Transposed 2D convolution layer (sometimes called 2D Deconvolution).
tf.compat.v1.layers.Conv2DTranspose( filters, kernel_size, strides=(1, 1), padding='valid', data_format='channels_last', activation=None, use_bias=True, kernel_initializer=None, bias_initializer=tf.zeros_initializer(), kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None, trainable=True, name=None, **kwargs )
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.
| ||Integer, the dimensionality of the output space (i.e. the number of filters in the convolution).|
| ||A tuple or list of 2 positive integers specifying the spatial dimensions of the filters. Can be a single integer to specify the same value for all spatial dimensions.|
| ||A tuple or list of 2 positive integers specifying the strides of the convolution. Can be a single integer to specify the same value for all spatial dimensions.|
| || one of |
| || A string, one of |
| ||Activation function. Set it to None to maintain a linear activation.|
| ||Boolean, whether the layer uses a bias.|
| ||An initializer for the convolution kernel.|
| ||An initializer for the bias vector. If None, the default initializer will be used.|
| ||Optional regularizer for the convolution kernel.|
| ||Optional regularizer for the bias vector.|
| ||Optional regularizer function for the output.|
| || Optional projection function to be applied to the kernel after being updated by an |
| || Optional projection function to be applied to the bias after being updated by an |
| || Boolean, if |
| ||A string, the name of the layer.|
| ||DEPRECATED FUNCTION|
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.