Hugging Face's logo

qualcomm
/
CVT

Other
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
46de88c
·
verified ·
1 Parent(s): 073473a

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 +49 -46
  2. release_assets.json +5 -5
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: other
14
  Cross-View Transformer generates real-time bird's-eye view maps from multiple vehicle cameras for autonomous driving.
15
 
16
  This is based on the implementation of CVT found [here](https://github.com/bradyz/cross_view_transformers).
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/v0.57.3/src/qai_hub_models/models/cvt) 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
 
@@ -27,24 +27,24 @@ 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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.57.3/cvt-onnx-float.zip)
31
- | ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.57.3/cvt-onnx-w8a16_mixed_fp16.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.57.3/cvt-qnn_dlc-float.zip)
33
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.57.3/cvt-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[CVT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cvt)**.
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/cvt) 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 [CVT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/cvt) for usage instructions.
48
 
49
  ## Model Details
50
 
@@ -60,49 +60,52 @@ See our repository for [CVT on GitHub](https://github.com/qualcomm/ai-hub-models
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
- | CVT | ONNX | float | Snapdragon® X2 Elite | 183.908 ms | 173 - 173 MB | NPU
64
- | CVT | ONNX | float | Snapdragon® X Elite | 274.2 ms | 142 - 142 MB | NPU
65
  | CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 245.125 ms | 8 - 2683 MB | NPU
66
- | CVT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 424.309 ms | 10 - 2821 MB | NPU
67
- | CVT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 325.517 ms | 0 - 24 MB | NPU
68
- | CVT | ONNX | float | Qualcomm® QCS8450 | 424.309 ms | 10 - 2821 MB | NPU
69
- | CVT | ONNX | float | Snapdragon® 8 Elite Mobile | 187.62 ms | 3 - 2380 MB | NPU
70
- | CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 167.214 ms | 0 - 2411 MB | NPU
71
- | CVT | ONNX | float | Qualcomm® QCS9075 | 321.618 ms | 7 - 53 MB | NPU
72
- | CVT | ONNX | float | Qualcomm® QCS8750 | 187.62 ms | 3 - 2380 MB | NPU
73
- | CVT | ONNX | float | Qualcomm® QCS7181 | 274.2 ms | 142 - 142 MB | NPU
74
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 253.311 ms | 15 - 2643 MB | NPU
75
- | CVT | ONNX | w8a16_mixed_fp16 | Qualcomm® QCS8550 (Proxy) | 355.673 ms | 13 - 18 MB | NPU
76
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Mobile | 217.182 ms | 12 - 2415 MB | NPU
77
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 198.04 ms | 12 - 2507 MB | NPU
78
- | CVT | ONNX | w8a16_mixed_fp16 | Qualcomm® QCS9075 | 425.412 ms | 14 - 59 MB | NPU
79
- | CVT | ONNX | w8a16_mixed_fp16 | Qualcomm® QCS8750 | 217.182 ms | 12 - 2415 MB | NPU
80
- | CVT | QNN_DLC | float | Snapdragon® X2 Elite | 182.322 ms | 7 - 7 MB | NPU
81
- | CVT | QNN_DLC | float | Snapdragon® X Elite | 286.885 ms | 7 - 7 MB | NPU
82
- | CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 222.363 ms | 7 - 2575 MB | NPU
83
- | CVT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 441.585 ms | 7 - 2718 MB | NPU
84
- | CVT | QNN_DLC | float | Qualcomm® QCS8275 | 425.513 ms | 2 - 2213 MB | NPU
85
- | CVT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 331.6 ms | 8 - 13 MB | NPU
86
- | CVT | QNN_DLC | float | Qualcomm® QCS8450 | 441.585 ms | 7 - 2718 MB | NPU
87
- | CVT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 184.913 ms | 0 - 2290 MB | NPU
88
- | CVT | QNN_DLC | float | Qualcomm® SA8295P | 332.666 ms | 0 - 2323 MB | NPU
89
- | CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 168.158 ms | 7 - 2319 MB | NPU
90
- | CVT | QNN_DLC | float | Qualcomm® QCS9075 | 322.622 ms | 7 - 17 MB | NPU
91
- | CVT | QNN_DLC | float | Qualcomm® SA7255P | 425.513 ms | 2 - 2213 MB | NPU
92
- | CVT | QNN_DLC | float | Qualcomm® QCS8750 | 184.913 ms | 0 - 2290 MB | NPU
93
- | CVT | QNN_DLC | float | Qualcomm® QCS7181 | 286.885 ms | 7 - 7 MB | NPU
94
- | CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 215.76 ms | 1 - 2673 MB | NPU
95
- | CVT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 416.47 ms | 1 - 2724 MB | NPU
96
- | CVT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 306.789 ms | 0 - 3 MB | NPU
 
 
 
97
  | CVT | TFLITE | float | Qualcomm® SA8775P | 572.418 ms | 48 - 60 MB | CPU
98
  | CVT | TFLITE | float | Qualcomm® SA8650P | 572.418 ms | 48 - 60 MB | CPU
99
  | CVT | TFLITE | float | Qualcomm® SA8255P | 572.418 ms | 48 - 60 MB | CPU
100
- | CVT | TFLITE | float | Qualcomm® QCS8450 | 416.47 ms | 1 - 2724 MB | NPU
101
- | CVT | TFLITE | float | Snapdragon® 8 Elite Mobile | 182.607 ms | 0 - 2363 MB | NPU
102
- | CVT | TFLITE | float | Qualcomm® SA8295P | 332.722 ms | 0 - 2306 MB | NPU
103
- | CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 167.605 ms | 0 - 2315 MB | NPU
104
- | CVT | TFLITE | float | Qualcomm® QCS9075 | 317.919 ms | 0 - 36 MB | NPU
105
- | CVT | TFLITE | float | Qualcomm® QCS8750 | 182.607 ms | 0 - 2363 MB | NPU
106
 
107
  ## License
108
  * The license for the original implementation of CVT can be found
 
14
  Cross-View Transformer generates real-time bird's-eye view maps from multiple vehicle cameras for autonomous driving.
15
 
16
  This is based on the implementation of CVT found [here](https://github.com/bradyz/cross_view_transformers).
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/v0.58.0/src/qai_hub_models/models/cvt) 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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.58.0/cvt-onnx-float.zip)
31
+ | ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.58.0/cvt-onnx-w8a16_mixed_fp16.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.58.0/cvt-qnn_dlc-float.zip)
33
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.58.0/cvt-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[CVT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cvt)**.
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/cvt) 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 [CVT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/cvt) 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
+ | CVT | ONNX | float | Snapdragon® X2 Elite | 182.294 ms | 8 - 8 MB | NPU
64
+ | CVT | ONNX | float | Snapdragon® X Elite | 270.902 ms | 19 - 19 MB | NPU
65
  | CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 245.125 ms | 8 - 2683 MB | NPU
66
+ | CVT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 436.757 ms | 8 - 2778 MB | NPU
67
+ | CVT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 329.711 ms | 0 - 25 MB | NPU
68
+ | CVT | ONNX | float | Qualcomm® QCS8450 | 436.757 ms | 8 - 2778 MB | NPU
69
+ | CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 169.577 ms | 3 - 2415 MB | NPU
70
+ | CVT | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 321.618 ms | 7 - 53 MB | NPU
71
+ | CVT | ONNX | float | Snapdragon® 8 Elite Mobile | 186.289 ms | 3 - 2380 MB | NPU
72
+ | CVT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 186.289 ms | 3 - 2380 MB | NPU
73
+ | CVT | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 270.902 ms | 19 - 19 MB | NPU
74
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 263.712 ms | 15 - 2659 MB | NPU
75
+ | CVT | ONNX | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 363.316 ms | 0 - 28 MB | NPU
76
+ | CVT | ONNX | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-9075 | 320.828 ms | 13 - 16 MB | NPU
77
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 197.898 ms | 12 - 2511 MB | NPU
78
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Mobile | 216.688 ms | 12 - 2416 MB | NPU
79
+ | CVT | ONNX | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ Q-8750 | 216.688 ms | 12 - 2416 MB | NPU
80
+ | CVT | QNN_DLC | float | Snapdragon® X2 Elite | 182.523 ms | 7 - 7 MB | NPU
81
+ | CVT | QNN_DLC | float | Snapdragon® X Elite | 286.686 ms | 7 - 7 MB | NPU
82
+ | CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 220.366 ms | 7 - 2575 MB | NPU
83
+ | CVT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 440.531 ms | 7 - 2720 MB | NPU
84
+ | CVT | QNN_DLC | float | Qualcomm® QCS8275 | 425.082 ms | 0 - 2212 MB | NPU
85
+ | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 332.747 ms | 8 - 12 MB | NPU
86
+ | CVT | QNN_DLC | float | Qualcomm® SA8775P | 292.829 ms | 2 - 2213 MB | NPU
87
+ | CVT | QNN_DLC | float | Qualcomm® SA8650P | 292.829 ms | 2 - 2213 MB | NPU
88
+ | CVT | QNN_DLC | float | Qualcomm® SA8255P | 292.829 ms | 2 - 2213 MB | NPU
89
+ | CVT | QNN_DLC | float | Qualcomm® QCS8450 | 440.531 ms | 7 - 2720 MB | NPU
90
+ | CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 167.886 ms | 7 - 2318 MB | NPU
91
+ | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 363.338 ms | 7 - 17 MB | NPU
92
+ | CVT | QNN_DLC | float | Qualcomm® SA7255P | 425.082 ms | 0 - 2212 MB | NPU
93
+ | CVT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 186.105 ms | 7 - 2299 MB | NPU
94
+ | CVT | QNN_DLC | float | Qualcomm® SA8295P | 334.575 ms | 0 - 2324 MB | NPU
95
+ | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 186.105 ms | 7 - 2299 MB | NPU
96
+ | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 286.686 ms | 7 - 7 MB | NPU
97
+ | CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 226.281 ms | 0 - 2673 MB | NPU
98
+ | CVT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 389.924 ms | 0 - 2726 MB | NPU
99
+ | CVT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 306.789 ms | 0 - 3 MB | NPU
100
  | CVT | TFLITE | float | Qualcomm® SA8775P | 572.418 ms | 48 - 60 MB | CPU
101
  | CVT | TFLITE | float | Qualcomm® SA8650P | 572.418 ms | 48 - 60 MB | CPU
102
  | CVT | TFLITE | float | Qualcomm® SA8255P | 572.418 ms | 48 - 60 MB | CPU
103
+ | CVT | TFLITE | float | Qualcomm® QCS8450 | 389.924 ms | 0 - 2726 MB | NPU
104
+ | CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 166.0 ms | 0 - 2314 MB | NPU
105
+ | CVT | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 317.919 ms | 0 - 36 MB | NPU
106
+ | CVT | TFLITE | float | Snapdragon® 8 Elite Mobile | 183.486 ms | 1 - 2364 MB | NPU
107
+ | CVT | TFLITE | float | Qualcomm® SA8295P | 331.769 ms | 0 - 2306 MB | NPU
108
+ | CVT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 183.486 ms | 1 - 2364 MB | NPU
109
 
110
  ## License
111
  * The license for the original implementation of CVT 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/cvt/releases/v0.57.3/cvt-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/cvt/releases/v0.57.3/cvt-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/cvt/releases/v0.57.3/cvt-onnx-float.zip"
25
  }
26
  }
27
  },
@@ -32,7 +32,7 @@
32
  "qairt": "2.45.0.260326154327",
33
  "onnx_runtime": "1.25.0"
34
  },
35
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.57.3/cvt-onnx-w8a16_mixed_fp16.zip"
36
  }
37
  }
38
  }
 
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/cvt/releases/v0.58.0/cvt-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/cvt/releases/v0.58.0/cvt-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/cvt/releases/v0.58.0/cvt-onnx-float.zip"
25
  }
26
  }
27
  },
 
32
  "qairt": "2.45.0.260326154327",
33
  "onnx_runtime": "1.25.0"
34
  },
35
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.58.0/cvt-onnx-w8a16_mixed_fp16.zip"
36
  }
37
  }
38
  }