v0.32.0

See https://github.com/quic/ai-hub-models/releases/v0.32.0 for changelog.

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 EfficientViT-l2-cls.so filter=lfs diff=lfs merge=lfs -text
 EfficientViT-l2-cls.dlc filter=lfs diff=lfs merge=lfs -text
+DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text

EfficientViT-l2-cls_w8a16.onnx → DEPLOYMENT_MODEL_LICENSE.pdf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbcd1ff0560a6a54520f8e6a154ae185c0a5fd6b40cfc236e5a538e750b299cf
-size 255783504
+oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
+size 109629

EfficientViT-l2-cls.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e54d6e5bcf689338cc3d3087f33253064aec38ab20383fb46223fea84ce160b
-size 254885534
+oid sha256:99f75e591eb1bb2c90360418623ffc63990b3f30502d525159c6aa26b57f12cf
+size 254898665

LICENSE

@@ -0,0 +1,2 @@
+The license of the original trained model can be found at https://github.com/CVHub520/efficientvit/blob/main/LICENSE.
+The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.

README.md

@@ -31,7 +31,7 @@ More details on model performance across various devices, can be found
 - **Model Stats:**
   - Model checkpoint: Imagenet
   - Input resolution: 224x224
-  - Number of parameters: 64M
+  - Number of parameters: 63.7M
   - Model size (float): 243 MB
 
 | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
@@ -46,16 +46,15 @@ More details on model performance across various devices, can be found
 | EfficientViT-l2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 9.255 ms | 1 - 88 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
 | EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.181 ms | 0 - 394 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
 | EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 7.084 ms | 0 - 23 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
-| EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 28.474 ms | 0 - 311 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
+| EfficientViT-l2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 28.507 ms | 0 - 381 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
 | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.032 ms | 0 - 251 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
 | EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.166 ms | 1 - 120 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
-| EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 19.93 ms | 1 - 170 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
+| EfficientViT-l2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 19.925 ms | 1 - 171 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
 | EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.648 ms | 0 - 226 MB | NPU | [EfficientViT-l2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.tflite) |
 | EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 4.485 ms | 1 - 177 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
-| EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 17.741 ms | 1 - 139 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
+| EfficientViT-l2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 17.662 ms | 1 - 138 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
 | EfficientViT-l2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.151 ms | 697 - 697 MB | NPU | [EfficientViT-l2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.dlc) |
-| EfficientViT-l2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 30.201 ms | 130 - 130 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |
-| EfficientViT-l2-cls | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 240.878 ms | 99 - 99 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls_w8a16.onnx) |
+| EfficientViT-l2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 30.211 ms | 130 - 130 MB | NPU | [EfficientViT-l2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-l2-cls/blob/main/EfficientViT-l2-cls.onnx) |