[Backend] cuda normalize and permute, cuda concat, optimized ppcls, ppdet & ppseg (#546)

* cuda normalize and permute, cuda concat

* add use cuda option for preprocessor

* ppyoloe use cuda normalize

* ppseg use cuda normalize

* add proclib cuda in processor base

* ppcls add use cuda preprocess api

* ppcls preprocessor set gpu id

* fix pybind

* refine ppcls preprocessing use gpu logic

* fdtensor device id is -1 by default

* refine assert message

Co-authored-by: heliqi <1101791222@qq.com>

python/fastdeploy/vision/classification/ppcls/__init__.py

@@ -35,6 +35,13 @@ class PaddleClasPreprocessor:
         """
         return self._preprocessor.run(input_ims)
 
+    def use_gpu(self, gpu_id=-1):
+        """Use CUDA preprocessors
+
+        :param: gpu_id: GPU device id
+        """
+        return self._preprocessor.use_gpu(gpu_id)
+
 
 class PaddleClasPostprocessor:
     def __init__(self, topk=1):