Hugging Face's logo

qualcomm
/
CVT

Other
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
bf87c14
·
verified ·
1 Parent(s): 0d148dc

v0.48.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

Files changed (1) hide show
  1. README.md +39 -40
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/quic/ai-hub-models/blob/main/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.47.0/cvt-onnx-float.zip)
31
- | ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.47.0/cvt-onnx-w8a16_mixed_fp16.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.47.0/cvt-qnn_dlc-float.zip)
33
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.47.0/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/quic/ai-hub-models/blob/main/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/quic/ai-hub-models/blob/main/qai_hub_models/models/cvt) for usage instructions.
48
 
49
  ## Model Details
50
 
@@ -60,39 +60,38 @@ See our repository for [CVT on GitHub](https://github.com/quic/ai-hub-models/blo
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
- | CVT | ONNX | float | Snapdragon® X Elite | 287.315 ms | 18 - 18 MB | NPU
64
- | CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 227.134 ms | 8 - 2577 MB | NPU
65
- | CVT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 336.234 ms | 0 - 26 MB | NPU
66
- | CVT | ONNX | float | Qualcomm® QCS9075 | 327.451 ms | 7 - 10 MB | NPU
67
- | CVT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 189.979 ms | 4 - 2222 MB | NPU
68
- | CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 173.494 ms | 8 - 2259 MB | NPU
69
- | CVT | ONNX | float | Snapdragon® X2 Elite | 186.137 ms | 20 - 20 MB | NPU
70
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® X Elite | 365.903 ms | 16 - 16 MB | NPU
71
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 303.459 ms | 15 - 1609 MB | NPU
72
- | CVT | ONNX | w8a16_mixed_fp16 | Qualcomm® QCS8550 (Proxy) | 400.69 ms | 13 - 2070 MB | NPU
73
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite For Galaxy Mobile | 263.913 ms | 12 - 1133 MB | NPU
74
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 217.984 ms | 16 - 1268 MB | NPU
75
- | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® X2 Elite | 221.965 ms | 18 - 18 MB | NPU
76
- | CVT | QNN_DLC | float | Snapdragon® X Elite | 277.336 ms | 7 - 7 MB | NPU
77
- | CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 224.075 ms | 4 - 2551 MB | NPU
78
- | CVT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 420.883 ms | 0 - 2185 MB | NPU
79
- | CVT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 334.853 ms | 8 - 10 MB | NPU
80
- | CVT | QNN_DLC | float | Qualcomm® SA8775P | 291.401 ms | 1 - 2187 MB | NPU
81
- | CVT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 426.183 ms | 7 - 2650 MB | NPU
82
- | CVT | QNN_DLC | float | Qualcomm® SA7255P | 420.883 ms | 0 - 2185 MB | NPU
83
- | CVT | QNN_DLC | float | Qualcomm® SA8295P | 331.888 ms | 0 - 2239 MB | NPU
84
- | CVT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 183.305 ms | 7 - 2172 MB | NPU
85
- | CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 166.578 ms | 7 - 2258 MB | NPU
86
- | CVT | QNN_DLC | float | Snapdragon® X2 Elite | 179.712 ms | 7 - 7 MB | NPU
87
- | CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 226.653 ms | 0 - 2563 MB | NPU
88
- | CVT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 426.132 ms | 0 - 2194 MB | NPU
89
- | CVT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 333.195 ms | 0 - 4 MB | NPU
90
- | CVT | TFLITE | float | Qualcomm® SA8775P | 931.204 ms | 0 - 2193 MB | NPU
91
- | CVT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 456.96 ms | 1 - 2731 MB | NPU
92
- | CVT | TFLITE | float | Qualcomm® SA7255P | 426.132 ms | 0 - 2194 MB | NPU
93
- | CVT | TFLITE | float | Qualcomm® SA8295P | 337.862 ms | 0 - 2290 MB | NPU
94
- | CVT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 188.748 ms | 0 - 2243 MB | NPU
95
- | CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 182.012 ms | 0 - 2288 MB | NPU
96
 
97
  ## License
98
  * 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/main/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.48.0/cvt-onnx-float.zip)
31
+ | ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.48.0/cvt-onnx-w8a16_mixed_fp16.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.48.0/cvt-qnn_dlc-float.zip)
33
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.48.0/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/main/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/main/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 | 183.019 ms | 20 - 20 MB | NPU
64
+ | CVT | ONNX | float | Snapdragon® X Elite | 288.642 ms | 18 - 18 MB | NPU
65
+ | CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 227.053 ms | 8 - 2577 MB | NPU
66
+ | CVT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 331.882 ms | 0 - 24 MB | NPU
67
+ | CVT | ONNX | float | Qualcomm® QCS9075 | 327.526 ms | 7 - 10 MB | NPU
68
+ | CVT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 190.833 ms | 0 - 2218 MB | NPU
69
+ | CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 183.548 ms | 8 - 2259 MB | NPU
70
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® X2 Elite | 223.535 ms | 17 - 17 MB | NPU
71
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® X Elite | 364.569 ms | 16 - 16 MB | NPU
72
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 308.333 ms | 15 - 1611 MB | NPU
73
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite For Galaxy Mobile | 263.664 ms | 14 - 1174 MB | NPU
74
+ | CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 217.599 ms | 16 - 1268 MB | NPU
75
+ | CVT | QNN_DLC | float | Snapdragon® X2 Elite | 181.045 ms | 7 - 7 MB | NPU
76
+ | CVT | QNN_DLC | float | Snapdragon® X Elite | 280.327 ms | 7 - 7 MB | NPU
77
+ | CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 232.914 ms | 5 - 2551 MB | NPU
78
+ | CVT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 420.107 ms | 1 - 2187 MB | NPU
79
+ | CVT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 321.73 ms | 8 - 11 MB | NPU
80
+ | CVT | QNN_DLC | float | Qualcomm® SA8775P | 291.527 ms | 1 - 2187 MB | NPU
81
+ | CVT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 448.203 ms | 5 - 2647 MB | NPU
82
+ | CVT | QNN_DLC | float | Qualcomm® SA7255P | 420.107 ms | 1 - 2187 MB | NPU
83
+ | CVT | QNN_DLC | float | Qualcomm® SA8295P | 332.897 ms | 0 - 2240 MB | NPU
84
+ | CVT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 183.082 ms | 7 - 2172 MB | NPU
85
+ | CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 167.215 ms | 7 - 2258 MB | NPU
86
+ | CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 225.117 ms | 0 - 2557 MB | NPU
87
+ | CVT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 426.739 ms | 0 - 2194 MB | NPU
88
+ | CVT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 335.078 ms | 0 - 4 MB | NPU
89
+ | CVT | TFLITE | float | Qualcomm® SA8775P | 296.259 ms | 0 - 2193 MB | NPU
90
+ | CVT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 465.477 ms | 0 - 2733 MB | NPU
91
+ | CVT | TFLITE | float | Qualcomm® SA7255P | 426.739 ms | 0 - 2194 MB | NPU
92
+ | CVT | TFLITE | float | Qualcomm® SA8295P | 339.762 ms | 0 - 2290 MB | NPU
93
+ | CVT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 186.793 ms | 0 - 2235 MB | NPU
94
+ | CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 171.033 ms | 0 - 2286 MB | NPU
 
95
 
96
  ## License
97
  * The license for the original implementation of CVT can be found