v0.32.0

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

.gitattributes

@@ -39,3 +39,4 @@ PoseDetector.so filter=lfs diff=lfs merge=lfs -text
 PoseLandmarkDetector.so filter=lfs diff=lfs merge=lfs -text
 MediaPipe-Pose-Estimation_PoseDetector.dlc filter=lfs diff=lfs merge=lfs -text
 MediaPipe-Pose-Estimation_PoseLandmarkDetector.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/zmurez/MediaPipePyTorch/blob/master/LICENSE.
+The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.

MediaPipe-Pose-Estimation_PoseDetector.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1399eec4e120d8968fa3750c771ff4132dc5b6fe3697b57bc3d548722eb8d2
-size 3310899
+oid sha256:ea3f84f3077fea4db9b7881b5af79dd1dd90fd1d66b6e333fddd029a29e1d9ff
+size 3318046

MediaPipe-Pose-Estimation_PoseLandmarkDetector.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49b7104ba37ffefcc2018608d900b76f299e989dd20f1299f215efd39992c4a
-size 13542910
+oid sha256:408f28fb9451e831993b6264b78401d3d32a90d0a52ed219c7dcefca81f8e9b4
+size 13554777

README.md

@@ -29,10 +29,10 @@ More details on model performance across various devices, can be found
 - **Model Type:** Model_use_case.pose_estimation
 - **Model Stats:**
   - Input resolution: 256x256
-  - Number of parameters (MediaPipePoseDetector): 815K
-  - Model size (MediaPipePoseDetector): 3.14 MB
-  - Number of parameters (MediaPipePoseLandmarkDetector): 3.37M
-  - Model size (MediaPipePoseLandmarkDetector): 12.9 MB
+  - Number of parameters (PoseDetector): 815K
+  - Model size (PoseDetector) (float): 3.14 MB
+  - Number of parameters (PoseLandmarkDetector): 3.36M
+  - Model size (PoseLandmarkDetector) (float): 12.9 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
 | PoseDetector | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.423 ms | 0 - 17 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
 | PoseDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.779 ms | 0 - 30 MB | NPU | [MediaPipe-Pose-Estimation.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.tflite) |
 | PoseDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.752 ms | 0 - 19 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
-| PoseDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.92 ms | 0 - 13 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
+| PoseDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.911 ms | 0 - 14 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
 | PoseDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.564 ms | 0 - 30 MB | NPU | [MediaPipe-Pose-Estimation.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.tflite) |
 | PoseDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.549 ms | 0 - 28 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
-| PoseDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.646 ms | 0 - 35 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
+| PoseDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.648 ms | 0 - 37 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
 | PoseDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.56 ms | 0 - 18 MB | NPU | [MediaPipe-Pose-Estimation.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.tflite) |
 | PoseDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.448 ms | 0 - 18 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
-| PoseDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.696 ms | 0 - 25 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
+| PoseDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.678 ms | 2 - 25 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
 | PoseDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.908 ms | 6 - 6 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
-| PoseDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.943 ms | 0 - 0 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
+| PoseDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.942 ms | 0 - 0 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
 | PoseLandmarkDetector | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3.202 ms | 0 - 35 MB | NPU | [MediaPipe-Pose-Estimation.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.tflite) |
 | PoseLandmarkDetector | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 3.128 ms | 1 - 23 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
 | PoseLandmarkDetector | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.999 ms | 0 - 46 MB | NPU | [MediaPipe-Pose-Estimation.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.tflite) |
@@ -85,15 +85,15 @@ More details on model performance across various devices, can be found
 | PoseLandmarkDetector | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.387 ms | 0 - 23 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
 | PoseLandmarkDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.803 ms | 0 - 79 MB | NPU | [MediaPipe-Pose-Estimation.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.tflite) |
 | PoseLandmarkDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.805 ms | 0 - 47 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
-| PoseLandmarkDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 1.104 ms | 0 - 41 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
+| PoseLandmarkDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 1.082 ms | 0 - 41 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
 | PoseLandmarkDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.608 ms | 0 - 57 MB | NPU | [MediaPipe-Pose-Estimation.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.tflite) |
 | PoseLandmarkDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.596 ms | 1 - 48 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
-| PoseLandmarkDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.763 ms | 0 - 55 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
+| PoseLandmarkDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.76 ms | 0 - 48 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
 | PoseLandmarkDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.56 ms | 0 - 39 MB | NPU | [MediaPipe-Pose-Estimation.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.tflite) |
 | PoseLandmarkDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.575 ms | 1 - 28 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
-| PoseLandmarkDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.796 ms | 1 - 30 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
+| PoseLandmarkDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.683 ms | 1 - 32 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
 | PoseLandmarkDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.021 ms | 29 - 29 MB | NPU | [MediaPipe-Pose-Estimation.dlc](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.dlc) |
-| PoseLandmarkDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.163 ms | 7 - 7 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |
+| PoseLandmarkDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.13 ms | 8 - 8 MB | NPU | [MediaPipe-Pose-Estimation.onnx](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipe-Pose-Estimation.onnx) |