Hugging Face's logo

qualcomm
/
ResNet-3D

Video Classification
PyTorch
backbone
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
06432cb
·
verified ·
1 Parent(s): ba0e691

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 +103 -95
  2. release_assets.json +7 -7
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: video-classification
15
  ResNet 3D is a network with 3D convolutions used for video understanding.
16
 
17
  This is based on the implementation of ResNet-3D found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.py).
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/resnet_3d) 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/resnet_3d/releases/v0.57.3/resnet_3d-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/resnet_3d/releases/v0.57.3/resnet_3d-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/resnet_3d/releases/v0.57.3/resnet_3d-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/resnet_3d/releases/v0.57.3/resnet_3d-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/resnet_3d/releases/v0.57.3/resnet_3d-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/resnet_3d/releases/v0.57.3/resnet_3d-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[ResNet-3D on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet_3d)**.
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/resnet_3d) 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 [ResNet-3D on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/resnet_3d) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,92 +63,100 @@ See our repository for [ResNet-3D 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
- | ResNet-3D | ONNX | float | Snapdragon® X2 Elite | 35.767 ms | 201 - 201 MB | NPU
67
- | ResNet-3D | ONNX | float | Snapdragon® X Elite | 67.533 ms | 171 - 171 MB | NPU
68
- | ResNet-3D | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 50.354 ms | 12 - 584 MB | NPU
69
- | ResNet-3D | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 134.238 ms | 12 - 490 MB | NPU
70
- | ResNet-3D | ONNX | float | Qualcomm® QCS8550 (Proxy) | 67.28 ms | 12 - 16 MB | NPU
71
- | ResNet-3D | ONNX | float | Qualcomm® QCS8450 | 134.238 ms | 12 - 490 MB | NPU
72
- | ResNet-3D | ONNX | float | Snapdragon® 8 Elite Mobile | 41.575 ms | 1 - 388 MB | NPU
73
- | ResNet-3D | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 29.505 ms | 1 - 403 MB | NPU
74
- | ResNet-3D | ONNX | float | Qualcomm® QCS9075 | 128.384 ms | 11 - 68 MB | NPU
75
- | ResNet-3D | ONNX | float | Qualcomm® QCS8750 | 41.575 ms | 1 - 388 MB | NPU
76
- | ResNet-3D | ONNX | float | Qualcomm® QCS7181 | 67.533 ms | 171 - 171 MB | NPU
77
- | ResNet-3D | ONNX | w8a8 | Snapdragon® X2 Elite | 11.525 ms | 210 - 210 MB | NPU
78
- | ResNet-3D | ONNX | w8a8 | Snapdragon® X Elite | 22.567 ms | 180 - 180 MB | NPU
79
- | ResNet-3D | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 16.827 ms | 3 - 406 MB | NPU
80
- | ResNet-3D | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 37.595 ms | 3 - 410 MB | NPU
81
- | ResNet-3D | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 22.277 ms | 3 - 7 MB | NPU
82
- | ResNet-3D | ONNX | w8a8 | Qualcomm® QCS8450 | 37.595 ms | 3 - 410 MB | NPU
83
- | ResNet-3D | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 9.977 ms | 0 - 293 MB | NPU
84
- | ResNet-3D | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 42.401 ms | 3 - 291 MB | NPU
85
- | ResNet-3D | ONNX | w8a8 | Qualcomm® QCS9075 | 22.06 ms | 3 - 48 MB | NPU
86
- | ResNet-3D | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 15.002 ms | 0 - 291 MB | NPU
87
- | ResNet-3D | ONNX | w8a8 | Qualcomm® QCS7790 | 42.401 ms | 3 - 291 MB | NPU
88
- | ResNet-3D | ONNX | w8a8 | Qualcomm® QCS8750 | 15.002 ms | 0 - 291 MB | NPU
89
- | ResNet-3D | ONNX | w8a8 | Qualcomm® QCS7181 | 22.567 ms | 180 - 180 MB | NPU
90
- | ResNet-3D | QNN_DLC | float | Snapdragon® X2 Elite | 36.369 ms | 12 - 12 MB | NPU
91
- | ResNet-3D | QNN_DLC | float | Snapdragon® X Elite | 70.634 ms | 12 - 12 MB | NPU
92
- | ResNet-3D | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 51.477 ms | 12 - 602 MB | NPU
93
- | ResNet-3D | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 134.622 ms | 7 - 500 MB | NPU
94
- | ResNet-3D | QNN_DLC | float | Qualcomm® QCS8275 | 467.796 ms | 1 - 395 MB | NPU
95
- | ResNet-3D | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 69.052 ms | 12 - 15 MB | NPU
96
- | ResNet-3D | QNN_DLC | float | Qualcomm® QCS8450 | 134.622 ms | 7 - 500 MB | NPU
97
- | ResNet-3D | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 41.726 ms | 11 - 400 MB | NPU
98
- | ResNet-3D | QNN_DLC | float | Qualcomm® SA8295P | 133.012 ms | 0 - 317 MB | NPU
99
- | ResNet-3D | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 29.444 ms | 12 - 406 MB | NPU
100
- | ResNet-3D | QNN_DLC | float | Qualcomm® SA7255P | 467.796 ms | 1 - 395 MB | NPU
101
- | ResNet-3D | QNN_DLC | float | Qualcomm® QCS9075 | 130.694 ms | 12 - 25 MB | NPU
102
- | ResNet-3D | QNN_DLC | float | Qualcomm® QCS8750 | 41.726 ms | 11 - 400 MB | NPU
103
- | ResNet-3D | QNN_DLC | float | Qualcomm® QCS7181 | 70.634 ms | 12 - 12 MB | NPU
104
- | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 12.349 ms | 3 - 3 MB | NPU
105
- | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® X Elite | 23.392 ms | 3 - 3 MB | NPU
106
- | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 17.043 ms | 3 - 409 MB | NPU
107
- | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 36.78 ms | 3 - 412 MB | NPU
108
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 102.317 ms | 2 - 7 MB | NPU
109
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 75.894 ms | 3 - 284 MB | NPU
110
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 21.484 ms | 3 - 5 MB | NPU
111
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 36.78 ms | 3 - 412 MB | NPU
112
- | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 10.65 ms | 3 - 298 MB | NPU
113
- | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 43.178 ms | 3 - 302 MB | NPU
114
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 22.559 ms | 5 - 9 MB | NPU
115
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® SA7255P | 75.894 ms | 3 - 284 MB | NPU
116
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 450.668 ms | 46 - 402 MB | NPU
117
- | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 15.271 ms | 3 - 291 MB | NPU
118
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® SA8295P | 39.848 ms | 0 - 281 MB | NPU
119
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 43.178 ms | 3 - 302 MB | NPU
120
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 15.271 ms | 3 - 291 MB | NPU
121
- | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 23.392 ms | 3 - 3 MB | NPU
122
- | ResNet-3D | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1144.915 ms | 0 - 640 MB | NPU
123
- | ResNet-3D | TFLITE | float | Qualcomm® QCS8275 | 2783.244 ms | 1 - 456 MB | NPU
124
- | ResNet-3D | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1429.804 ms | 0 - 3 MB | NPU
125
- | ResNet-3D | TFLITE | float | Qualcomm® SA8775P | 188084.492 ms | 910 - 926 MB | CPU
126
- | ResNet-3D | TFLITE | float | Qualcomm® SA8650P | 188084.492 ms | 910 - 926 MB | CPU
127
- | ResNet-3D | TFLITE | float | Qualcomm® SA8255P | 188084.492 ms | 910 - 926 MB | CPU
128
- | ResNet-3D | TFLITE | float | Snapdragon® 8 Elite Mobile | 1009.106 ms | 1 - 467 MB | NPU
129
- | ResNet-3D | TFLITE | float | Qualcomm® SA8295P | 1728.57 ms | 1 - 456 MB | NPU
130
- | ResNet-3D | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 887.207 ms | 0 - 471 MB | NPU
131
- | ResNet-3D | TFLITE | float | Qualcomm® SA7255P | 2783.244 ms | 1 - 456 MB | NPU
132
- | ResNet-3D | TFLITE | float | Qualcomm® QCS9075 | 1457.644 ms | 0 - 82 MB | NPU
133
- | ResNet-3D | TFLITE | float | Qualcomm® QCS8750 | 1009.106 ms | 1 - 467 MB | NPU
134
- | ResNet-3D | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 950.777 ms | 0 - 1007 MB | NPU
135
- | ResNet-3D | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1414.799 ms | 1 - 869 MB | NPU
136
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCS6490 | 9566.046 ms | 3462 - 5277 MB | NPU
137
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCS8275 | 2556.985 ms | 1 - 819 MB | NPU
138
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1255.964 ms | 0 - 3 MB | NPU
139
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA8775P | 191859.909 ms | 918 - 934 MB | CPU
140
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA8650P | 191859.909 ms | 918 - 934 MB | CPU
141
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA8255P | 191859.909 ms | 918 - 934 MB | CPU
142
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCS8450 | 1414.799 ms | 1 - 869 MB | NPU
143
- | ResNet-3D | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 817.083 ms | 0 - 928 MB | NPU
144
- | ResNet-3D | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 343740.245 ms | 919 - 1201 MB | NPU
145
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCS9075 | 1116.476 ms | 0 - 74 MB | NPU
146
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA7255P | 2556.985 ms | 1 - 819 MB | NPU
147
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCM6690 | 386810.527 ms | 905 - 1116 MB | NPU
148
- | ResNet-3D | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 656.895 ms | 0 - 729 MB | NPU
149
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA8295P | 1342.31 ms | 0 - 685 MB | NPU
150
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCS7790 | 343740.245 ms | 919 - 1201 MB | NPU
151
- | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCS8750 | 656.895 ms | 0 - 729 MB | NPU
 
 
 
 
 
 
 
 
152
 
153
  ## License
154
  * The license for the original implementation of ResNet-3D can be found
 
15
  ResNet 3D is a network with 3D convolutions used for video understanding.
16
 
17
  This is based on the implementation of ResNet-3D found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.py).
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/resnet_3d) 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/resnet_3d/releases/v0.58.0/resnet_3d-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/resnet_3d/releases/v0.58.0/resnet_3d-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/resnet_3d/releases/v0.58.0/resnet_3d-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/resnet_3d/releases/v0.58.0/resnet_3d-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/resnet_3d/releases/v0.58.0/resnet_3d-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/resnet_3d/releases/v0.58.0/resnet_3d-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[ResNet-3D on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet_3d)**.
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/resnet_3d) 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 [ResNet-3D on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/resnet_3d) for usage instructions.
51
 
52
  ## Model Details
53
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | ResNet-3D | ONNX | float | Snapdragon® X2 Elite | 35.857 ms | 12 - 12 MB | NPU
67
+ | ResNet-3D | ONNX | float | Snapdragon® X Elite | 67.783 ms | 58 - 58 MB | NPU
68
+ | ResNet-3D | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 50.647 ms | 12 - 596 MB | NPU
69
+ | ResNet-3D | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 133.711 ms | 1 - 488 MB | NPU
70
+ | ResNet-3D | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 67.483 ms | 0 - 70 MB | NPU
71
+ | ResNet-3D | ONNX | float | Qualcomm® QCS8450 | 133.711 ms | 1 - 488 MB | NPU
72
+ | ResNet-3D | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 123.178 ms | 11 - 26 MB | NPU
73
+ | ResNet-3D | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 30.098 ms | 1 - 407 MB | NPU
74
+ | ResNet-3D | ONNX | float | Snapdragon® 8 Elite Mobile | 41.705 ms | 1 - 390 MB | NPU
75
+ | ResNet-3D | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 41.705 ms | 1 - 390 MB | NPU
76
+ | ResNet-3D | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 67.783 ms | 58 - 58 MB | NPU
77
+ | ResNet-3D | ONNX | w8a8 | Snapdragon® X2 Elite | 11.557 ms | 3 - 3 MB | NPU
78
+ | ResNet-3D | ONNX | w8a8 | Snapdragon® X Elite | 22.419 ms | 32 - 32 MB | NPU
79
+ | ResNet-3D | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 16.84 ms | 0 - 413 MB | NPU
80
+ | ResNet-3D | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 36.196 ms | 0 - 417 MB | NPU
81
+ | ResNet-3D | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 22.193 ms | 0 - 40 MB | NPU
82
+ | ResNet-3D | ONNX | w8a8 | Qualcomm® QCS8450 | 36.196 ms | 0 - 417 MB | NPU
83
+ | ResNet-3D | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 15.039 ms | 0 - 293 MB | NPU
84
+ | ResNet-3D | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 42.16 ms | 3 - 295 MB | NPU
85
+ | ResNet-3D | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 9.996 ms | 2 - 300 MB | NPU
86
+ | ResNet-3D | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 21.313 ms | 0 - 6 MB | NPU
87
+ | ResNet-3D | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 42.16 ms | 3 - 295 MB | NPU
88
+ | ResNet-3D | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 15.039 ms | 0 - 293 MB | NPU
89
+ | ResNet-3D | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 22.419 ms | 32 - 32 MB | NPU
90
+ | ResNet-3D | QNN_DLC | float | Snapdragon® X2 Elite | 36.361 ms | 12 - 12 MB | NPU
91
+ | ResNet-3D | QNN_DLC | float | Snapdragon® X Elite | 70.616 ms | 12 - 12 MB | NPU
92
+ | ResNet-3D | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 50.936 ms | 12 - 600 MB | NPU
93
+ | ResNet-3D | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 134.755 ms | 7 - 501 MB | NPU
94
+ | ResNet-3D | QNN_DLC | float | Qualcomm® QCS8275 | 467.719 ms | 0 - 396 MB | NPU
95
+ | ResNet-3D | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 69.081 ms | 12 - 48 MB | NPU
96
+ | ResNet-3D | QNN_DLC | float | Qualcomm® SA8775P | 123.936 ms | 1 - 395 MB | NPU
97
+ | ResNet-3D | QNN_DLC | float | Qualcomm® SA8650P | 123.936 ms | 1 - 395 MB | NPU
98
+ | ResNet-3D | QNN_DLC | float | Qualcomm® SA8255P | 123.936 ms | 1 - 395 MB | NPU
99
+ | ResNet-3D | QNN_DLC | float | Qualcomm® QCS8450 | 134.755 ms | 7 - 501 MB | NPU
100
+ | ResNet-3D | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 123.805 ms | 13 - 27 MB | NPU
101
+ | ResNet-3D | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 30.011 ms | 12 - 406 MB | NPU
102
+ | ResNet-3D | QNN_DLC | float | Qualcomm® SA7255P | 467.719 ms | 0 - 396 MB | NPU
103
+ | ResNet-3D | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 41.732 ms | 12 - 401 MB | NPU
104
+ | ResNet-3D | QNN_DLC | float | Qualcomm® SA8295P | 133.038 ms | 0 - 317 MB | NPU
105
+ | ResNet-3D | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 41.732 ms | 12 - 401 MB | NPU
106
+ | ResNet-3D | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 70.616 ms | 12 - 12 MB | NPU
107
+ | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 12.375 ms | 3 - 3 MB | NPU
108
+ | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® X Elite | 23.398 ms | 3 - 3 MB | NPU
109
+ | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 17.098 ms | 3 - 411 MB | NPU
110
+ | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 38.046 ms | 3 - 413 MB | NPU
111
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 137.01 ms | 3 - 7 MB | NPU
112
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 75.863 ms | 3 - 284 MB | NPU
113
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 22.729 ms | 3 - 5 MB | NPU
114
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® SA8775P | 21.813 ms | 3 - 284 MB | NPU
115
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® SA8650P | 21.813 ms | 3 - 284 MB | NPU
116
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® SA8255P | 21.813 ms | 3 - 284 MB | NPU
117
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 38.046 ms | 3 - 413 MB | NPU
118
+ | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 15.452 ms | 3 - 292 MB | NPU
119
+ | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 43.297 ms | 3 - 300 MB | NPU
120
+ | ResNet-3D | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 10.672 ms | 3 - 299 MB | NPU
121
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 21.073 ms | 5 - 9 MB | NPU
122
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 472.175 ms | 6 - 363 MB | NPU
123
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® SA7255P | 75.863 ms | 3 - 284 MB | NPU
124
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® SA8295P | 39.827 ms | 0 - 280 MB | NPU
125
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 43.297 ms | 3 - 300 MB | NPU
126
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 15.452 ms | 3 - 292 MB | NPU
127
+ | ResNet-3D | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 23.398 ms | 3 - 3 MB | NPU
128
+ | ResNet-3D | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1069.241 ms | 0 - 636 MB | NPU
129
+ | ResNet-3D | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 1625.325 ms | 1 - 606 MB | NPU
130
+ | ResNet-3D | TFLITE | float | Qualcomm® QCS8275 | 2774.41 ms | 1 - 457 MB | NPU
131
+ | ResNet-3D | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1474.312 ms | 0 - 4 MB | NPU
132
+ | ResNet-3D | TFLITE | float | Qualcomm® SA8775P | 1478.637 ms | 1 - 476 MB | NPU
133
+ | ResNet-3D | TFLITE | float | Qualcomm® SA8650P | 1478.637 ms | 1 - 476 MB | NPU
134
+ | ResNet-3D | TFLITE | float | Qualcomm® SA8255P | 1478.637 ms | 1 - 476 MB | NPU
135
+ | ResNet-3D | TFLITE | float | Qualcomm® QCS8450 | 1625.325 ms | 1 - 606 MB | NPU
136
+ | ResNet-3D | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1418.372 ms | 0 - 83 MB | NPU
137
+ | ResNet-3D | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 885.903 ms | 1 - 473 MB | NPU
138
+ | ResNet-3D | TFLITE | float | Qualcomm® SA7255P | 2774.41 ms | 1 - 457 MB | NPU
139
+ | ResNet-3D | TFLITE | float | Snapdragon® 8 Elite Mobile | 988.491 ms | 0 - 466 MB | NPU
140
+ | ResNet-3D | TFLITE | float | Qualcomm® SA8295P | 1734.663 ms | 0 - 454 MB | NPU
141
+ | ResNet-3D | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 988.491 ms | 0 - 466 MB | NPU
142
+ | ResNet-3D | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 934.855 ms | 0 - 1008 MB | NPU
143
+ | ResNet-3D | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1413.153 ms | 0 - 867 MB | NPU
144
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 9658.683 ms | 3462 - 5278 MB | NPU
145
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCS8275 | 2556.009 ms | 1 - 820 MB | NPU
146
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1256.34 ms | 0 - 4 MB | NPU
147
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA8775P | 1259.878 ms | 1 - 819 MB | NPU
148
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA8650P | 1259.878 ms | 1 - 819 MB | NPU
149
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA8255P | 1259.878 ms | 1 - 819 MB | NPU
150
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® QCS8450 | 1413.153 ms | 0 - 867 MB | NPU
151
+ | ResNet-3D | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 681.809 ms | 1 - 724 MB | NPU
152
+ | ResNet-3D | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 341128.645 ms | 920 - 1201 MB | NPU
153
+ | ResNet-3D | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 820.336 ms | 0 - 926 MB | NPU
154
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1272.405 ms | 0 - 77 MB | NPU
155
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 384880.936 ms | 953 - 1169 MB | NPU
156
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA7255P | 2556.009 ms | 1 - 820 MB | NPU
157
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® SA8295P | 1342.174 ms | 1 - 685 MB | NPU
158
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 341128.645 ms | 920 - 1201 MB | NPU
159
+ | ResNet-3D | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 681.809 ms | 1 - 724 MB | NPU
160
 
161
  ## License
162
  * The license for the original implementation of ResNet-3D can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,20 +8,20 @@
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.57.3/resnet_3d-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.57.3/resnet_3d-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.57.3/resnet_3d-onnx-float.zip"
25
  }
26
  }
27
  },
@@ -32,20 +32,20 @@
32
  "qairt": "2.45.0.260326154327",
33
  "litert": "1.4.4"
34
  },
35
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.57.3/resnet_3d-tflite-w8a8.zip"
36
  },
37
  "qnn_dlc": {
38
  "tool_versions": {
39
  "qairt": "2.45.0.260326154327"
40
  },
41
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.57.3/resnet_3d-qnn_dlc-w8a8.zip"
42
  },
43
  "onnx": {
44
  "tool_versions": {
45
  "qairt": "2.45.0.260326154327",
46
  "onnx_runtime": "1.25.0"
47
  },
48
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.57.3/resnet_3d-onnx-w8a8.zip"
49
  }
50
  }
51
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.58.0/resnet_3d-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.58.0/resnet_3d-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.58.0/resnet_3d-onnx-float.zip"
25
  }
26
  }
27
  },
 
32
  "qairt": "2.45.0.260326154327",
33
  "litert": "1.4.4"
34
  },
35
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.58.0/resnet_3d-tflite-w8a8.zip"
36
  },
37
  "qnn_dlc": {
38
  "tool_versions": {
39
  "qairt": "2.45.0.260326154327"
40
  },
41
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.58.0/resnet_3d-qnn_dlc-w8a8.zip"
42
  },
43
  "onnx": {
44
  "tool_versions": {
45
  "qairt": "2.45.0.260326154327",
46
  "onnx_runtime": "1.25.0"
47
  },
48
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_3d/releases/v0.58.0/resnet_3d-onnx-w8a8.zip"
49
  }
50
  }
51
  }