from pyeddl.layers.base import Layer
[docs]class Conv2DTranspose(Layer):
"""Transposed convolution layer (sometimes called Deconvolution).
The need for transposed convolutions generally arises
from the desire to use a transformation going in the opposite direction
of a normal convolution, i.e., from something that has the shape of the
output of some convolution to something that has the shape of its input
while maintaining a connectivity pattern that is compatible with
said convolution.
When using this layer as the first layer in a model,
provide the keyword argument `input_shape`
(tuple of integers, does not include the batch axis),
e.g. `input_shape=(128, 128, 3)` for 128x128 RGB pictures
in `data_format="channels_last"`.
Args:
filters: Integer, the dimensionality of the output space
(i.e. the number of output filters in the convolution).
kernel_size: An integer or tuple/list of 2 integers, specifying the
height and width of the 2D convolution window.
Can be a single integer to specify the same value for
all spatial dimensions.
strides: An integer or tuple/list of 2 integers,
specifying the strides of the convolution
along the height and width.
Can be a single integer to specify the same value for
all spatial dimensions.
Specifying any stride value != 1 is incompatible with specifying
any `dilation_rate` value != 1.
padding: one of `"valid"` or `"same"` (case-insensitive).
output_padding: An integer or tuple/list of 2 integers,
specifying the amount of padding along the height and width
of the output tensor.
Can be a single integer to specify the same value for all
spatial dimensions.
The amount of output padding along a given dimension must be
lower than the stride along that same dimension.
If set to `None` (default), the output shape is inferred.
data_format: A string,
one of `"channels_last"` or `"channels_first"`.
The ordering of the dimensions in the inputs.
`"channels_last"` corresponds to inputs with shape
`(batch, height, width, channels)` while `"channels_first"`
corresponds to inputs with shape
`(batch, channels, height, width)`.
It defaults to the `image_data_format` value found in your
dilation_rate: an integer or tuple/list of 2 integers, specifying
the dilation rate to use for dilated convolution.
Can be a single integer to specify the same value for
all spatial dimensions.
Currently, specifying any `dilation_rate` value != 1 is
incompatible with specifying any stride value != 1.
activation: Activation function to use
If you don't specify anything, no activation is applied
(ie. "linear" activation: `a(x) = x`).
use_bias: Boolean, whether the layer uses a bias vector.
kernel_initializer: Initializer for the `kernel` weights matrix
bias_initializer: Initializer for the bias vector
kernel_regularizer: Regularizer function applied to
the `kernel` weights matrix
bias_regularizer: Regularizer function applied to the bias vector
activity_regularizer: Regularizer function applied to
the output of the layer (its "activation").
kernel_constraint: Constraint function applied to the kernel matrix
bias_constraint: Constraint function applied to the bias vector
Input shape:
4D tensor with shape:
`(batch, channels, rows, cols)`
if `data_format` is `"channels_first"`
or 4D tensor with shape:
`(batch, rows, cols, channels)`
if `data_format` is `"channels_last"`.
Output shape:
4D tensor with shape:
`(batch, filters, new_rows, new_cols)`
if `data_format` is `"channels_first"`
or 4D tensor with shape:
`(batch, new_rows, new_cols, filters)`
if `data_format` is `"channels_last"`.
`rows` and `cols` values might have changed due to padding.
If `output_padding` is specified:
```
new_rows = ((rows - 1) * strides[0] + kernel_size[0]
- 2 * padding[0] + output_padding[0])
new_cols = ((cols - 1) * strides[1] + kernel_size[1]
- 2 * padding[1] + output_padding[1])
```
References
- [A guide to convolution arithmetic for deep learning](
https://arxiv.org/abs/1603.07285v1)
- [Deconvolutional Networks](
https://www.matthewzeiler.com/mattzeiler/deconvolutionalnetworks.pdf)
"""
[docs] def __init__(self, filters,
kernel_size,
strides=(1, 1),
padding='valid',
output_padding=None,
data_format=None,
dilation_rate=(1, 1),
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs):
super(Conv2DTranspose, self).__init__()