67.192 ms | 2 - 221 MB | NPU
131
- | PidNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 40.864 ms | 1 - 264 MB | NPU
132
 
133
  ## License
134
  * 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/main/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.48.0/pidnet-onnx-float.zip)
32
+ | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.48.0/pidnet-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.48.0/pidnet-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.48.0/pidnet-qnn_dlc-w8a8.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.48.0/pidnet-tflite-float.zip)
36
+ | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/pidnet/releases/v0.48.0/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/main/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/main/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 | 14.154 ms | 22 - 22 MB | NPU
69
+ | PidNet | ONNX | float | Snapdragon® X Elite | 34.21 ms | 24 - 24 MB | NPU
70
+ | PidNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 24.114 ms | 18 - 334 MB | NPU
71
+ | PidNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 34.459 ms | 24 - 27 MB | NPU
72
+ | PidNet | ONNX | float | Qualcomm® QCS9075 | 47.725 ms | 24 - 51 MB | NPU
73
+ | PidNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 17.416 ms | 6 - 225 MB | NPU
74
+ | PidNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 13.39 ms | 30 - 298 MB | NPU
75
+ | PidNet | ONNX | w8a8 | Snapdragon® X2 Elite | 45.505 ms | 134 - 134 MB | NPU
76
+ | PidNet | ONNX | w8a8 | Snapdragon® X Elite | 85.169 ms | 133 - 133 MB | NPU
77
+ | PidNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 45.893 ms | 109 - 371 MB | NPU
78
+ | PidNet | ONNX | w8a8 | Qualcomm® QCS6490 | 395.24 ms | 197 - 215 MB | CPU
79
+ | PidNet | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 60.084 ms | 101 - 107 MB | NPU
80
+ | PidNet | ONNX | w8a8 | Qualcomm® QCS9075 | 66.844 ms | 104 - 106 MB | NPU
81
+ | PidNet | ONNX | w8a8 | Qualcomm® QCM6690 | 348.38 ms | 198 - 208 MB | CPU
82
+ | PidNet | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 43.624 ms | 98 - 308 MB | NPU
83
+ | PidNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 327.876 ms | 211 - 222 MB | CPU
84
+ | PidNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 45.169 ms | 99 - 319 MB | NPU
85
+ | PidNet | QNN_DLC | float | Snapdragon® X2 Elite | 13.818 ms | 24 - 24 MB | NPU
86
+ | PidNet | QNN_DLC | float | Snapdragon® X Elite | 40.239 ms | 24 - 24 MB | NPU
87
+ | PidNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 26.914 ms | 24 - 343 MB | NPU
88
+ | PidNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 121.006 ms | 24 - 244 MB | NPU
89
+ | PidNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 38.712 ms | 24 - 36 MB | NPU
90
+ | PidNet | QNN_DLC | float | Qualcomm® SA8775P | 48.083 ms | 24 - 244 MB | NPU
91
+ | PidNet | QNN_DLC | float | Qualcomm® QCS9075 | 61.877 ms | 24 - 52 MB | NPU
92
+ | PidNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 76.2 ms | 5 - 336 MB | NPU
93
+ | PidNet | QNN_DLC | float | Qualcomm® SA7255P | 121.006 ms | 24 - 244 MB | NPU
94
+ | PidNet | QNN_DLC | float | Qualcomm® SA8295P | 52.875 ms | 24 - 261 MB | NPU
95
+ | PidNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 19.401 ms | 21 - 266 MB | NPU
96
+ | PidNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.273 ms | 10 - 281 MB | NPU
97
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 48.221 ms | 6 - 6 MB | NPU
98
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 60.443 ms | 6 - 6 MB | NPU
99
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 43.161 ms | 6 - 272 MB | NPU
100
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 111.117 ms | 6 - 217 MB | NPU
101
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 58.012 ms | 6 - 8 MB | NPU
102
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 58.495 ms | 6 - 218 MB | NPU
103
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 61.544 ms | 6 - 14 MB | NPU
104
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 64.308 ms | 6 - 271 MB | NPU
105
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 111.117 ms | 6 - 217 MB | NPU
106
+ | PidNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 66.512 ms | 6 - 220 MB | NPU
107
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 41.45 ms | 6 - 240 MB | NPU
108
+ | PidNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 47.754 ms | 6 - 271 MB | NPU
109
+ | PidNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 26.686 ms | 1 - 335 MB | NPU
110
+ | PidNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 121.027 ms | 2 - 232 MB | NPU
111
+ | PidNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 38.953 ms | 2 - 54 MB | NPU
112
+ | PidNet | TFLITE | float | Qualcomm® SA8775P | 48.051 ms | 2 - 233 MB | NPU
113
+ | PidNet | TFLITE | float | Qualcomm® QCS9075 | 62.137 ms | 0 - 45 MB | NPU
114
+ | PidNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 77.886 ms | 3 - 344 MB | NPU
115
+ | PidNet | TFLITE | float | Qualcomm® SA7255P | 121.027 ms | 2 - 232 MB | NPU
116
+ | PidNet | TFLITE | float | Qualcomm® SA8295P | 52.951 ms | 2 - 244 MB | NPU
117
+ | PidNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 19.491 ms | 2 - 251 MB | NPU
118
+ | PidNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.232 ms | 2 - 276 MB | NPU
119
+ | PidNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 37.912 ms | 1 - 270 MB | NPU
120
+ | PidNet | TFLITE | w8a8 | Qualcomm® QCS6490 | 206.978 ms | 3 - 73 MB | NPU
121
+ | PidNet | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 98.64 ms | 0 - 211 MB | NPU
122
+ | PidNet | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 50.438 ms | 0 - 167 MB | NPU
123
+ | PidNet | TFLITE | w8a8 | Qualcomm® SA8775P | 51.148 ms | 1 - 213 MB | NPU
124
+ | PidNet | TFLITE | w8a8 | Qualcomm® QCS9075 | 53.612 ms | 1 - 17 MB | NPU
125
+ | PidNet | TFLITE | w8a8 | Qualcomm® QCM6690 | 238.637 ms | 3 - 197 MB | NPU
126
+ | PidNet | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 58.989 ms | 1 - 267 MB | NPU
127
+ | PidNet | TFLITE | w8a8 | Qualcomm® SA7255P | 98.64 ms | 0 - 211 MB | NPU
128
+ | PidNet | TFLITE | w8a8 | Qualcomm® SA8295P | 58.249 ms | 1 - 215 MB | NPU
129
+ | PidNet | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 38.413 ms | 0 - 234 MB | NPU
130
+ | PidNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 66.975 ms | 2 - 221 MB | NPU
131
+ | PidNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 41.186 ms | 1 - 265 MB | NPU
132
 
133
  ## License
134
  * The license for the original implementation of PidNet can be found