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
 DETR-ResNet101.so filter=lfs diff=lfs merge=lfs -text
 DETR-ResNet101.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

DETR-ResNet101.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1dc01c6d136a4fce3d1edb2acd7995f568c4522b3b3437460890268c45a9ce
-size 241938885
+oid sha256:38b4311d0378f6598434044922c5261a32fc5646c2ed11462ccf0af2ede8035d
+size 241972926

LICENSE

@@ -0,0 +1,2 @@
+The license of the original trained model can be found at https://github.com/facebookresearch/detr/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

@@ -30,7 +30,7 @@ More details on model performance across various devices, can be found
   - Model checkpoint: ResNet101
   - Input resolution: 480x480
   - Number of parameters: 60.3M
-  - Model size: 230 MB
+  - Model size (float): 230 MB
 
 | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
@@ -54,15 +54,15 @@ More details on model performance across various devices, can be found
 | DETR-ResNet101 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 38.968 ms | 5 - 133 MB | NPU | [DETR-ResNet101.dlc](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.dlc) |
 | DETR-ResNet101 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 26.615 ms | 0 - 50 MB | NPU | [DETR-ResNet101.tflite](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.tflite) |
 | DETR-ResNet101 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 25.097 ms | 5 - 54 MB | NPU | [DETR-ResNet101.dlc](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.dlc) |
-| DETR-ResNet101 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 25.039 ms | 1 - 303 MB | NPU | [DETR-ResNet101.onnx](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.onnx) |
+| DETR-ResNet101 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 25.251 ms | 0 - 279 MB | NPU | [DETR-ResNet101.onnx](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.onnx) |
 | DETR-ResNet101 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 19.21 ms | 97 - 368 MB | NPU | [DETR-ResNet101.tflite](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.tflite) |
 | DETR-ResNet101 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 18.071 ms | 5 - 139 MB | NPU | [DETR-ResNet101.dlc](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.dlc) |
-| DETR-ResNet101 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 18.215 ms | 5 - 170 MB | NPU | [DETR-ResNet101.onnx](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.onnx) |
+| DETR-ResNet101 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 18.192 ms | 5 - 174 MB | NPU | [DETR-ResNet101.onnx](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.onnx) |
 | DETR-ResNet101 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 17.805 ms | 0 - 243 MB | NPU | [DETR-ResNet101.tflite](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.tflite) |
 | DETR-ResNet101 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 17.741 ms | 12 - 143 MB | NPU | [DETR-ResNet101.dlc](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.dlc) |
-| DETR-ResNet101 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 17.529 ms | 5 - 135 MB | NPU | [DETR-ResNet101.onnx](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.onnx) |
+| DETR-ResNet101 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 18.185 ms | 0 - 129 MB | NPU | [DETR-ResNet101.onnx](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.onnx) |
 | DETR-ResNet101 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 27.379 ms | 320 - 320 MB | NPU | [DETR-ResNet101.dlc](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.dlc) |
-| DETR-ResNet101 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 26.354 ms | 114 - 114 MB | NPU | [DETR-ResNet101.onnx](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.onnx) |
+| DETR-ResNet101 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 26.496 ms | 115 - 115 MB | NPU | [DETR-ResNet101.onnx](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.onnx) |