在AARC64上构建Tensorflow Lite时出错

嗨，我是Tensorflow的新手，我正在尝试为Pine64 A64+板构建Tensorflow Lite。我按照上的说明操作，遇到了很多错误，例如：

./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:55:78: error: cannot convert ‘int32x4_t {aka __vector(4) int}’ to ‘int8x16_t {aka __vector(16) signed char}’ in assignment
 #define vld1q_dup_s8x4(src) vld1q_dup_s32(reinterpret_cast<const int32*>(src))
                                                                              ^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:5994:30: note: in expansion of macro ‘vld1q_dup_s8x4’
           input_bank_c_reg = vld1q_dup_s8x4(

/tensorflow/lite/kernels/internal/optimized/depthwiseconv\u uint8\u 3x3\u filter.h:55:78:错误：无法将赋值中的'int32x4\u t{aka\u向量（4）int}'转换为'int8x16\u t{aka\u向量（16）有符号字符'
#定义vld1q_dup_s8x4（src）vld1q_dup_s32（重新解释强制转换（src））
^
./tensorflow/lite/kernels/internal/optimized/depthwiseconv_uint8_3x3_filter.h:5994:30:注意：在宏“vld1q_dup_s8x4”的展开中
输入_bank_c_reg=vld1q_dup_s8x4(

---

我做错了什么？

我认为这应该已经修复，您可以同步到head并重试吗？

是的，已经修复。请参阅