Hugging Face's logo

qualcomm
/
FFNet-78S

Image Segmentation
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
e87441e
·
verified ·
1 Parent(s): 734a0da

v0.60.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.

Files changed (2) hide show
  1. README.md +111 -104
  2. release_assets.json +7 -7
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/v0.59.0/src/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
 
@@ -27,135 +27,142 @@ 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/ffnet_78s/releases/v0.59.0/ffnet_78s-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/ffnet_78s/releases/v0.59.0/ffnet_78s-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/ffnet_78s/releases/v0.59.0/ffnet_78s-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/ffnet_78s/releases/v0.59.0/ffnet_78s-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/ffnet_78s/releases/v0.59.0/ffnet_78s-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/ffnet_78s/releases/v0.59.0/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/v0.59.0/src/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/v0.59.0/src/qai_hub_models/models/ffnet_78s) for usage instructions.
50
 
51
  ## Model Details
52
 
53
  **Model Type:** Model_use_case.semantic_segmentation
54
 
55
  **Model Stats:**
56
- - Model checkpoint: ffnet78S_dBBB_cityscapes_state_dict_quarts
57
  - Input resolution: 2048x1024
58
- - Number of output classes: 19
59
- - Number of parameters: 27.5M
60
  - Model size (float): 105 MB
61
  - Model size (w8a8): 26.7 MB
 
 
62
 
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 | 18.528 ms | 24 - 24 MB | NPU
67
- | FFNet-78S | ONNX | float | Snapdragon® X Elite | 37.713 ms | 31 - 31 MB | NPU
68
- | FFNet-78S | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 27.589 ms | 19 - 332 MB | NPU
69
- | FFNet-78S | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 59.731 ms | 9 - 288 MB | NPU
70
- | FFNet-78S | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 38.389 ms | 24 - 395 MB | NPU
71
- | FFNet-78S | ONNX | float | Qualcomm® QCS8450 | 59.731 ms | 9 - 288 MB | NPU
72
- | FFNet-78S | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 56.807 ms | 24 - 51 MB | NPU
73
- | FFNet-78S | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 37.713 ms | 31 - 31 MB | NPU
74
- | FFNet-78S | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 21.667 ms | 7 - 204 MB | NPU
75
- | FFNet-78S | ONNX | float | Snapdragon® 8 Elite Mobile | 21.667 ms | 7 - 204 MB | NPU
76
- | FFNet-78S | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.722 ms | 5 - 228 MB | NPU
77
- | FFNet-78S | ONNX | w8a8 | Snapdragon® X2 Elite | 7.965 ms | 7 - 7 MB | NPU
78
- | FFNet-78S | ONNX | w8a8 | Snapdragon® X Elite | 13.545 ms | 22 - 22 MB | NPU
79
- | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.54 ms | 5 - 297 MB | NPU
80
- | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 17.858 ms | 7 - 301 MB | NPU
81
- | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 56.444 ms | 6 - 9 MB | NPU
82
- | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.808 ms | 0 - 23 MB | NPU
83
- | FFNet-78S | ONNX | w8a8 | Qualcomm® QCS8450 | 17.858 ms | 7 - 301 MB | NPU
84
- | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 19.088 ms | 6 - 9 MB | NPU
85
- | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 13.545 ms | 22 - 22 MB | NPU
86
- | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.737 ms | 1 - 215 MB | NPU
87
- | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 8.737 ms | 1 - 215 MB | NPU
88
- | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.414 ms | 2 - 219 MB | NPU
89
- | FFNet-78S | QNN_DLC | float | Snapdragon® X2 Elite | 17.988 ms | 24 - 24 MB | NPU
90
- | FFNet-78S | QNN_DLC | float | Snapdragon® X Elite | 44.547 ms | 24 - 24 MB | NPU
91
- | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 29.441 ms | 15 - 312 MB | NPU
92
- | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 85.623 ms | 6 - 290 MB | NPU
93
- | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 188.034 ms | 24 - 234 MB | NPU
94
- | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 42.686 ms | 24 - 26 MB | NPU
95
- | FFNet-78S | QNN_DLC | float | Qualcomm® SA8775P | 60.885 ms | 24 - 234 MB | NPU
96
- | FFNet-78S | QNN_DLC | float | Qualcomm® SA8650P | 60.885 ms | 24 - 234 MB | NPU
97
- | FFNet-78S | QNN_DLC | float | Qualcomm® SA8255P | 60.885 ms | 24 - 234 MB | NPU
98
- | FFNet-78S | QNN_DLC | float | Qualcomm® QCS8450 | 85.623 ms | 6 - 290 MB | NPU
99
- | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 66.625 ms | 24 - 52 MB | NPU
100
- | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 44.547 ms | 24 - 24 MB | NPU
101
- | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 21.86 ms | 15 - 242 MB | NPU
102
- | FFNet-78S | QNN_DLC | float | Qualcomm® SA7255P | 188.034 ms | 24 - 234 MB | NPU
103
- | FFNet-78S | QNN_DLC | float | Qualcomm® SA8295P | 66.414 ms | 24 - 229 MB | NPU
104
- | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 21.86 ms | 15 - 242 MB | NPU
105
- | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 15.697 ms | 14 - 266 MB | NPU
106
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 7.036 ms | 6 - 6 MB | NPU
107
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® X Elite | 17.7 ms | 6 - 6 MB | NPU
108
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.63 ms | 6 - 291 MB | NPU
109
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 23.66 ms | 6 - 293 MB | NPU
110
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 64.262 ms | 8 - 16 MB | NPU
111
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8275 | 39.091 ms | 6 - 225 MB | NPU
112
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 16.828 ms | 6 - 8 MB | NPU
113
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8775P | 17.18 ms | 6 - 225 MB | NPU
114
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8650P | 17.18 ms | 6 - 225 MB | NPU
115
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8255P | 17.18 ms | 6 - 225 MB | NPU
116
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 23.66 ms | 6 - 293 MB | NPU
117
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 17.637 ms | 6 - 14 MB | NPU
118
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 17.7 ms | 6 - 6 MB | NPU
119
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 162.0 ms | 6 - 254 MB | NPU
120
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 22.675 ms | 6 - 242 MB | NPU
121
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.06 ms | 6 - 238 MB | NPU
122
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA7255P | 39.091 ms | 6 - 225 MB | NPU
123
- | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8295P | 23.307 ms | 6 - 227 MB | NPU
124
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 8.06 ms | 6 - 238 MB | NPU
 
 
 
 
 
 
125
  | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 5.967 ms | 6 - 251 MB | NPU
126
- | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 22.675 ms | 6 - 242 MB | NPU
127
- | FFNet-78S | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 29.256 ms | 1 - 377 MB | NPU
128
- | FFNet-78S | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 86.333 ms | 3 - 363 MB | NPU
129
- | FFNet-78S | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 188.019 ms | 3 - 245 MB | NPU
130
- | FFNet-78S | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 43.073 ms | 2 - 5 MB | NPU
131
- | FFNet-78S | TFLITE | float | Qualcomm® SA8775P | 60.981 ms | 3 - 246 MB | NPU
132
- | FFNet-78S | TFLITE | float | Qualcomm® SA8650P | 60.981 ms | 3 - 246 MB | NPU
133
- | FFNet-78S | TFLITE | float | Qualcomm® SA8255P | 60.981 ms | 3 - 246 MB | NPU
134
- | FFNet-78S | TFLITE | float | Qualcomm® QCS8450 | 86.333 ms | 3 - 363 MB | NPU
135
- | FFNet-78S | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 61.731 ms | 0 - 82 MB | NPU
136
- | FFNet-78S | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 21.712 ms | 2 - 263 MB | NPU
137
- | FFNet-78S | TFLITE | float | Qualcomm® SA7255P | 188.019 ms | 3 - 245 MB | NPU
138
- | FFNet-78S | TFLITE | float | Qualcomm® SA8295P | 66.419 ms | 3 - 240 MB | NPU
139
- | FFNet-78S | TFLITE | float | Snapdragon® 8 Elite Mobile | 21.712 ms | 2 - 263 MB | NPU
140
- | FFNet-78S | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 15.458 ms | 2 - 284 MB | NPU
141
- | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.443 ms | 1 - 288 MB | NPU
142
- | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 18.231 ms | 1 - 290 MB | NPU
143
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 49.884 ms | 1 - 36 MB | NPU
144
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8275 | 26.23 ms | 1 - 218 MB | NPU
145
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.053 ms | 1 - 3 MB | NPU
146
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8775P | 9.747 ms | 1 - 219 MB | NPU
147
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8650P | 9.747 ms | 1 - 219 MB | NPU
148
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8255P | 9.747 ms | 1 - 219 MB | NPU
149
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS8450 | 18.231 ms | 1 - 290 MB | NPU
150
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 9.478 ms | 0 - 36 MB | NPU
151
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 138.117 ms | 0 - 246 MB | NPU
152
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 14.527 ms | 1 - 235 MB | NPU
153
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 5.028 ms | 1 - 231 MB | NPU
154
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA7255P | 26.23 ms | 1 - 218 MB | NPU
155
- | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8295P | 14.885 ms | 1 - 223 MB | NPU
156
- | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 5.028 ms | 1 - 231 MB | NPU
157
- | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.657 ms | 1 - 244 MB | NPU
158
- | FFNet-78S | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.527 ms | 1 - 235 MB | NPU
 
159
 
160
  ## License
161
  * 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/blob/v0.60.0/src/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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/ffnet_78s/releases/v0.60.0/ffnet_78s-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/ffnet_78s/releases/v0.60.0/ffnet_78s-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/ffnet_78s/releases/v0.60.0/ffnet_78s-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/ffnet_78s/releases/v0.60.0/ffnet_78s-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/ffnet_78s/releases/v0.60.0/ffnet_78s-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/ffnet_78s/releases/v0.60.0/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/v0.60.0/src/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/v0.60.0/src/qai_hub_models/models/ffnet_78s) for usage instructions.
50
 
51
  ## Model Details
52
 
53
  **Model Type:** Model_use_case.semantic_segmentation
54
 
55
  **Model Stats:**
 
56
  - Input resolution: 2048x1024
57
+ - Model checkpoint: ffnet78S_dBBB_cityscapes_state_dict_quarts
 
58
  - Model size (float): 105 MB
59
  - Model size (w8a8): 26.7 MB
60
+ - Number of output classes: 19
61
+ - Number of parameters: 27.5M
62
 
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 | 18.406 ms | 24 - 24 MB | NPU
67
+ | FFNet-78S | ONNX | float | Snapdragon® X Elite | 37.496 ms | 31 - 31 MB | NPU
68
+ | FFNet-78S | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 27.346 ms | 0 - 316 MB | NPU
69
+ | FFNet-78S | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 60.18 ms | 13 - 296 MB | NPU
70
+ | FFNet-78S | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 58.076 ms | 24 - 51 MB | NPU
71
+ | FFNet-78S | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 38.642 ms | 24 - 54 MB | NPU
72
+ | FFNet-78S | ONNX | float | Qualcomm® QCS8450 | 60.18 ms | 13 - 296 MB | NPU
73
+ | FFNet-78S | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 61.637 ms | 24 - 51 MB | NPU
74
+ | FFNet-78S | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 37.496 ms | 31 - 31 MB | NPU
75
+ | FFNet-78S | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 21.651 ms | 8 - 207 MB | NPU
76
+ | FFNet-78S | ONNX | float | Snapdragon® 8 Elite Mobile | 21.651 ms | 8 - 207 MB | NPU
77
+ | FFNet-78S | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.798 ms | 6 - 229 MB | NPU
78
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® X2 Elite | 9.31 ms | 7 - 7 MB | NPU
79
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® X Elite | 13.6 ms | 22 - 22 MB | NPU
80
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.551 ms | 7 - 301 MB | NPU
81
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 17.807 ms | 8 - 301 MB | NPU
82
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 57.086 ms | 6 - 9 MB | NPU
83
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 12.802 ms | 6 - 10 MB | NPU
84
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.838 ms | 0 - 24 MB | NPU
85
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® QCS8450 | 17.807 ms | 8 - 301 MB | NPU
86
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 13.501 ms | 6 - 9 MB | NPU
87
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 13.6 ms | 22 - 22 MB | NPU
88
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 150.009 ms | 6 - 237 MB | NPU
89
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 17.779 ms | 7 - 257 MB | NPU
90
+ | FFNet-78S | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.741 ms | 1 - 216 MB | NPU
91
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 8.741 ms | 1 - 216 MB | NPU
92
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.413 ms | 2 - 219 MB | NPU
93
+ | FFNet-78S | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 17.779 ms | 7 - 257 MB | NPU
94
+ | FFNet-78S | QNN_DLC | float | Snapdragon® X2 Elite | 17.97 ms | 24 - 24 MB | NPU
95
+ | FFNet-78S | QNN_DLC | float | Snapdragon® X Elite | 44.558 ms | 24 - 24 MB | NPU
96
+ | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 29.695 ms | 19 - 315 MB | NPU
97
+ | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 85.9 ms | 5 - 286 MB | NPU
98
+ | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 62.48 ms | 24 - 53 MB | NPU
99
+ | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 187.969 ms | 24 - 234 MB | NPU
100
+ | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 42.756 ms | 24 - 35 MB | NPU
101
+ | FFNet-78S | QNN_DLC | float | Qualcomm® SA8775P | 60.877 ms | 24 - 234 MB | NPU
102
+ | FFNet-78S | QNN_DLC | float | Qualcomm® SA8650P | 60.877 ms | 24 - 234 MB | NPU
103
+ | FFNet-78S | QNN_DLC | float | Qualcomm® SA8255P | 60.877 ms | 24 - 234 MB | NPU
104
+ | FFNet-78S | QNN_DLC | float | Qualcomm® QCS8450 | 85.9 ms | 5 - 286 MB | NPU
105
+ | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 61.367 ms | 24 - 52 MB | NPU
106
+ | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 44.558 ms | 24 - 24 MB | NPU
107
+ | FFNet-78S | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 21.74 ms | 12 - 238 MB | NPU
108
+ | FFNet-78S | QNN_DLC | float | Qualcomm® SA7255P | 187.969 ms | 24 - 234 MB | NPU
109
+ | FFNet-78S | QNN_DLC | float | Qualcomm® SA8295P | 66.507 ms | 24 - 228 MB | NPU
110
+ | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 21.74 ms | 12 - 238 MB | NPU
111
+ | FFNet-78S | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 15.635 ms | 14 - 267 MB | NPU
112
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 6.977 ms | 6 - 6 MB | NPU
113
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® X Elite | 17.785 ms | 6 - 6 MB | NPU
114
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 11.613 ms | 6 - 290 MB | NPU
115
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 23.625 ms | 6 - 292 MB | NPU
116
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 63.946 ms | 3 - 12 MB | NPU
117
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 39.091 ms | 6 - 226 MB | NPU
118
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 16.776 ms | 6 - 8 MB | NPU
119
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8775P | 17.186 ms | 6 - 226 MB | NPU
120
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8650P | 17.186 ms | 6 - 226 MB | NPU
121
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8255P | 17.186 ms | 6 - 226 MB | NPU
122
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 23.625 ms | 6 - 292 MB | NPU
123
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 17.446 ms | 8 - 16 MB | NPU
124
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 17.785 ms | 6 - 6 MB | NPU
125
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 166.357 ms | 6 - 256 MB | NPU
126
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 22.32 ms | 6 - 243 MB | NPU
127
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 8.055 ms | 0 - 231 MB | NPU
128
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA7255P | 39.091 ms | 6 - 226 MB | NPU
129
+ | FFNet-78S | QNN_DLC | w8a8 | Qualcomm® SA8295P | 23.333 ms | 6 - 227 MB | NPU
130
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 8.055 ms | 0 - 231 MB | NPU
131
  | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 5.967 ms | 6 - 251 MB | NPU
132
+ | FFNet-78S | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 22.32 ms | 6 - 243 MB | NPU
133
+ | FFNet-78S | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 29.431 ms | 1 - 377 MB | NPU
134
+ | FFNet-78S | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 86.118 ms | 3 - 363 MB | NPU
135
+ | FFNet-78S | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 62.554 ms | 0 - 83 MB | NPU
136
+ | FFNet-78S | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 188.047 ms | 3 - 245 MB | NPU
137
+ | FFNet-78S | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 42.889 ms | 3 - 5 MB | NPU
138
+ | FFNet-78S | TFLITE | float | Qualcomm® SA8775P | 60.992 ms | 3 - 245 MB | NPU
139
+ | FFNet-78S | TFLITE | float | Qualcomm® SA8650P | 60.992 ms | 3 - 245 MB | NPU
140
+ | FFNet-78S | TFLITE | float | Qualcomm® SA8255P | 60.992 ms | 3 - 245 MB | NPU
141
+ | FFNet-78S | TFLITE | float | Qualcomm® QCS8450 | 86.118 ms | 3 - 363 MB | NPU
142
+ | FFNet-78S | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 67.349 ms | 0 - 82 MB | NPU
143
+ | FFNet-78S | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 21.727 ms | 2 - 258 MB | NPU
144
+ | FFNet-78S | TFLITE | float | Qualcomm® SA7255P | 188.047 ms | 3 - 245 MB | NPU
145
+ | FFNet-78S | TFLITE | float | Qualcomm® SA8295P | 66.385 ms | 3 - 239 MB | NPU
146
+ | FFNet-78S | TFLITE | float | Snapdragon® 8 Elite Mobile | 21.727 ms | 2 - 258 MB | NPU
147
+ | FFNet-78S | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 15.675 ms | 0 - 281 MB | NPU
148
+ | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.43 ms | 1 - 287 MB | NPU
149
+ | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 18.283 ms | 1 - 291 MB | NPU
150
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 49.896 ms | 1 - 36 MB | NPU
151
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 9.77 ms | 1 - 37 MB | NPU
152
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 26.206 ms | 1 - 218 MB | NPU
153
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.063 ms | 1 - 3 MB | NPU
154
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8775P | 9.739 ms | 1 - 219 MB | NPU
155
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8650P | 9.739 ms | 1 - 219 MB | NPU
156
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA8255P | 9.739 ms | 1 - 219 MB | NPU
157
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® QCS8450 | 18.283 ms | 1 - 291 MB | NPU
158
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 9.462 ms | 1 - 36 MB | NPU
159
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 139.928 ms | 1 - 246 MB | NPU
160
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 14.724 ms | 1 - 234 MB | NPU
161
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 5.036 ms | 1 - 231 MB | NPU
162
+ | FFNet-78S | TFLITE | w8a8 | Qualcomm® SA7255P | 26.206 ms | 1 - 218 MB | NPU
163
+ | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 5.036 ms | 1 - 231 MB | NPU
164
+ | FFNet-78S | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.654 ms | 1 - 243 MB | NPU
165
+ | FFNet-78S | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.724 ms | 1 - 234 MB | NPU
166
 
167
  ## License
168
  * The license for the original implementation of FFNet-78S can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.59.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
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/ffnet_78s/releases/v0.59.0/ffnet_78s-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/ffnet_78s/releases/v0.59.0/ffnet_78s-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/ffnet_78s/releases/v0.59.0/ffnet_78s-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,19 +31,19 @@
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/ffnet_78s/releases/v0.59.0/ffnet_78s-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/ffnet_78s/releases/v0.59.0/ffnet_78s-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/ffnet_78s/releases/v0.59.0/ffnet_78s-tflite-w8a8.zip"
47
  }
48
  }
49
  }
 
1
  {
2
+ "version": "0.60.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
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/ffnet_78s/releases/v0.60.0/ffnet_78s-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/ffnet_78s/releases/v0.60.0/ffnet_78s-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/ffnet_78s/releases/v0.60.0/ffnet_78s-tflite-float.zip"
24
  }
25
  }
26
  },
 
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/ffnet_78s/releases/v0.60.0/ffnet_78s-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/ffnet_78s/releases/v0.60.0/ffnet_78s-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/ffnet_78s/releases/v0.60.0/ffnet_78s-tflite-w8a8.zip"
47
  }
48
  }
49
  }