v0.30.5

See https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.

README.md

@@ -36,10 +36,10 @@ More details on model performance across various devices, can be found
 
 | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
-| EfficientViT-l2-seg | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 1681.589 ms | 6 - 316 MB | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
-| EfficientViT-l2-seg | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1884.553 ms | 133 - 985 MB | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
-| EfficientViT-l2-seg | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1222.36 ms | 112 - 1013 MB | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
-| EfficientViT-l2-seg | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2220.252 ms | 144 - 144 MB | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
+| EfficientViT-l2-seg | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 1916.068 ms | 26 - 324 MB | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
+| EfficientViT-l2-seg | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2084.291 ms | 128 - 1009 MB | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
+| EfficientViT-l2-seg | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1203.099 ms | 107 - 1061 MB | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
+| EfficientViT-l2-seg | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2376.256 ms | 144 - 144 MB | NPU | [EfficientViT-l2-seg.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-seg/blob/main/EfficientViT-l2-seg.onnx) |
 
 
 
@@ -103,8 +103,8 @@ Profiling Results
 EfficientViT-l2-seg
 Device                          : cs_8_gen_2 (ANDROID 13)              
 Runtime                         : ONNX                                 
-Estimated inference time (ms)   : 1681.6                               
-Estimated peak memory usage (MB): [6, 316]                             
+Estimated inference time (ms)   : 1916.1                               
+Estimated peak memory usage (MB): [26, 324]                            
 Total # Ops                     : 464                                  
 Compute Unit(s)                 : npu (462 ops) gpu (0 ops) cpu (2 ops)
 ```
@@ -193,13 +193,13 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
 You can also run the demo on-device.
 
 ```bash
-python -m qai_hub_models.models.efficientvit_l2_seg.demo --on-device
+python -m qai_hub_models.models.efficientvit_l2_seg.demo --eval-mode on-device
 ```
 
 **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
 environment, please add the following to your cell (instead of the above).
 ```
-%run -m qai_hub_models.models.efficientvit_l2_seg.demo -- --on-device
+%run -m qai_hub_models.models.efficientvit_l2_seg.demo -- --eval-mode on-device
 ```