module 'tensorflow_core._api.v2.config' has no attribute 'list_physical_devices'

This error occurs when you are trying to use the `list_physical_devices` function from the `tensorflow_core._api.v2.config` module, but this function is not available in the module.

To fix this error, you can try using the `list_physical_devices` function from the `tensorflow` module instead. Here's an example:

import tensorflow as tf

# get list of all available physical devices
physical_devices = tf.config.list_physical_devices()

# print the list of physical devices
print(physical_devices)

This should print a list of all the physical devices available on your system that can be used for running TensorFlow computations.

相关问题

AttributeError: module 'tensorflow_core._api.v2.config' has no attribute 'experimental_list_devices'

This error occurs when you try to use the method `experimental_list_devices()` in TensorFlow 2 but it is not available in the module `tensorflow_core._api.v2.config`. This method was experimental and has been removed in TensorFlow 2.

To solve this error, you can use the method `list_physical_devices()` instead. Here's an example:

import tensorflow as tf

physical_devices = tf.config.list_physical_devices('GPU') 
print("Number of GPUs available: ", len(physical_devices)) 

for device in physical_devices:
    print(device)

This will print the number of available GPUs and their names. You can also use the method `list_logical_devices()` to get a list of all logical devices available.

AttributeError: module 'tensorflow_core._api.v2.compat.v2' has no attribute 'Session'

这个错误通常是因为 TensorFlow 2.x 版本中没有 `Session` 这个类。而在 TensorFlow 1.x 版本中，我们需要使用 `Session` 来启动计算图。如果你在 TensorFlow 2.x 版本中想要使用 `Session`，你可以使用 `tf.compat.v1.Session()` 来创建一个 TensorFlow 1.x 兼容的会话。但是，建议你修改你的代码以适应 TensorFlow 2.x 的执行方式，例如使用 Eager Execution 或者使用 `tf.function`。