Hugging Face's logo

qualcomm
/
CVT

Other
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
30a5f74
·
verified ·
1 Parent(s): 3c1147c

v0.61.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.61.0 for changelog.

Files changed (2) hide show
  1. README.md +42 -40
  2. release_assets.json +4 -4
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: other
4
  tags:
5
  - android
6
  pipeline_tag: other
@@ -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/v0.60.0/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
 
@@ -27,23 +27,23 @@ 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/cvt/releases/v0.60.0/cvt-onnx-float.zip)
31
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.60.0/cvt-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.60.0/cvt-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[CVT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cvt)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/cvt) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
- See our repository for [CVT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/cvt) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -59,39 +59,41 @@ See our repository for [CVT on GitHub](https://github.com/qualcomm/ai-hub-models
59
  ## Performance Summary
60
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
61
  |---|---|---|---|---|---|---
62
- | CVT | ONNX | float | Snapdragon® X2 Elite | 179.93 ms | 8 - 8 MB | NPU
63
- | CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 225.492 ms | 8 - 2726 MB | NPU
64
- | CVT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 440.517 ms | 8 - 2756 MB | NPU
65
- | CVT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 333.474 ms | 0 - 23 MB | NPU
66
- | CVT | ONNX | float | Qualcomm® QCS8450 | 440.517 ms | 8 - 2756 MB | NPU
67
- | CVT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 188.235 ms | 1 - 2394 MB | NPU
68
- | CVT | ONNX | float | Snapdragon® 8 Elite Mobile | 188.235 ms | 1 - 2394 MB | NPU
69
- | CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 166.873 ms | 0 - 2442 MB | NPU
70
- | CVT | QNN_DLC | float | Snapdragon® X2 Elite | 182.316 ms | 7 - 7 MB | NPU
71
- | CVT | QNN_DLC | float | Snapdragon® X Elite | 286.424 ms | 7 - 7 MB | NPU
72
- | CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 224.915 ms | 8 - 2574 MB | NPU
73
- | CVT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 437.202 ms | 7 - 2720 MB | NPU
74
- | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 425.474 ms | 2 - 2213 MB | NPU
75
- | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 333.437 ms | 8 - 10 MB | NPU
76
- | CVT | QNN_DLC | float | Qualcomm® SA8775P | 292.508 ms | 2 - 2213 MB | NPU
77
- | CVT | QNN_DLC | float | Qualcomm® SA8650P | 292.508 ms | 2 - 2213 MB | NPU
78
- | CVT | QNN_DLC | float | Qualcomm® SA8255P | 292.508 ms | 2 - 2213 MB | NPU
79
- | CVT | QNN_DLC | float | Qualcomm® QCS8450 | 437.202 ms | 7 - 2720 MB | NPU
80
- | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 283.238 ms | 7 - 17 MB | NPU
81
- | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 286.424 ms | 7 - 7 MB | NPU
82
- | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 184.434 ms | 7 - 2297 MB | NPU
83
- | CVT | QNN_DLC | float | Qualcomm® SA7255P | 425.474 ms | 2 - 2213 MB | NPU
84
- | CVT | QNN_DLC | float | Qualcomm® SA8295P | 333.241 ms | 0 - 2324 MB | NPU
85
- | CVT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 184.434 ms | 7 - 2297 MB | NPU
86
- | CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 167.54 ms | 7 - 2318 MB | NPU
87
- | CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 217.0 ms | 89 - 2762 MB | NPU
88
- | CVT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 420.379 ms | 1 - 2728 MB | NPU
89
- | CVT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 324.21 ms | 0 - 4 MB | NPU
90
- | CVT | TFLITE | float | Qualcomm® QCS8450 | 420.379 ms | 1 - 2728 MB | NPU
91
- | CVT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 182.24 ms | 0 - 2363 MB | NPU
92
- | CVT | TFLITE | float | Qualcomm® SA8295P | 331.54 ms | 0 - 2306 MB | NPU
93
- | CVT | TFLITE | float | Snapdragon® 8 Elite Mobile | 182.24 ms | 0 - 2363 MB | NPU
94
- | CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 165.602 ms | 0 - 2315 MB | NPU
 
 
95
 
96
  ## License
97
  * The license for the original implementation of CVT can be found
 
1
  ---
2
  library_name: pytorch
3
+ license: mit
4
  tags:
5
  - android
6
  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/v0.61.0/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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.61.0/cvt-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.61.0/cvt-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.61.0/cvt-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[CVT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cvt)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/cvt) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
+ See our repository for [CVT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/cvt) for usage instructions.
47
 
48
  ## Model Details
49
 
 
59
  ## Performance Summary
60
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
61
  |---|---|---|---|---|---|---
62
+ | CVT | ONNX | float | Snapdragon® X2 Elite | 179.834 ms | 8 - 8 MB | NPU
63
+ | CVT | ONNX | float | Snapdragon® X Elite | 278.673 ms | 20 - 20 MB | NPU
64
+ | CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 225.436 ms | 8 - 2726 MB | NPU
65
+ | CVT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 444.226 ms | 8 - 2755 MB | NPU
66
+ | CVT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 332.188 ms | 0 - 2051 MB | NPU
67
+ | CVT | ONNX | float | Qualcomm® QCS8450 | 444.226 ms | 8 - 2755 MB | NPU
68
+ | CVT | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 278.673 ms | 20 - 20 MB | NPU
69
+ | CVT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 188.833 ms | 3 - 2396 MB | NPU
70
+ | CVT | ONNX | float | Snapdragon® 8 Elite Mobile | 188.833 ms | 3 - 2396 MB | NPU
71
+ | CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 167.698 ms | 0 - 2442 MB | NPU
72
+ | CVT | QNN_DLC | float | Snapdragon® X2 Elite | 183.246 ms | 7 - 7 MB | NPU
73
+ | CVT | QNN_DLC | float | Snapdragon® X Elite | 277.978 ms | 7 - 7 MB | NPU
74
+ | CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 223.295 ms | 0 - 2570 MB | NPU
75
+ | CVT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 442.247 ms | 7 - 2720 MB | NPU
76
+ | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 424.739 ms | 2 - 2213 MB | NPU
77
+ | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 334.128 ms | 8 - 1657 MB | NPU
78
+ | CVT | QNN_DLC | float | Qualcomm® SA8775P | 292.604 ms | 2 - 2213 MB | NPU
79
+ | CVT | QNN_DLC | float | Qualcomm® SA8650P | 292.604 ms | 2 - 2213 MB | NPU
80
+ | CVT | QNN_DLC | float | Qualcomm® SA8255P | 292.604 ms | 2 - 2213 MB | NPU
81
+ | CVT | QNN_DLC | float | Qualcomm® QCS8450 | 442.247 ms | 7 - 2720 MB | NPU
82
+ | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 282.71 ms | 7 - 17 MB | NPU
83
+ | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 277.978 ms | 7 - 7 MB | NPU
84
+ | CVT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 184.32 ms | 4 - 2294 MB | NPU
85
+ | CVT | QNN_DLC | float | Qualcomm® SA7255P | 424.739 ms | 2 - 2213 MB | NPU
86
+ | CVT | QNN_DLC | float | Qualcomm® SA8295P | 334.316 ms | 0 - 2324 MB | NPU
87
+ | CVT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 184.32 ms | 4 - 2294 MB | NPU
88
+ | CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 168.51 ms | 7 - 2317 MB | NPU
89
+ | CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 217.652 ms | 98 - 2774 MB | NPU
90
+ | CVT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 420.463 ms | 1 - 2726 MB | NPU
91
+ | CVT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 323.215 ms | 0 - 3 MB | NPU
92
+ | CVT | TFLITE | float | Qualcomm® QCS8450 | 420.463 ms | 1 - 2726 MB | NPU
93
+ | CVT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 182.869 ms | 1 - 2364 MB | NPU
94
+ | CVT | TFLITE | float | Qualcomm® SA8295P | 330.821 ms | 0 - 2306 MB | NPU
95
+ | CVT | TFLITE | float | Snapdragon® 8 Elite Mobile | 182.869 ms | 1 - 2364 MB | NPU
96
+ | CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 167.033 ms | 0 - 2315 MB | NPU
97
 
98
  ## License
99
  * The license for the original implementation of CVT can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.60.0",
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/cvt/releases/v0.60.0/cvt-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/cvt/releases/v0.60.0/cvt-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/cvt/releases/v0.60.0/cvt-tflite-float.zip"
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.61.0",
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/cvt/releases/v0.61.0/cvt-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/cvt/releases/v0.61.0/cvt-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/cvt/releases/v0.61.0/cvt-tflite-float.zip"
24
  }
25
  }
26
  }