v0.52.0

See https://github.com/qualcomm/ai-hub-models/releases/v0.52.0 for changelog.

README.md

@@ -15,7 +15,7 @@ pipeline_tag: object-detection
 
 YoloR is a machine learning model that predicts bounding boxes and classes of objects in an image.
 
-This is based on the implementation of Yolo-R found [here](https://github.com/WongKinYiu/yolor.git).
+This is based on the implementation of Yolo-R found [here](https://github.com/WongKinYiu/yolor).
 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/src/qai_hub_models/models/yolor) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
 
 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.
@@ -60,21 +60,21 @@ See our repository for [Yolo-R on GitHub](https://github.com/qualcomm/ai-hub-mod
 | Yolo-R | ONNX | w8a16 | Qualcomm® QCM6690 | 1176.44 ms | 102 - 115 MB | CPU
 | Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 17.376 ms | 1 - 355 MB | NPU
 | Yolo-R | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1118.179 ms | 128 - 141 MB | CPU
-| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 7.405 ms | 2 - 304 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 8.495 ms | 2 - 2 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Snapdragon® X Elite | 19.71 ms | 2 - 2 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 12.53 ms | 2 - 359 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 78.591 ms | 1 - 6 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 37.793 ms | 1 - 290 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 19.022 ms | 2 - 5 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8775P | 19.005 ms | 1 - 290 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 19.439 ms | 2 - 6 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 219.17 ms | 2 - 399 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 24.834 ms | 2 - 359 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA7255P | 37.793 ms | 1 - 290 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8295P | 24.351 ms | 0 - 292 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 9.608 ms | 2 - 305 MB | NPU
-| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 26.925 ms | 2 - 318 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 7.394 ms | 2 - 304 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 8.458 ms | 2 - 2 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Snapdragon® X Elite | 19.7 ms | 2 - 2 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 12.489 ms | 0 - 354 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 78.838 ms | 2 - 7 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 37.822 ms | 1 - 289 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 19.007 ms | 2 - 5 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8775P | 18.971 ms | 1 - 289 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 19.787 ms | 1 - 5 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 220.184 ms | 2 - 400 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 24.744 ms | 2 - 359 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA7255P | 37.822 ms | 1 - 289 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8295P | 24.367 ms | 0 - 292 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 9.605 ms | 2 - 303 MB | NPU
+| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 26.657 ms | 2 - 318 MB | NPU
 
 ## License
 * The license for the original implementation of Yolo-R can be found
@@ -82,7 +82,7 @@ See our repository for [Yolo-R on GitHub](https://github.com/qualcomm/ai-hub-mod
 
 ## References
 * [You Only Learn One Representation: Unified Network for Multiple Tasks](https://arxiv.org/abs/2105.04206)
-* [Source Model Implementation](https://github.com/WongKinYiu/yolor.git)
+* [Source Model Implementation](https://github.com/WongKinYiu/yolor)
 
 ## Community
 * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.