v0.32.0

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

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 MobileNet-v3-Small.so filter=lfs diff=lfs merge=lfs -text
 MobileNet-v3-Small_w8a16.so filter=lfs diff=lfs merge=lfs -text
 MobileNet-v3-Small.dlc filter=lfs diff=lfs merge=lfs -text
+DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text

DEPLOYMENT_MODEL_LICENSE.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
+size 109629

LICENSE

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

MobileNet-v3-Small.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65b8a8e7166bc8229e4bc0fb3ebf7f75f46ac8ca138c997df7c3d2e7e7128c2
-size 10184906
+oid sha256:95e0fdaba77d94f84f4ab12771222073dd26e80d64aa05b47bfb2f4cb37bdff6
+size 10189622

README.md

@@ -32,7 +32,7 @@ More details on model performance across various devices, can be found
   - Model checkpoint: Imagenet
   - Input resolution: 224x224
   - Number of parameters: 2.54M
-  - Model size: 9.72 MB
+  - Model size (float): 9.71 MB
 
 | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
@@ -56,15 +56,15 @@ More details on model performance across various devices, can be found
 | MobileNet-v3-Small | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.032 ms | 1 - 19 MB | NPU | [MobileNet-v3-Small.dlc](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.dlc) |
 | MobileNet-v3-Small | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.77 ms | 0 - 51 MB | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
 | MobileNet-v3-Small | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.755 ms | 0 - 48 MB | NPU | [MobileNet-v3-Small.dlc](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.dlc) |
-| MobileNet-v3-Small | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.644 ms | 0 - 41 MB | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
+| MobileNet-v3-Small | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.645 ms | 0 - 17 MB | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
 | MobileNet-v3-Small | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.508 ms | 0 - 35 MB | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
 | MobileNet-v3-Small | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.503 ms | 0 - 32 MB | NPU | [MobileNet-v3-Small.dlc](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.dlc) |
-| MobileNet-v3-Small | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.415 ms | 0 - 34 MB | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
+| MobileNet-v3-Small | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.416 ms | 0 - 33 MB | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
 | MobileNet-v3-Small | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.432 ms | 1 - 20 MB | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
 | MobileNet-v3-Small | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.494 ms | 0 - 20 MB | NPU | [MobileNet-v3-Small.dlc](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.dlc) |
-| MobileNet-v3-Small | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.395 ms | 0 - 25 MB | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
+| MobileNet-v3-Small | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.44 ms | 1 - 24 MB | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
 | MobileNet-v3-Small | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.247 ms | 40 - 40 MB | NPU | [MobileNet-v3-Small.dlc](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.dlc) |
-| MobileNet-v3-Small | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.696 ms | 5 - 5 MB | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
+| MobileNet-v3-Small | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.699 ms | 5 - 5 MB | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |