tf.get_default_graph

简介:
get_default_graph()
    Returns the default graph for the current thread.
    
    The returned graph will be the innermost graph on which a
    `Graph.as_default()` context has been entered, or a global default
    graph if none has been explicitly created.
    
    NOTE: The default graph is a property of the current thread. If you
    create a new thread, and wish to use the default graph in that
    thread, you must explicitly add a `with g.as_default():` in that
    thread's function.
    
    Returns:
      The default `Graph` being used in the current thread.
目录
相关文章
|
2月前
|
TensorFlow 算法框架/工具
【Tensorflow】解决A `Concatenate` layer should be called on a list of at least 2 inputs
在TensorFlow 2.0中,使用Concatenate函数时出现错误,可以通过替换为tf.concat 来解决。
32 4
|
5月前
random.sample(population, k)
random.sample(population, k)
34 0
|
API 数据格式
TensorFlow2._:model.summary() Output Shape为multiple解决方法
TensorFlow2._:model.summary() Output Shape为multiple解决方法
268 0
TensorFlow2._:model.summary() Output Shape为multiple解决方法
|
API
No module named 'plotly.graph_objects'问题解决
No module named 'plotly.graph_objects'问题解决
333 0
No module named 'plotly.graph_objects'问题解决
Can‘t get attribute ‘SiLU‘ on <module ‘torch.nn.modules.activation‘
Can‘t get attribute ‘SiLU‘ on <module ‘torch.nn.modules.activation‘
|
TensorFlow 算法框架/工具
TF版本升级问题:成功解决AttributeError: module tensorflow has no attribute mul
TF版本升级问题:成功解决AttributeError: module tensorflow has no attribute mul
TF版本升级问题:成功解决AttributeError: module tensorflow has no attribute mul
|
算法框架/工具 Windows
|
并行计算
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the
507 0
|
机器学习/深度学习 计算机视觉
成功解决This module was deprecated in version 0.18 in favor of the model_selection module into which all
成功解决This module was deprecated in version 0.18 in favor of the model_selection module into which all