Hugging Face's logo

qualcomm
/
FFNet-78S

Image Segmentation
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
00608cd
·
verified ·
1 Parent(s): 4970ac6

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +75 -76
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-segmentation
14
  FFNet-78S is a "fuss-free network" that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.
15
 
16
  This is based on the implementation of FFNet-78S found [here](https://github.com/Qualcomm-AI-research/FFNet).
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/main/qai_hub_models/models/ffnet_78s) 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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ffnet_78s/releases/v0.48.0/ffnet_78s-onnx-float.zip)
31
- | 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/ffnet_78s/releases/v0.48.0/ffnet_78s-onnx-w8a8.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ffnet_78s/releases/v0.48.0/ffnet_78s-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ffnet_78s/releases/v0.48.0/ffnet_78s-qnn_dlc-w8a8.zip)
34
- | 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/ffnet_78s/releases/v0.48.0/ffnet_78s-tflite-float.zip)
35
- | 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/ffnet_78s/releases/v0.48.0/ffnet_78s-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[FFNet-78S on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/ffnet_78s)**.
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/main/qai_hub_models/models/ffnet_78s) 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 [FFNet-78S on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/ffnet_78s) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -63,73 +63,72 @@ See our repository for [FFNet-78S on GitHub](https://github.com/qualcomm/ai-hub-
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | FFNet-78S | ONNX | float | Snapdragon® X2 Elite | 18.102 ms | 30 - 30 MB | NPU
67
- | FFNet-78S | ONNX | float | Snapdragon® X Elite | 37.773 ms | 30 - 30 MB | NPU
68
- | FFNet-78S | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 26.986 ms | 0 - 302 MB | NPU
69
- | FFNet-78S | ONNX | float | Qualcomm® QCS8550 (Proxy) | 38.05 ms | 24 - 27 MB | NPU
70
- | FFNet-78S | ONNX | float | Qualcomm® QCS9075 | 59.191 ms | 24 - 51 MB | NPU
71
- | FFNet-78S | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 20.318 ms | 5 - 214 MB | NPU
72
- | FFNet-78S | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.168 ms | 30 - 259 MB | NPU
73
- | FFNet-78S | ONNX | w8a8 | Snapdragon® X2 Elite | 7.934 ms | 22 - 22 MB | NPU
74
- | FFNet-78S | ONNX | w8a8 | Snapdragon® X Elite | 14.86 ms | 21 - 21 MB | NPU
75
- | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.575 ms | 7 - 297 MB | NPU
76
- | FFNet-78S | ONNX | w8a8 | Qualcomm® QCS6490 | 496.283 ms | 168 - 221 MB | CPU
77
- | FFNet-78S | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 15.576 ms | 0 - 24 MB | NPU
78
- | FFNet-78S | ONNX | w8a8 | Qualcomm® QCS9075 | 14.497 ms | 6 - 9 MB | NPU
79
- | FFNet-78S | ONNX | w8a8 | Qualcomm® QCM6690 | 536.759 ms | 136 - 146 MB | CPU
80
- | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 8.773 ms | 1 - 209 MB | NPU
81
- | FFNet-78S | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 534.017 ms | 145 - 156 MB | CPU
82
- | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.308 ms | 0 - 219 MB | NPU
83
- | FFNet-78S | QNN_DLC | float | Snapdragon® X2 Elite | 18.007 ms | 24 - 24 MB | NPU
84
- | FFNet-78S | QNN_DLC | float | Snapdragon® X Elite | 43.789 ms | 24 - 24 MB | NPU
85
- | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 29.414 ms | 76 - 389 MB | NPU
86
- | FFNet-78S | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 186.955 ms | 24 - 235 MB | NPU
87
- | FFNet-78S | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.249 ms | 24 - 28 MB | NPU
88
- | FFNet-78S | QNN_DLC | float | Qualcomm® SA8775P | 60.75 ms | 24 - 235 MB | NPU
89
- | FFNet-78S | QNN_DLC | float | Qualcomm® QCS9075 | 73.12 ms | 26 - 54 MB | NPU
90
- | FFNet-78S | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 84.436 ms | 3 - 298 MB | NPU
91
- | FFNet-78S | QNN_DLC | float | Qualcomm® SA7255P | 186.955 ms | 24 - 235 MB | NPU
92
- | FFNet-78S | QNN_DLC | float | Qualcomm® SA8295P | 66.023 ms | 24 - 230 MB | NPU
93
- | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 21.466 ms | 17 - 245 MB | NPU
94
- | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 15.524 ms | 8 - 258 MB | NPU
95
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 7.039 ms | 6 - 6 MB | NPU
96
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® X Elite | 17.701 ms | 6 - 6 MB | NPU
97
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.644 ms | 6 - 287 MB | NPU
98
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 72.774 ms | 5 - 13 MB | NPU
99
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 39.127 ms | 6 - 217 MB | NPU
100
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 16.72 ms | 6 - 42 MB | NPU
101
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8775P | 77.742 ms | 6 - 217 MB | NPU
102
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 20.341 ms | 6 - 14 MB | NPU
103
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 163.405 ms | 6 - 253 MB | NPU
104
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 24.122 ms | 6 - 285 MB | NPU
105
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA7255P | 39.127 ms | 6 - 217 MB | NPU
106
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8295P | 23.343 ms | 6 - 219 MB | NPU
107
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.936 ms | 6 - 234 MB | NPU
108
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 22.335 ms | 6 - 237 MB | NPU
109
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 5.885 ms | 6 - 256 MB | NPU
110
- | FFNet-78S | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 29.374 ms | 1 - 388 MB | NPU
111
- | FFNet-78S | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 186.875 ms | 0 - 245 MB | NPU
112
- | FFNet-78S | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 42.398 ms | 3 - 5 MB | NPU
113
- | FFNet-78S | TFLITE | float | Qualcomm® SA8775P | 60.867 ms | 2 - 247 MB | NPU
114
- | FFNet-78S | TFLITE | float | Qualcomm® QCS9075 | 72.983 ms | 0 - 82 MB | NPU
115
- | FFNet-78S | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 85.435 ms | 2 - 375 MB | NPU
116
- | FFNet-78S | TFLITE | float | Qualcomm® SA7255P | 186.875 ms | 0 - 245 MB | NPU
117
- | FFNet-78S | TFLITE | float | Qualcomm® SA8295P | 66.052 ms | 2 - 244 MB | NPU
118
- | FFNet-78S | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 21.647 ms | 0 - 259 MB | NPU
119
- | FFNet-78S | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 15.398 ms | 1 - 284 MB | NPU
120
- | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.451 ms | 1 - 285 MB | NPU
121
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS6490 | 57.155 ms | 1 - 36 MB | NPU
122
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 26.382 ms | 1 - 210 MB | NPU
123
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 9.074 ms | 1 - 3 MB | NPU
124
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8775P | 9.771 ms | 0 - 210 MB | NPU
125
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS9075 | 10.967 ms | 1 - 36 MB | NPU
126
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCM6690 | 138.255 ms | 1 - 246 MB | NPU
127
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 18.372 ms | 1 - 286 MB | NPU
128
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA7255P | 26.382 ms | 1 - 210 MB | NPU
129
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8295P | 14.992 ms | 1 - 214 MB | NPU
130
- | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 4.954 ms | 0 - 230 MB | NPU
131
- | FFNet-78S | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.678 ms | 0 - 230 MB | NPU
132
- | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.594 ms | 0 - 248 MB | NPU
133
 
134
  ## License
135
  * The license for the original implementation of FFNet-78S can be found
 
14
  FFNet-78S is a "fuss-free network" that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.
15
 
16
  This is based on the implementation of FFNet-78S found [here](https://github.com/Qualcomm-AI-research/FFNet).
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/tree/v0.49.1/qai_hub_models/models/ffnet_78s) 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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ffnet_78s/releases/v0.49.1/ffnet_78s-onnx-float.zip)
31
+ | 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/ffnet_78s/releases/v0.49.1/ffnet_78s-onnx-w8a8.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ffnet_78s/releases/v0.49.1/ffnet_78s-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ffnet_78s/releases/v0.49.1/ffnet_78s-qnn_dlc-w8a8.zip)
34
+ | 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/ffnet_78s/releases/v0.49.1/ffnet_78s-tflite-float.zip)
35
+ | 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/ffnet_78s/releases/v0.49.1/ffnet_78s-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[FFNet-78S on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/ffnet_78s)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/ffnet_78s) 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 [FFNet-78S on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/ffnet_78s) 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
+ | FFNet-78S | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.26 ms | 29 - 257 MB | NPU
67
+ | FFNet-78S | ONNX | float | Snapdragon® X2 Elite | 18.053 ms | 30 - 30 MB | NPU
68
+ | FFNet-78S | ONNX | float | Snapdragon® X Elite | 37.729 ms | 30 - 30 MB | NPU
69
+ | FFNet-78S | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 27.076 ms | 0 - 303 MB | NPU
70
+ | FFNet-78S | ONNX | float | Qualcomm® QCS8550 (Proxy) | 38.291 ms | 24 - 58 MB | NPU
71
+ | FFNet-78S | ONNX | float | Qualcomm® QCS9075 | 59.563 ms | 24 - 51 MB | NPU
72
+ | FFNet-78S | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 20.275 ms | 7 - 210 MB | NPU
73
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.298 ms | 0 - 219 MB | NPU
74
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® X2 Elite | 7.882 ms | 22 - 22 MB | NPU
75
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® X Elite | 14.824 ms | 21 - 21 MB | NPU
76
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.625 ms | 7 - 294 MB | NPU
77
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® QCS6490 | 487.641 ms | 162 - 216 MB | CPU
78
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 15.459 ms | 0 - 25 MB | NPU
79
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® QCS9075 | 14.549 ms | 6 - 9 MB | NPU
80
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® QCM6690 | 535.901 ms | 176 - 186 MB | CPU
81
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 8.771 ms | 1 - 212 MB | NPU
82
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 535.24 ms | 144 - 155 MB | CPU
83
+ | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 15.517 ms | 8 - 258 MB | NPU
84
+ | FFNet-78S | QNN_DLC | float | Snapdragon® X2 Elite | 48.916 ms | 24 - 24 MB | NPU
85
+ | FFNet-78S | QNN_DLC | float | Snapdragon® X Elite | 43.814 ms | 24 - 24 MB | NPU
86
+ | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 29.384 ms | 8 - 315 MB | NPU
87
+ | FFNet-78S | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 187.008 ms | 24 - 235 MB | NPU
88
+ | FFNet-78S | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.303 ms | 24 - 26 MB | NPU
89
+ | FFNet-78S | QNN_DLC | float | Qualcomm® SA8775P | 60.742 ms | 24 - 235 MB | NPU
90
+ | FFNet-78S | QNN_DLC | float | Qualcomm® QCS9075 | 72.995 ms | 24 - 52 MB | NPU
91
+ | FFNet-78S | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 83.966 ms | 2 - 295 MB | NPU
92
+ | FFNet-78S | QNN_DLC | float | Qualcomm® SA7255P | 187.008 ms | 24 - 235 MB | NPU
93
+ | FFNet-78S | QNN_DLC | float | Qualcomm® SA8295P | 65.995 ms | 24 - 229 MB | NPU
94
+ | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 21.718 ms | 16 - 244 MB | NPU
95
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 5.886 ms | 6 - 256 MB | NPU
96
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 7.029 ms | 6 - 6 MB | NPU
97
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® X Elite | 17.682 ms | 6 - 6 MB | NPU
98
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.636 ms | 6 - 287 MB | NPU
99
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 72.359 ms | 4 - 12 MB | NPU
100
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 39.144 ms | 6 - 217 MB | NPU
101
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 16.769 ms | 6 - 8 MB | NPU
102
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8775P | 17.199 ms | 6 - 218 MB | NPU
103
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 19.955 ms | 8 - 16 MB | NPU
104
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 142.792 ms | 6 - 254 MB | NPU
105
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 24.066 ms | 6 - 286 MB | NPU
106
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA7255P | 39.144 ms | 6 - 217 MB | NPU
107
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8295P | 23.34 ms | 6 - 220 MB | NPU
108
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.961 ms | 6 - 233 MB | NPU
109
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 22.418 ms | 6 - 237 MB | NPU
110
+ | FFNet-78S | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 15.385 ms | 1 - 286 MB | NPU
111
+ | FFNet-78S | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 29.497 ms | 2 - 394 MB | NPU
112
+ | FFNet-78S | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 186.902 ms | 3 - 248 MB | NPU
113
+ | FFNet-78S | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 42.742 ms | 2 - 5 MB | NPU
114
+ | FFNet-78S | TFLITE | float | Qualcomm® SA8775P | 60.834 ms | 0 - 245 MB | NPU
115
+ | FFNet-78S | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 86.014 ms | 0 - 371 MB | NPU
116
+ | FFNet-78S | TFLITE | float | Qualcomm® SA7255P | 186.902 ms | 3 - 248 MB | NPU
117
+ | FFNet-78S | TFLITE | float | Qualcomm® SA8295P | 66.02 ms | 2 - 244 MB | NPU
118
+ | FFNet-78S | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 21.58 ms | 1 - 264 MB | NPU
119
+ | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.603 ms | 1 - 249 MB | NPU
120
+ | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.441 ms | 0 - 285 MB | NPU
121
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS6490 | 57.031 ms | 1 - 36 MB | NPU
122
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 26.392 ms | 1 - 210 MB | NPU
123
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 9.049 ms | 0 - 2 MB | NPU
124
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8775P | 42.159 ms | 1 - 211 MB | NPU
125
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS9075 | 10.973 ms | 0 - 35 MB | NPU
126
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCM6690 | 124.774 ms | 1 - 248 MB | NPU
127
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 18.303 ms | 1 - 285 MB | NPU
128
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA7255P | 26.392 ms | 1 - 210 MB | NPU
129
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8295P | 14.994 ms | 1 - 214 MB | NPU
130
+ | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 4.958 ms | 0 - 229 MB | NPU
131
+ | FFNet-78S | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.611 ms | 0 - 230 MB | NPU
 
132
 
133
  ## License
134
  * The license for the original implementation of FFNet-78S can be found