[Model] Support DINO & DETR and add PaddleDetectionModel class (#1837)

* 添加paddleclas模型

* 更新README_CN

* 更新README_CN

* 更新README

* update get_model.sh

* update get_models.sh

* update paddleseg models

* update paddle_seg models

* update paddle_seg models

* modified test resources

* update benchmark_gpu_trt.sh

* add paddle detection

* add paddledetection to benchmark

* modified benchmark cmakelists

* update benchmark scripts

* modified benchmark function calling

* modified paddledetection documents

* add PaddleDetectonModel

* reset examples/paddledetection

* resolve conflict

* update pybind

* resolve conflict

* fix bug

* delete debug mode

* update checkarch log

* update trt inputs example

* Update README.md

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>

benchmark/cpp/README.md

@@ -186,6 +186,10 @@ benchmark: ./benchmark -[info|diff|check|dump|mem] -model xxx -config_path xxx -
 ```bash  
 ./benchmark --model ResNet50_vd_infer --config_path config/config.gpu.paddle_trt.fp16.txt --trt_shapes 1,3,224,224:1,3,224,224:1,3,224,224 --names inputs --dtypes FP32
 ```
+- TensorRT/Paddle-TRT多输入示例：  
+```bash 
+./benchmark --model rtdetr_r50vd_6x_coco --trt_shapes 1,2:1,2:1,2:1,3,640,640:1,3,640,640:1,3,640,640:1,2:1,2:1,2 --names im_shape:image:scale_factor --shapes 1,2:1,3,640,640:1,2  --config_path config/config.gpu.paddle_trt.fp32.txt --dtypes FP32:FP32:FP32
+```
 - 支持FD全部后端和全部模型格式：--model_file, --params_file(optional), --model_format
 ```bash
 # ONNX模型示例
@@ -206,4 +210,4 @@ benchmark: ./benchmark -[info|diff|check|dump|mem] -model xxx -config_path xxx -
 - 显示模型的输入信息： --info
 ```bash
 ./benchmark --info --model picodet_l_640_coco_lcnet --config_path config/config.arm.lite.fp32.txt 
-```
+```