a Sic @sddZddlmmZddlmZddlmZddl m Z ddl m Z e dGdd d ej ZdS) zContains the Dropout layer.N)backend) base_layer)control_flow_util) keras_exportzkeras.layers.DropoutcsHeZdZdZd fdd ZddZdddZd d Zfd d ZZ S)DropoutaApplies Dropout to the input. The Dropout layer randomly sets input units to 0 with a frequency of `rate` at each step during training time, which helps prevent overfitting. Inputs not set to 0 are scaled up by 1/(1 - rate) such that the sum over all inputs is unchanged. Note that the Dropout layer only applies when `training` is set to True such that no values are dropped during inference. When using `model.fit`, `training` will be appropriately set to True automatically, and in other contexts, you can set the kwarg explicitly to True when calling the layer. (This is in contrast to setting `trainable=False` for a Dropout layer. `trainable` does not affect the layer's behavior, as Dropout does not have any variables/weights that can be frozen during training.) >>> tf.random.set_seed(0) >>> layer = tf.keras.layers.Dropout(.2, input_shape=(2,)) >>> data = np.arange(10).reshape(5, 2).astype(np.float32) >>> print(data) [[0. 1.] [2. 3.] [4. 5.] [6. 7.] [8. 9.]] >>> outputs = layer(data, training=True) >>> print(outputs) tf.Tensor( [[ 0. 1.25] [ 2.5 3.75] [ 5. 6.25] [ 7.5 8.75] [10. 0. ]], shape=(5, 2), dtype=float32) Args: rate: Float between 0 and 1. Fraction of the input units to drop. noise_shape: 1D integer tensor representing the shape of the binary dropout mask that will be multiplied with the input. For instance, if your inputs have shape `(batch_size, timesteps, features)` and you want the dropout mask to be the same for all timesteps, you can use `noise_shape=(batch_size, 1, features)`. seed: A Python integer to use as random seed. Call arguments: inputs: Input tensor (of any rank). training: Python boolean indicating whether the layer should behave in training mode (adding dropout) or in inference mode (doing nothing). Nc sftjfd|i|t|ttfrJd|kr8dksJntd|d||_||_||_d|_ dS)NseedrzInvalid value z7 received for `rate`, expected a value between 0 and 1.T) super__init__ isinstanceintfloat ValueErrorrate noise_shapersupports_masking)selfrrrkwargs __class___/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/layers/regularization/dropout.pyr Ps$ zDropout.__init__cCsT|jdurdSt|}g}t|jD]"\}}||durB||n|q&t|SN)rtfshape enumerateappendconvert_to_tensor)rinputsconcrete_inputs_shaperivaluerrr_get_noise_shape\s  zDropout._get_noise_shapecs8|durt}fdd}t||fdd}|S)NcsjjjdS)N)r)_random_generatordropoutrr"rrrrrdropped_inputsosz$Dropout.call..dropped_inputscs tSr)ridentityr)rrruzDropout.call..)rlearning_phaser smart_cond)rrtrainingr&outputrr%rcallksz Dropout.callcCs|Srr)r input_shaperrrcompute_output_shapeyszDropout.compute_output_shapecs8|j|j|jd}t}tt|t|S)N)rrr)rrrr get_configdictlistitems)rconfig base_configrrrr1|s  zDropout.get_config)NN)N) __name__ __module__ __qualname____doc__r r"r.r0r1 __classcell__rrrrrs 2  r)r:tensorflow.compat.v2compatv2rkerasr keras.enginer keras.utilsr tensorflow.python.util.tf_exportrBaseRandomLayerrrrrrs