Hugging Face's logo

qualcomm
/
RangeNet-Plus-Plus

Other
PyTorch
real_time
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
f47020c
·
verified ·
1 Parent(s): b38f9e8

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 +93 -86
  2. release_assets.json +6 -6
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: other
16
  RangeNet-Plus-Plus (also stylized as RangeNet++) projects a LiDAR point cloud onto a 5-channel range image (depth, x, y, z, intensity) and applies a DarkNet-53 encoder with a decoder head to predict per-point semantic class labels in real time.
17
 
18
  This is based on the implementation of RangeNet-Plus-Plus found [here](https://github.com/PRBonn/lidar-bonnetal).
19
- 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/rangenet_plus_plus) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
@@ -29,115 +29,122 @@ Below are pre-exported model assets ready for deployment.
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
- | 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/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-onnx-float.zip)
33
- | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-onnx-w8a16.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-qnn_dlc-float.zip)
35
- | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-qnn_dlc-w8a16.zip)
36
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-tflite-float.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[RangeNet-Plus-Plus on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/rangenet_plus_plus)**.
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/v0.59.0/src/qai_hub_models/models/rangenet_plus_plus) 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 [RangeNet-Plus-Plus on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/rangenet_plus_plus) for usage instructions.
51
 
52
  ## Model Details
53
 
54
  **Model Type:** Model_use_case.driver_assistance
55
 
56
  **Model Stats:**
57
- - Model checkpoint: darknet53_rangenet++
58
- - Input resolution: 64x2048
59
  - Input channels: 5
 
 
60
  - Number of output classes: 20
61
- - Backbone: DarkNet-53
62
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® X2 Elite | 50.249 ms | 35 - 35 MB | NPU
67
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® X Elite | 99.955 ms | 101 - 101 MB | NPU
68
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 76.463 ms | 0 - 455 MB | NPU
69
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 217.203 ms | 1 - 447 MB | NPU
70
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 102.101 ms | 0 - 138 MB | NPU
71
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® QCS8450 | 217.203 ms | 1 - 447 MB | NPU
72
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 152.799 ms | 21 - 26 MB | NPU
73
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 99.955 ms | 101 - 101 MB | NPU
74
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 59.683 ms | 25 - 344 MB | NPU
75
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Elite Mobile | 59.683 ms | 25 - 344 MB | NPU
76
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 43.705 ms | 22 - 363 MB | NPU
77
- | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® X2 Elite | 37.752 ms | 18 - 18 MB | NPU
78
- | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® X Elite | 65.56 ms | 52 - 52 MB | NPU
79
- | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 50.743 ms | 0 - 474 MB | NPU
80
- | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 111.168 ms | 1 - 584 MB | NPU
81
- | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 422.1 ms | 13 - 17 MB | NPU
82
- | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 67.594 ms | 0 - 58 MB | NPU
83
- | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® QCS8450 | 111.168 ms | 1 - 584 MB | NPU
84
- | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 68.952 ms | 13 - 17 MB | NPU
85
- | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 65.56 ms | 52 - 52 MB | NPU
86
- | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 44.656 ms | 13 - 357 MB | NPU
87
- | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 44.656 ms | 13 - 357 MB | NPU
88
- | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 31.707 ms | 12 - 361 MB | NPU
89
- | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® X2 Elite | 49.228 ms | 3 - 3 MB | NPU
90
- | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® X Elite | 99.676 ms | 3 - 3 MB | NPU
91
- | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 76.707 ms | 3 - 457 MB | NPU
92
- | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 186.021 ms | 2 - 445 MB | NPU
93
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 591.087 ms | 2 - 332 MB | NPU
94
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 101.404 ms | 3 - 4 MB | NPU
95
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8775P | 151.457 ms | 1 - 332 MB | NPU
96
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8650P | 151.457 ms | 1 - 332 MB | NPU
97
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8255P | 151.457 ms | 1 - 332 MB | NPU
98
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® QCS8450 | 186.021 ms | 2 - 445 MB | NPU
99
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 151.442 ms | 3 - 17 MB | NPU
100
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 99.676 ms | 3 - 3 MB | NPU
101
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 59.104 ms | 0 - 318 MB | NPU
102
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA7255P | 591.087 ms | 2 - 332 MB | NPU
103
- | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8295P | 168.089 ms | 0 - 325 MB | NPU
104
- | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 59.104 ms | 0 - 318 MB | NPU
105
- | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 42.935 ms | 3 - 344 MB | NPU
106
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 35.413 ms | 1 - 1 MB | NPU
107
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® X Elite | 64.031 ms | 1 - 1 MB | NPU
108
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 51.51 ms | 0 - 455 MB | NPU
109
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 102.817 ms | 1 - 568 MB | NPU
110
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 415.398 ms | 3 - 11 MB | NPU
111
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 192.032 ms | 2 - 322 MB | NPU
112
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 64.24 ms | 1 - 4 MB | NPU
113
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8775P | 62.8 ms | 1 - 322 MB | NPU
114
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8650P | 62.8 ms | 1 - 322 MB | NPU
115
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8255P | 62.8 ms | 1 - 322 MB | NPU
116
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 102.817 ms | 1 - 568 MB | NPU
117
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 63.197 ms | 1 - 9 MB | NPU
118
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 64.031 ms | 1 - 1 MB | NPU
119
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 1565.631 ms | 1 - 713 MB | NPU
120
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 120.593 ms | 1 - 445 MB | NPU
121
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 43.882 ms | 2 - 340 MB | NPU
122
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA7255P | 192.032 ms | 2 - 322 MB | NPU
123
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8295P | 104.143 ms | 2 - 431 MB | NPU
124
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 43.882 ms | 2 - 340 MB | NPU
125
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 31.168 ms | 1 - 344 MB | NPU
126
- | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 120.593 ms | 1 - 445 MB | NPU
127
- | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 80.492 ms | 10 - 516 MB | NPU
128
- | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 209.919 ms | 10 - 509 MB | NPU
129
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 595.971 ms | 10 - 317 MB | NPU
130
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 104.209 ms | 10 - 186 MB | NPU
131
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8775P | 155.354 ms | 10 - 317 MB | NPU
132
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8650P | 155.354 ms | 10 - 317 MB | NPU
133
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8255P | 155.354 ms | 10 - 317 MB | NPU
134
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® QCS8450 | 209.919 ms | 10 - 509 MB | NPU
135
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 155.53 ms | 10 - 127 MB | NPU
136
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 62.819 ms | 10 - 303 MB | NPU
137
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA7255P | 595.971 ms | 10 - 317 MB | NPU
138
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8295P | 173.168 ms | 10 - 312 MB | NPU
139
- | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Elite Mobile | 62.819 ms | 10 - 303 MB | NPU
140
- | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 43.71 ms | 0 - 319 MB | NPU
 
 
 
 
 
 
 
141
 
142
  ## License
143
  * The license for the original implementation of RangeNet-Plus-Plus can be found
 
16
  RangeNet-Plus-Plus (also stylized as RangeNet++) projects a LiDAR point cloud onto a 5-channel range image (depth, x, y, z, intensity) and applies a DarkNet-53 encoder with a decoder head to predict per-point semantic class labels in real time.
17
 
18
  This is based on the implementation of RangeNet-Plus-Plus found [here](https://github.com/PRBonn/lidar-bonnetal).
19
+ 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/rangenet_plus_plus) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
 
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
+ | 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/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-onnx-float.zip)
33
+ | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-onnx-w8a16.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-qnn_dlc-float.zip)
35
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-qnn_dlc-w8a16.zip)
36
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-tflite-float.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[RangeNet-Plus-Plus on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/rangenet_plus_plus)**.
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/v0.60.0/src/qai_hub_models/models/rangenet_plus_plus) 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 [RangeNet-Plus-Plus on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/rangenet_plus_plus) for usage instructions.
51
 
52
  ## Model Details
53
 
54
  **Model Type:** Model_use_case.driver_assistance
55
 
56
  **Model Stats:**
57
+ - Backbone: DarkNet-53
 
58
  - Input channels: 5
59
+ - Input resolution: 64x2048
60
+ - Model checkpoint: darknet53_rangenet++
61
  - Number of output classes: 20
 
62
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® X2 Elite | 50.487 ms | 35 - 35 MB | NPU
67
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® X Elite | 100.113 ms | 101 - 101 MB | NPU
68
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 77.958 ms | 0 - 459 MB | NPU
69
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 216.607 ms | 1 - 524 MB | NPU
70
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 178.11 ms | 21 - 27 MB | NPU
71
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 104.064 ms | 0 - 112 MB | NPU
72
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® QCS8450 | 216.607 ms | 1 - 524 MB | NPU
73
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 157.296 ms | 21 - 26 MB | NPU
74
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 100.113 ms | 101 - 101 MB | NPU
75
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 60.117 ms | 23 - 349 MB | NPU
76
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Elite Mobile | 60.117 ms | 23 - 349 MB | NPU
77
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 42.943 ms | 21 - 370 MB | NPU
78
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® X2 Elite | 37.594 ms | 18 - 18 MB | NPU
79
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® X Elite | 65.689 ms | 52 - 52 MB | NPU
80
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 51.762 ms | 0 - 473 MB | NPU
81
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 114.83 ms | 12 - 595 MB | NPU
82
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 425.984 ms | 24 - 28 MB | NPU
83
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 70.041 ms | 10 - 15 MB | NPU
84
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 67.652 ms | 0 - 57 MB | NPU
85
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® QCS8450 | 114.83 ms | 12 - 595 MB | NPU
86
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 70.225 ms | 13 - 17 MB | NPU
87
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 65.689 ms | 52 - 52 MB | NPU
88
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 1619.834 ms | 0 - 795 MB | NPU
89
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 135.934 ms | 29 - 553 MB | NPU
90
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 45.496 ms | 12 - 357 MB | NPU
91
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 45.496 ms | 12 - 357 MB | NPU
92
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 31.753 ms | 12 - 361 MB | NPU
93
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 135.934 ms | 29 - 553 MB | NPU
94
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® X2 Elite | 50.01 ms | 3 - 3 MB | NPU
95
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® X Elite | 100.174 ms | 3 - 3 MB | NPU
96
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 77.492 ms | 0 - 451 MB | NPU
97
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 206.249 ms | 0 - 443 MB | NPU
98
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 177.235 ms | 3 - 17 MB | NPU
99
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 593.196 ms | 1 - 334 MB | NPU
100
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 103.825 ms | 3 - 31 MB | NPU
101
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8775P | 152.968 ms | 1 - 333 MB | NPU
102
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8650P | 152.968 ms | 1 - 333 MB | NPU
103
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8255P | 152.968 ms | 1 - 333 MB | NPU
104
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® QCS8450 | 206.249 ms | 0 - 443 MB | NPU
105
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 152.851 ms | 3 - 17 MB | NPU
106
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 100.174 ms | 3 - 3 MB | NPU
107
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 60.973 ms | 0 - 317 MB | NPU
108
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA7255P | 593.196 ms | 1 - 334 MB | NPU
109
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8295P | 169.411 ms | 0 - 327 MB | NPU
110
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 60.973 ms | 0 - 317 MB | NPU
111
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 43.791 ms | 2 - 345 MB | NPU
112
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 36.382 ms | 1 - 1 MB | NPU
113
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® X Elite | 66.06 ms | 1 - 1 MB | NPU
114
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 52.438 ms | 0 - 461 MB | NPU
115
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 105.796 ms | 1 - 571 MB | NPU
116
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 421.074 ms | 3 - 11 MB | NPU
117
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 68.452 ms | 0 - 9 MB | NPU
118
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 193.562 ms | 2 - 325 MB | NPU
119
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 66.585 ms | 1 - 491 MB | NPU
120
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8775P | 62.383 ms | 1 - 325 MB | NPU
121
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8650P | 62.383 ms | 1 - 325 MB | NPU
122
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8255P | 62.383 ms | 1 - 325 MB | NPU
123
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 105.796 ms | 1 - 571 MB | NPU
124
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 62.698 ms | 1 - 9 MB | NPU
125
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 66.06 ms | 1 - 1 MB | NPU
126
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 1566.549 ms | 2 - 783 MB | NPU
127
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 131.361 ms | 1 - 513 MB | NPU
128
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 44.679 ms | 1 - 336 MB | NPU
129
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA7255P | 193.562 ms | 2 - 325 MB | NPU
130
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 44.679 ms | 1 - 336 MB | NPU
131
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 31.847 ms | 1 - 342 MB | NPU
132
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 131.361 ms | 1 - 513 MB | NPU
133
+ | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 76.979 ms | 11 - 521 MB | NPU
134
+ | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 210.817 ms | 13 - 513 MB | NPU
135
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 179.156 ms | 13 - 133 MB | NPU
136
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 593.609 ms | 13 - 322 MB | NPU
137
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 106.264 ms | 13 - 185 MB | NPU
138
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8775P | 153.741 ms | 13 - 323 MB | NPU
139
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8650P | 153.741 ms | 13 - 323 MB | NPU
140
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8255P | 153.741 ms | 13 - 323 MB | NPU
141
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® QCS8450 | 210.817 ms | 13 - 513 MB | NPU
142
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 154.001 ms | 11 - 130 MB | NPU
143
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 61.777 ms | 13 - 310 MB | NPU
144
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA7255P | 593.609 ms | 13 - 322 MB | NPU
145
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8295P | 170.588 ms | 13 - 315 MB | NPU
146
+ | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Elite Mobile | 61.777 ms | 13 - 310 MB | NPU
147
+ | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 43.676 ms | 12 - 332 MB | NPU
148
 
149
  ## License
150
  * The license for the original implementation of RangeNet-Plus-Plus 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/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-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/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-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/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,13 +31,13 @@
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/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-onnx-w8a16.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/rangenet_plus_plus/releases/v0.59.0/rangenet_plus_plus-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }
 
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/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-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/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-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/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-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/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-onnx-w8a16.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/rangenet_plus_plus/releases/v0.60.0/rangenet_plus_plus-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }