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
dcf5ed5
·
verified ·
1 Parent(s): c9ea9d1

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 +82 -30
  2. release_assets.json +3 -3
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/v0.57.3/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
 
@@ -29,22 +29,22 @@ 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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.57.3/rangenet_plus_plus-onnx-float.zip)
33
- | 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/v0.57.3/rangenet_plus_plus-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[RangeNet-Plus-Plus on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/rangenet_plus_plus)**.
36
 
37
 
38
  ### Option 2: Export with Custom Configurations
39
 
40
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/rangenet_plus_plus) Python library to compile and export the model with your own:
41
  - Custom weights (e.g., fine-tuned checkpoints)
42
  - Custom input shapes
43
  - Target device and runtime configurations
44
 
45
  This option is ideal if you need to customize the model beyond the default configuration provided here.
46
 
47
- See our repository for [RangeNet-Plus-Plus on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/rangenet_plus_plus) for usage instructions.
48
 
49
  ## Model Details
50
 
@@ -60,31 +60,83 @@ See our repository for [RangeNet-Plus-Plus on GitHub](https://github.com/qualcom
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® X2 Elite | 49.351 ms | 210 - 210 MB | NPU
64
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® X Elite | 99.787 ms | 147 - 147 MB | NPU
65
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 75.688 ms | 47 - 492 MB | NPU
66
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 214.848 ms | 3 - 441 MB | NPU
67
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® QCS8550 (Proxy) | 102.175 ms | 0 - 113 MB | NPU
68
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® QCS8450 | 214.848 ms | 3 - 441 MB | NPU
69
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 42.224 ms | 2 - 342 MB | NPU
70
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® QCS9075 | 159.825 ms | 2 - 48 MB | NPU
71
- | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Elite Mobile | 59.183 ms | 1 - 321 MB | NPU
72
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® QCS8750 | 59.183 ms | 1 - 321 MB | NPU
73
- | RangeNet-Plus-Plus | ONNX | float | Qualcomm® QCS7181 | 99.787 ms | 147 - 147 MB | NPU
74
- | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 78.955 ms | 1 - 510 MB | NPU
75
- | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 197.635 ms | 1 - 499 MB | NPU
76
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® QCS8275 | 596.038 ms | 1 - 308 MB | NPU
77
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 106.778 ms | 0 - 96 MB | NPU
78
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8775P | 1229.142 ms | 0 - 29 MB | GPU
79
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8650P | 1229.142 ms | 0 - 29 MB | GPU
80
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8255P | 1229.142 ms | 0 - 29 MB | GPU
81
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® QCS8450 | 197.635 ms | 1 - 499 MB | NPU
82
- | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 43.272 ms | 6 - 323 MB | NPU
83
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA7255P | 596.038 ms | 1 - 308 MB | NPU
84
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® QCS9075 | 167.687 ms | 0 - 107 MB | NPU
85
- | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Elite Mobile | 60.072 ms | 1 - 294 MB | NPU
86
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8295P | 172.041 ms | 1 - 302 MB | NPU
87
- | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® QCS8750 | 60.072 ms | 1 - 294 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
 
89
  ## License
90
  * 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/v0.58.0/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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.58.0/rangenet_plus_plus-onnx-float.zip)
33
+ | 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/v0.58.0/rangenet_plus_plus-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[RangeNet-Plus-Plus on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/rangenet_plus_plus)**.
36
 
37
 
38
  ### Option 2: Export with Custom Configurations
39
 
40
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/rangenet_plus_plus) Python library to compile and export the model with your own:
41
  - Custom weights (e.g., fine-tuned checkpoints)
42
  - Custom input shapes
43
  - Target device and runtime configurations
44
 
45
  This option is ideal if you need to customize the model beyond the default configuration provided here.
46
 
47
+ See our repository for [RangeNet-Plus-Plus on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/rangenet_plus_plus) for usage instructions.
48
 
49
  ## Model Details
50
 
 
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® X2 Elite | 50.185 ms | 35 - 35 MB | NPU
64
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® X Elite | 99.855 ms | 101 - 101 MB | NPU
65
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 76.089 ms | 0 - 453 MB | NPU
66
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 194.334 ms | 20 - 467 MB | NPU
67
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 105.21 ms | 23 - 26 MB | NPU
68
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® QCS8450 | 194.334 ms | 20 - 467 MB | NPU
69
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 152.411 ms | 21 - 26 MB | NPU
70
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 44.041 ms | 24 - 364 MB | NPU
71
+ | RangeNet-Plus-Plus | ONNX | float | Snapdragon® 8 Elite Mobile | 59.563 ms | 24 - 342 MB | NPU
72
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 59.563 ms | 24 - 342 MB | NPU
73
+ | RangeNet-Plus-Plus | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 99.855 ms | 101 - 101 MB | NPU
74
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® X2 Elite | 37.698 ms | 18 - 18 MB | NPU
75
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® X Elite | 65.62 ms | 52 - 52 MB | NPU
76
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 50.478 ms | 14 - 489 MB | NPU
77
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 110.317 ms | 1 - 583 MB | NPU
78
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 420.396 ms | 11 - 15 MB | NPU
79
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 66.827 ms | 11 - 14 MB | NPU
80
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® QCS8450 | 110.317 ms | 1 - 583 MB | NPU
81
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 127.11 ms | 16 - 536 MB | NPU
82
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 31.79 ms | 12 - 363 MB | NPU
83
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 1554.648 ms | 4 - 799 MB | NPU
84
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 45.05 ms | 13 - 357 MB | NPU
85
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 127.11 ms | 16 - 536 MB | NPU
86
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 45.05 ms | 13 - 357 MB | NPU
87
+ | RangeNet-Plus-Plus | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 65.62 ms | 52 - 52 MB | NPU
88
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® X2 Elite | 49.303 ms | 3 - 3 MB | NPU
89
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® X Elite | 99.544 ms | 3 - 3 MB | NPU
90
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 76.893 ms | 1 - 450 MB | NPU
91
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 196.172 ms | 0 - 442 MB | NPU
92
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® QCS8275 | 591.086 ms | 1 - 332 MB | NPU
93
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 102.54 ms | 3 - 4 MB | NPU
94
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8775P | 151.454 ms | 1 - 332 MB | NPU
95
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8650P | 151.454 ms | 1 - 332 MB | NPU
96
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8255P | 151.454 ms | 1 - 332 MB | NPU
97
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® QCS8450 | 196.172 ms | 0 - 442 MB | NPU
98
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 151.158 ms | 5 - 19 MB | NPU
99
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 42.227 ms | 3 - 342 MB | NPU
100
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA7255P | 591.086 ms | 1 - 332 MB | NPU
101
+ | RangeNet-Plus-Plus | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 59.308 ms | 2 - 320 MB | NPU
102
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® SA8295P | 168.089 ms | 0 - 325 MB | NPU
103
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 59.308 ms | 2 - 320 MB | NPU
104
+ | RangeNet-Plus-Plus | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 99.544 ms | 3 - 3 MB | NPU
105
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 35.294 ms | 1 - 1 MB | NPU
106
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® X Elite | 63.823 ms | 1 - 1 MB | NPU
107
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 50.431 ms | 0 - 457 MB | NPU
108
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 101.458 ms | 1 - 569 MB | NPU
109
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 415.697 ms | 1 - 9 MB | NPU
110
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 192.142 ms | 2 - 322 MB | NPU
111
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 64.276 ms | 1 - 4 MB | NPU
112
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8775P | 62.794 ms | 1 - 322 MB | NPU
113
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8650P | 62.794 ms | 1 - 322 MB | NPU
114
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8255P | 62.794 ms | 1 - 322 MB | NPU
115
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 101.458 ms | 1 - 569 MB | NPU
116
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 120.558 ms | 1 - 451 MB | NPU
117
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 31.394 ms | 1 - 344 MB | NPU
118
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 1523.969 ms | 1 - 713 MB | NPU
119
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 62.754 ms | 1 - 9 MB | NPU
120
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA7255P | 192.142 ms | 2 - 322 MB | NPU
121
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 44.019 ms | 1 - 338 MB | NPU
122
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® SA8295P | 104.095 ms | 2 - 431 MB | NPU
123
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 120.558 ms | 1 - 451 MB | NPU
124
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 44.019 ms | 1 - 338 MB | NPU
125
+ | RangeNet-Plus-Plus | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 63.823 ms | 1 - 1 MB | NPU
126
+ | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 80.467 ms | 10 - 516 MB | NPU
127
+ | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 199.33 ms | 0 - 499 MB | NPU
128
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® QCS8275 | 595.949 ms | 10 - 317 MB | NPU
129
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 104.342 ms | 10 - 226 MB | NPU
130
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8775P | 155.505 ms | 10 - 317 MB | NPU
131
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8650P | 155.505 ms | 10 - 317 MB | NPU
132
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8255P | 155.505 ms | 10 - 317 MB | NPU
133
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® QCS8450 | 199.33 ms | 0 - 499 MB | NPU
134
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 167.687 ms | 0 - 107 MB | NPU
135
+ | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 43.828 ms | 10 - 330 MB | NPU
136
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA7255P | 595.949 ms | 10 - 317 MB | NPU
137
+ | RangeNet-Plus-Plus | TFLITE | float | Snapdragon® 8 Elite Mobile | 62.774 ms | 8 - 306 MB | NPU
138
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® SA8295P | 173.207 ms | 10 - 312 MB | NPU
139
+ | RangeNet-Plus-Plus | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 62.774 ms | 8 - 306 MB | NPU
140
 
141
  ## License
142
  * The license for the original implementation of RangeNet-Plus-Plus can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,14 +8,14 @@
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/rangenet_plus_plus/releases/v0.57.3/rangenet_plus_plus-tflite-float.zip"
12
  },
13
  "onnx": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327",
16
  "onnx_runtime": "1.25.0"
17
  },
18
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.57.3/rangenet_plus_plus-onnx-float.zip"
19
  }
20
  }
21
  }
 
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/rangenet_plus_plus/releases/v0.58.0/rangenet_plus_plus-tflite-float.zip"
12
  },
13
  "onnx": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327",
16
  "onnx_runtime": "1.25.0"
17
  },
18
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rangenet_plus_plus/releases/v0.58.0/rangenet_plus_plus-onnx-float.zip"
19
  }
20
  }
21
  }