keras tensor基本操作

tensor操作

reshape

keras.backend.reshape(x,shape)

Arguments

• x:Tensor or variable
• shape:Target shape tuple

permute_dimensions

keras.backend.permute_dimensions(x,pattern)

Arguments

• pattern: A tuple of dimension indices eg.(0,2,1)

resize_images

keras.backend.resize_images(x, height_factor, width_factor, data_format, interpolation='nearest')

Resizes the images contained in a 4D tensor.

Arguments

• x: Tensor or variable to resize.
• height_factor: Positive integer.
• width_factor: Positive integer.
• data_format: string, "channels_last" or "channels_first".
• interpolation: A string, one of nearest or bilinear.

resize_volumes

keras.backend.resize_volumes(x, depth_factor, height_factor, width_factor, data_format)

Resizes the volume contained in a 5D tensor.

Arguments

• x: Tensor or variable to resize.
• depth_factor: Positive integer.
• height_factor: Positive integer.
• width_factor: Positive integer.
• data_format: string, "channels_last" or "channels_first".

arange

keras.backend.arange(start, stop=None, step=1, dtype='int32')

Creates a 1D tensor containing a sequence of integers.

Arguments

• start: Start value.
• stop: Stop value.
• step: Difference between two successive values.
• dtype: Integer dtype to use.

tile

keras.backend.tile(x, n)

Creates a tensor by tiling x by n.return a tiled tensor .网格化tensor,像瓷砖一样铺展开来，类似于repeat复制

Arguments

• x: A tensor or variable
• n: A list of integer. The length must be the
• same as the number of dimensions in x.

batch_flatten

keras.backend.batch_flatten(x)

Turn a nD tensor into a 2D tensor with same 0th dimension.
In other words, it flattens each data samples of a batch.按batch展开tensor。

expand_dims

keras.backend.expand_dims(x, axis=-1)

在指定的轴上进行维度拓展

Arguments

• x: A tensor or variable.
• axis: Position where to add a new axis.

squeeze

keras.backend.squeeze(x,axis)

Removes a 1-dimension from the tensor at index "axis".
降低指定轴上的维度

cast

keras.backend.cast(x, dtype)

Casts a tensor to a different dtype and returns it.
You can cast a Keras variable but it still returns a Keras tensor.
数据类型转化