我尝试构建并运行tensorflow lite示例(最小) .
构建正常,但运行此程序时出错 .
为什么会出现此错误?
使用的模型是对tensorflow的自定义模型训练和使用toco转换tensorflow lite .
root@90f212114f89:/tensorflow# bazel-bin/tensorflow/contrib/lite/examples/minimal/minimal /root/DNNSE/model/tflite_model.lite
tensorflow/contrib/lite/kernels/reduce.cc:107 current >= 0 && current < input_num_dims was not true.
tensorflow/contrib/lite/kernels/reduce.cc:107 current >= 0 && current < input_num_dims was not true.
tensorflow/contrib/lite/kernels/reduce.cc:107 current >= 0 && current < input_num_dims was not true.
tensorflow/contrib/lite/kernels/reduce.cc:107 current >= 0 && current < input_num_dims was not true.
Node 8 failed to prepare.
Error at tensorflow/contrib/lite/examples/minimal/minimal.cc:59
节点8未能准备好 . < - 此错误抛出解释器PrepareOpsStartingAt()函数 .
我认为模型转换中的一些错误.tflite
我该如何调试此问题?
我在下面使用了构建选项 .
bazel build ... --compilation_mode=dbg -s
任何其他有用的构建选项?