Upload README.md with huggingface_hub

README.md

@@ -16,7 +16,7 @@ tags:
 
 DETR is a machine learning model that can detect objects (trained on COCO dataset).
 
-This model is an implementation of DETR-ResNet50-DC5 found [here](https://github.com/facebookresearch/detr).
+This model is an implementation of DETR-ResNet50-DC5 found [here]({source_repo}).
 This repository provides scripts to run DETR-ResNet50-DC5 on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/detr_resnet50_dc5).
@@ -31,14 +31,23 @@ More details on model performance across various devices, can be found
   - Number of parameters: 42.2M
   - Model size: 159 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| DETR-ResNet50-DC5 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 75.052 ms | 0 - 2 MB | FP16 | NPU | [DETR-ResNet50-DC5.tflite](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.tflite) |
+| DETR-ResNet50-DC5 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 92.231 ms | 0 - 96 MB | FP16 | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
+| DETR-ResNet50-DC5 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 68.196 ms | 0 - 493 MB | FP16 | NPU | [DETR-ResNet50-DC5.tflite](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.tflite) |
+| DETR-ResNet50-DC5 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 81.134 ms | 2 - 505 MB | FP16 | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
+| DETR-ResNet50-DC5 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 74.434 ms | 0 - 2 MB | FP16 | NPU | [DETR-ResNet50-DC5.tflite](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.tflite) |
+| DETR-ResNet50-DC5 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 85.586 ms | 0 - 3 MB | FP16 | NPU | [DETR-ResNet50-DC5.tflite](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.tflite) |
+| DETR-ResNet50-DC5 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 74.502 ms | 0 - 3 MB | FP16 | NPU | [DETR-ResNet50-DC5.tflite](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.tflite) |
+| DETR-ResNet50-DC5 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 80.512 ms | 0 - 3 MB | FP16 | NPU | [DETR-ResNet50-DC5.tflite](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.tflite) |
+| DETR-ResNet50-DC5 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 91.938 ms | 0 - 455 MB | FP16 | NPU | [DETR-ResNet50-DC5.tflite](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.tflite) |
+| DETR-ResNet50-DC5 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 49.532 ms | 0 - 253 MB | FP16 | NPU | [DETR-ResNet50-DC5.tflite](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.tflite) |
+| DETR-ResNet50-DC5 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 66.336 ms | 2 - 295 MB | FP16 | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
+| DETR-ResNet50-DC5 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 65.232 ms | 83 - 83 MB | FP16 | NPU | [DETR-ResNet50-DC5.onnx](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.onnx) |
 
 
 
-| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
-| ---|---|---|---|---|---|---|---|
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 111.119 ms | 0 - 2 MB | FP16 | NPU |  [DETR-ResNet50-DC5.tflite](https://huggingface.co/qualcomm/DETR-ResNet50-DC5/blob/main/DETR-ResNet50-DC5.tflite) 
-
-
 
 ## Installation
 
@@ -94,7 +103,17 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.detr_resnet50_dc5.export
 ```
-
+```
+Profiling Results
+------------------------------------------------------------
+DETR-ResNet50-DC5
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 75.1                   
+Estimated peak memory usage (MB): [0, 2]                 
+Total # Ops                     : 789                    
+Compute Unit(s)                 : NPU (789 ops)          
+```
 
 
 ## How does this work?
@@ -192,15 +211,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on DETR-ResNet50-DC5's performance across various devices [here](https://aihub.qualcomm.com/models/detr_resnet50_dc5).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of DETR-ResNet50-DC5 can be found
-  [here](https://github.com/facebookresearch/detr/blob/main/LICENSE).
-- The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
+* The license for the original implementation of DETR-ResNet50-DC5 can be found [here](https://github.com/facebookresearch/detr/blob/main/LICENSE).
+* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
+
+
 
 ## References
 * [End-to-End Object Detection with Transformers](https://arxiv.org/abs/2005.12872)
 * [Source Model Implementation](https://github.com/facebookresearch/detr)
 
+
+
 ## Community
 * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).