&Vf. d dl mZ d dl mZ d dlmZ d dlmZ d dlmZ d dl m
Z
ed G d d e Z d
S ) )backend)ops) keras_export) InputSpec)Layer)argument_validationzkeras.layers.UpSampling3Dc @ e Zd ZdZd fd Zd Zd Z fdZd Z xZ S )
UpSampling3Da Upsampling layer for 3D inputs.
Repeats the 1st, 2nd and 3rd dimensions
of the data by `size[0]`, `size[1]` and `size[2]` respectively.
Example:
>>> input_shape = (2, 1, 2, 1, 3)
>>> x = np.ones(input_shape)
>>> y = keras.layers.UpSampling3D(size=(2, 2, 2))(x)
>>> y.shape
(2, 2, 4, 2, 3)
Args:
size: Int, or tuple of 3 integers.
The upsampling factors for dim1, dim2 and dim3.
data_format: A string,
one of `"channels_last"` (default) or `"channels_first"`.
The ordering of the dimensions in the inputs.
`"channels_last"` corresponds to inputs with shape
`(batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)`
while `"channels_first"` corresponds to inputs with shape
`(batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)`.
When unspecified, uses
`image_data_format` value found in your Keras config file at
`~/.keras/keras.json` (if exists) else `"channels_last"`.
Defaults to `"channels_last"`.
Input shape:
5D tensor with shape:
- If `data_format` is `"channels_last"`:
`(batch_size, dim1, dim2, dim3, channels)`
- If `data_format` is `"channels_first"`:
`(batch_size, channels, dim1, dim2, dim3)`
Output shape:
5D tensor with shape:
- If `data_format` is `"channels_last"`:
`(batch_size, upsampled_dim1, upsampled_dim2, upsampled_dim3,
channels)`
- If `data_format` is `"channels_first"`:
`(batch_size, channels, upsampled_dim1, upsampled_dim2,
upsampled_dim3)`
r r Nc t j di | t j | | _ t j |dd | _ t d | _ d S )N size )ndim )
super__init__r standardize_data_format data_formatr standardize_tupler r
input_spec)selfr r kwargs __class__s e/var/www/html/software/conda/lib/python3.11/site-packages/keras/src/layers/reshaping/up_sampling3d.pyr zUpSampling3D.__init__8 s_ ""6"""":;GG'9$6JJ #+++ c | j dk rs|d | j d |d z nd }|d | j d |d z nd }|d | j d |d z nd }|d |d |||fS |d | j d |d z nd }|d | j d |d z nd }|d | j d |d z nd }|d ||||d fS )Nchannels_firstr r r )r r )r input_shapedim1dim2dim3s r compute_output_shapez!UpSampling3D.compute_output_shape> sI / / / q>- ! {1~--
q>- ! {1~--
q>- ! {1~--
NKND$E E q>- ! {1~--
q>- ! {1~--
q>- ! {1~--
ND$k!nE Er c | || j d | j d | j d | j S )Nr r r )_resize_volumesr r )r inputss r callzUpSampling3D.callb s: ## DIaL$)A, ! d>N
r c n | j | j d}t }i ||S )N)r r )r r r
get_config)r config base_configr s r r, zUpSampling3D.get_configg s: )D4DEEgg((** (+(((r c Z |dk rGt j ||d }t j ||d }t j ||d }|S |dk rGt j ||d }t j ||d }t j ||d }|S t d| ) ak Resizes the volume contained in a 5D tensor.
Args:
x: Tensor or variable to resize.
depth_factor: Positive integer.
height_factor: Positive integer.
width_factor: Positive integer.
data_format: One of `"channels_first"`, `"channels_last"`.
Returns:
Resized tensor.
r r )axisr r!
channels_lastr zInvalid data_format: )r repeat
ValueError)r x depth_factor
height_factor width_factorr outputs r r( z UpSampling3D._resize_volumesl s * * *Z>>FZ 1===FM
O
+
+Z>>FZ 1===FM B[ B BCC Cr )r N)
__name__
__module__ __qualname____doc__r r& r* r, r(
__classcell__)r s @r r
r
s + +Z, , , , , , "F "F "FH
) ) ) ) )
D D D D D D Dr r
N) keras.srcr r keras.src.api_exportr keras.src.layers.input_specr keras.src.layers.layerr keras.src.utilsr r
r r r rC s - - - - - - 1 1 1 1 1 1 ( ( ( ( ( ( / / / / / / )**|D |D |D |D |D5 |D |D +*|D |D |Dr