Refactor inference engine and task management: Remove obsolete inference engine and ONNX engine files, update inference processing to utilize batch handling, and enhance task management structure in documentation. Adjust paths for task specifications to align with new directory organization.

engines/tensorrt_engine.pxd

@@ -0,0 +1,24 @@
+from engines.inference_engine cimport InferenceEngine
+
+
+cdef class TensorRTEngine(InferenceEngine):
+
+    cdef public object context
+
+    cdef public object d_input
+    cdef public object d_output
+    cdef str input_name
+    cdef object input_shape
+
+    cdef object h_output
+    cdef str output_name
+    cdef object output_shape
+
+    cdef object stream
+
+
+    cdef tuple get_input_shape(self)
+
+    cdef int get_batch_size(self)
+
+    cdef run(self, input_data)