Fix incorrect values in recorded_allocation on BE machines (#303)

Use base class version of AllocateFromTail() instead of derived class
version in FlatBufferVectorToTfLiteTypeArray() to solve the issue
Signed-off-by: NKun-Lu <kun.lu@ibm.com>

tensorflow/lite/micro/micro_allocator.cc

@@ -370,8 +370,8 @@ TfLiteStatus FlatBufferVectorToTfLiteTypeArray(
     // Big-endian architecture can not use the same memory layout as
     // flatbuffers::Vector<kFlatBufferVectorType>. Allocate from the tail and
     // copy values from the flatbuffer into the newly allocated chunk.
-    kTfLiteArrayType* array =
-        reinterpret_cast<kTfLiteArrayType*>(allocator->AllocateFromTail(
+    kTfLiteArrayType* array = reinterpret_cast<kTfLiteArrayType*>(
+        allocator->SimpleMemoryAllocator::AllocateFromTail(
             TfLiteIntArrayGetSizeInBytes(flatbuffer_array->size()),
             alignof(kTfLiteArrayType)));
     if (array == nullptr) {