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-ResNet50.so filter=lfs diff=lfs merge=lfs -text
 DETR-ResNet50.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-ResNet50.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26bcde32aa7338b7fe04523fff487bbba58d126f59c0469d40e8921bd83caf24
-size 165884436
+oid sha256:dc3631db166a9f4488dbadd85d568afd19108c0302e63928217f595385d704d0
+size 165909411

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

@@ -29,8 +29,8 @@ More details on model performance across various devices, can be found
 - **Model Stats:**
   - Model checkpoint: ResNet50
   - Input resolution: 480x480
-  - Number of parameters: 41.3M
-  - Model size: 158 MB
+  - Number of parameters: 41.4M
+  - Model size (float): 158 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-ResNet50 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 27.25 ms | 4 - 178 MB | NPU | [DETR-ResNet50.dlc](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.dlc) |
 | DETR-ResNet50 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 20.268 ms | 0 - 48 MB | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
 | DETR-ResNet50 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 18.693 ms | 5 - 41 MB | NPU | [DETR-ResNet50.dlc](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.dlc) |
-| DETR-ResNet50 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 18.798 ms | 1 - 242 MB | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
+| DETR-ResNet50 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 18.566 ms | 1 - 211 MB | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
 | DETR-ResNet50 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 14.094 ms | 0 - 228 MB | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
 | DETR-ResNet50 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 12.942 ms | 5 - 183 MB | NPU | [DETR-ResNet50.dlc](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.dlc) |
-| DETR-ResNet50 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 13.654 ms | 4 - 155 MB | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
+| DETR-ResNet50 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 13.592 ms | 4 - 156 MB | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
 | DETR-ResNet50 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 13.162 ms | 0 - 217 MB | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
 | DETR-ResNet50 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 12.481 ms | 5 - 118 MB | NPU | [DETR-ResNet50.dlc](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.dlc) |
-| DETR-ResNet50 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 10.57 ms | 5 - 134 MB | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
+| DETR-ResNet50 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 10.397 ms | 5 - 134 MB | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
 | DETR-ResNet50 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 20.558 ms | 263 - 263 MB | NPU | [DETR-ResNet50.dlc](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.dlc) |
-| DETR-ResNet50 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.535 ms | 78 - 78 MB | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
+| DETR-ResNet50 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.376 ms | 77 - 77 MB | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |