tensorflow.python.eager.core._FallbackException: This function does not handle the case of the path

最新推荐文章于 2023-04-04 13:39:55 发布

原创

最新推荐文章于 2023-04-04 13:39:55 发布 · 2.6k 阅读

1 ·

CC 4.0 BY-SA版权

在TensorFlow训练神经网络时，可能会遇到`_FallbackException`和`InvalidArgumentError`，特别是关于`Nan in summary histogram`的问题。这通常是由于损失函数计算中的log操作遇到0值或者学习率设置不恰当导致。解决方案包括使用`tf.clip_by_value`避免log(0)，以及调整学习率。

大体报错：

错误一：

File "/home/ac/anaconda3/envs/tf-gpu/lib/python3.7/site-packages/tensorflow/python/ops/gen_summary_ops.py", line 464, in write_histogram_summary

tld.op_callbacks, writer, step, tag, values)

tensorflow.python.eager.core._FallbackException: This function does not handle the case of the path where all inputs are not already EagerTensors.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):

错误二：

tensorflow.python.framework.errors_impl.InvalidArgumentError: Nan in summary histogram for: block1_conv2/kernel_0 [Op:WriteHistogramSummary]

2020-07-07 20:45:58.272736: W tensorflow/core/kernels/data/generator_dataset_op.cc:103] Error occurred when finalizing GeneratorDataset iterator: Failed precondition: Python interpreter state is not initialized. The process may be terminated.

[[{ {node PyFunc}}]]