v0.61.0

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

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: pytorch
-license: other
+license: bsd-3-clause
 tags:
 - bu_auto
 - real_time
@@ -16,7 +16,7 @@ pipeline_tag: image-segmentation
 HRNet-W48-OCR is a machine learning model that can segment images from the Cityscape dataset. It has lightweight and hardware-efficient operations and thus delivers significant speedup on diverse hardware platforms
 
 This is based on the implementation of HRNet-W48-OCR found [here](https://github.com/HRNet/HRNet-Semantic-Segmentation).
-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/hrnet_w48_ocr) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
+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/hrnet_w48_ocr) 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.
 
@@ -29,21 +29,21 @@ Below are pre-exported model assets ready for deployment.
 
 | Runtime | Precision | Chipset | SDK Versions | Download |
 |---|---|---|---|---|
-| 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/hrnet_w48_ocr/releases/v0.60.0/hrnet_w48_ocr-onnx-float.zip)
+| 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/hrnet_w48_ocr/releases/v0.61.0/hrnet_w48_ocr-onnx-float.zip)
 
 For more device-specific assets and performance metrics, visit **[HRNet-W48-OCR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/hrnet_w48_ocr)**.
 
 
 ### Option 2: Export with Custom Configurations
 
-Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/hrnet_w48_ocr) Python library to compile and export the model with your own:
+Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/hrnet_w48_ocr) Python library to compile and export the model with your own:
 - Custom weights (e.g., fine-tuned checkpoints)
 - Custom input shapes
 - Target device and runtime configurations
 
 This option is ideal if you need to customize the model beyond the default configuration provided here.
 
-See our repository for [HRNet-W48-OCR on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/hrnet_w48_ocr) for usage instructions.
+See our repository for [HRNet-W48-OCR on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/hrnet_w48_ocr) for usage instructions.
 
 ## Model Details
 
@@ -60,18 +60,18 @@ See our repository for [HRNet-W48-OCR on GitHub](https://github.com/qualcomm/ai-
 ## Performance Summary
 | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
 |---|---|---|---|---|---|---
-| HRNet-W48-OCR | ONNX | float | Snapdragon® X2 Elite | 615.429 ms | 33 - 33 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Snapdragon® X Elite | 987.542 ms | 134 - 134 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 793.461 ms | 25 - 2294 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2056.21 ms | 34 - 2178 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1227.269 ms | 24 - 51 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1115.754 ms | 0 - 136 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Qualcomm® QCS8450 | 2056.21 ms | 34 - 2178 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1894.146 ms | 24 - 51 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 987.542 ms | 134 - 134 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 685.999 ms | 13 - 1133 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite Mobile | 685.999 ms | 13 - 1133 MB | NPU
-| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 532.834 ms | 13 - 1236 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Snapdragon® X2 Elite | 617.735 ms | 32 - 32 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Snapdragon® X Elite | 988.054 ms | 132 - 132 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 802.136 ms | 36 - 2306 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1999.906 ms | 34 - 2177 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1225.897 ms | 24 - 52 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1113.717 ms | 0 - 135 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Qualcomm® QCS8450 | 1999.906 ms | 34 - 2177 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1581.21 ms | 24 - 50 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 988.054 ms | 132 - 132 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 686.836 ms | 17 - 1136 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite Mobile | 686.836 ms | 17 - 1136 MB | NPU
+| HRNet-W48-OCR | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 534.785 ms | 13 - 1238 MB | NPU
 
 ## License
 * The license for the original implementation of HRNet-W48-OCR can be found

release_assets.json

@@ -1,5 +1,5 @@
 {
-    "version": "0.60.0",
+    "version": "0.61.0",
     "precisions": {
         "float": {
             "universal_assets": {
@@ -8,7 +8,7 @@
                         "qairt": "2.45.0.260326154327",
                         "onnx_runtime": "1.27.1"
                     },
-                    "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_w48_ocr/releases/v0.60.0/hrnet_w48_ocr-onnx-float.zip"
+                    "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_w48_ocr/releases/v0.61.0/hrnet_w48_ocr-onnx-float.zip"
                 }
             }
         }