|View source on GitHub|
Locally-connected layer for 2D inputs.
Compat aliases for migration
See Migration guide for more details.
tf.keras.layers.LocallyConnected2D( filters, kernel_size, strides=(1, 1), padding='valid', data_format=None, 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, implementation=1, **kwargs )
LocallyConnected2D layer works similarly to the
Conv2D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input.
Note: layer attributes cannot be modified after the layer has been called once (except the
# apply a 3x3 unshared weights convolution with 64 output filters on a 32x32 image # with `data_format="channels_last"`: model = Sequential() model.add(LocallyConnected2D(64, (3, 3), input_shape=(32, 32, 3))) # now model.output_shape == (None, 30, 30, 64) # notice that this layer will consume (30*30)*(3*3*3*64) + (30*30)*64 parameters # add a 3x3 unshared weights convolution on top, with 32 output filters: model.add(LocallyConnected2D(32, (3, 3))) # now model.output_shape == (None, 28, 28, 32)
| ||Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution).|
| ||An integer or tuple/list of 2 integers, specifying the width and height of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions.|
| ||An integer or tuple/list of 2 integers, specifying the strides of the convolution along the width and height. Can be a single integer to specify the same value for all spatial dimensions.|
| || Currently only support |
| || A string, one of |
| || Activation function to use. If you don't specify anything, no activation is applied (ie. "linear" activation: |
| ||Boolean, whether the layer uses a bias vector.|
| || Initializer for the |
| ||Initializer for the bias vector.|
| || Regularizer function applied to the |
| ||Regularizer function applied to the bias vector.|
| ||Regularizer function applied to the output of the layer (its "activation").|
| ||Constraint function applied to the kernel matrix.|
| ||Constraint function applied to the bias vector.|
| || implementation mode, either |
How to choose:
where "large" stands for large input/output activations (i.e. many
It is recommended to benchmark each in the setting of interest to pick the most efficient one (in terms of speed and memory usage). Correct choice of implementation can lead to dramatic speed improvements (e.g. 50X), potentially at the expense of RAM.
4D tensor with shape:
(samples, channels, rows, cols) if data_format='channels_first' or 4D tensor with shape:
(samples, rows, cols, channels) if data_format='channels_last'.
4D tensor with shape:
(samples, filters, new_rows, new_cols) if data_format='channels_first' or 4D tensor with shape:
(samples, new_rows, new_cols, filters) if data_format='channels_last'.
cols values might have changed due to padding.
© 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.