2VhddlmZddlmZddlmZddlmZddlmZGddeZ edGd d e Z ed Gd d e Z edGdde Z y))backend)ops) keras_export) InputSpec)Dropoutc.eZdZdfd ZddZdZxZS)BaseSpatialDropoutc,t|||||y)Nseednamedtype)super__init__selfrater r r __class__s _/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/layers/regularization/spatial_dropout.pyrzBaseSpatialDropout.__init__ s Dt5Ac|rU|jdkDrFtjj||j|j ||j S|S)Nr) noise_shaper )rrrandomdropout_get_noise_shapeseed_generator)rinputstrainings rcallzBaseSpatialDropout.call sS  A >>))  11&9(( *   rc`|j|j|j|jdS)Nrr r rr!)rs r get_configzBaseSpatialDropout.get_configs(IIIIIIZZ   rNNN)F)__name__ __module__ __qualname__rrr" __classcell__rs@rr r sB rr zkeras.layers.SpatialDropout1Dc*eZdZdZdfd ZdZxZS)SpatialDropout1DaSpatial 1D version of Dropout. This layer performs the same function as Dropout, however, it drops entire 1D feature maps instead of individual elements. If adjacent frames within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective learning rate decrease. In this case, `SpatialDropout1D` will help promote independence between feature maps and should be used instead. Args: rate: Float between 0 and 1. Fraction of the input units to drop. Call arguments: inputs: A 3D tensor. training: Python boolean indicating whether the layer should behave in training mode (applying dropout) or in inference mode (pass-through). Input shape: 3D tensor with shape: `(samples, timesteps, channels)` Output shape: Same as input. Reference: - [Tompson et al., 2014](https://arxiv.org/abs/1411.4280) cNt|||||td|_y)Nr ndim)rrr input_specrs rrzSpatialDropout1D.__init__>s% Dt5A#+rcBtj|}|dd|dfS)Nr)rshaperr input_shapes rrz!SpatialDropout1D._get_noise_shapeBs%ii' A;q>22rr#)r$r%r&__doc__rrr'r(s@rr*r*s:,3rr*zkeras.layers.SpatialDropout2Dc6eZdZdZ dfd ZdZfdZxZS)SpatialDropout2DaHSpatial 2D version of Dropout. This version performs the same function as Dropout, however, it drops entire 2D feature maps instead of individual elements. If adjacent pixels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective learning rate decrease. In this case, `SpatialDropout2D` will help promote independence between feature maps and should be used instead. Args: rate: Float between 0 and 1. Fraction of the input units to drop. data_format: `"channels_first"` or `"channels_last"`. In `"channels_first"` mode, the channels dimension (the depth) is at index 1, in `"channels_last"` mode is it at index 3. It defaults to the `image_data_format` value found in your Keras config file at `~/.keras/keras.json`. If you never set it, then it will be `"channels_last"`. Call arguments: inputs: A 4D tensor. training: Python boolean indicating whether the layer should behave in training mode (applying dropout) or in inference mode (pass-through). Input shape: 4D tensor with shape: `(samples, channels, rows, cols)` if data_format='channels_first' or 4D tensor with shape: `(samples, rows, cols, channels)` if data_format='channels_last'. Output shape: Same as input. Reference: - [Tompson et al., 2014](https://arxiv.org/abs/1411.4280) ct|||||tj||_t d|_y)Nr r-rrrstandardize_data_format data_formatrr/rrr=r r rrs rrzSpatialDropout2D.__init__o: Dt5A"::;G#+rctj|}|jdk(r |d|dddfS|jdk(r |ddd|dfSy)Nchannels_firstrr1 channels_lastr,rr3r=r4s rrz!SpatialDropout2D._get_noise_shapevs`ii'   / /NKNAq9 9    0NAq+a.9 91rcHt|}d|ji}i||SNr=rr"r=r base_configconfigrs rr"zSpatialDropout2D.get_config}4g(* 4++ )+(((rNNNNr$r%r&r6rrr"r'r(s@rr8r8Gs$$NCG,:))rr8zkeras.layers.SpatialDropout3Dc6eZdZdZ dfd ZdZfdZxZS)SpatialDropout3DaZSpatial 3D version of Dropout. This version performs the same function as Dropout, however, it drops entire 3D feature maps instead of individual elements. If adjacent voxels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective learning rate decrease. In this case, SpatialDropout3D will help promote independence between feature maps and should be used instead. Args: rate: Float between 0 and 1. Fraction of the input units to drop. data_format: `"channels_first"` or `"channels_last"`. In `"channels_first"` mode, the channels dimension (the depth) is at index 1, in `"channels_last"` mode is it at index 4. It defaults to the `image_data_format` value found in your Keras config file at `~/.keras/keras.json`. If you never set it, then it will be `"channels_last"`. Call arguments: inputs: A 5D tensor. training: Python boolean indicating whether the layer should behave in training mode (applying dropout) or in inference mode (pass-through). Input shape: 5D tensor with shape: `(samples, channels, dim1, dim2, dim3)` if data_format='channels_first' or 5D tensor with shape: `(samples, dim1, dim2, dim3, channels)` if data_format='channels_last'. Output shape: Same as input. Reference: - [Tompson et al., 2014](https://arxiv.org/abs/1411.4280) ct|||||tj||_t d|_y)Nr r-r;r>s rrzSpatialDropout3D.__init__r?rctj|}|jdk(r |d|ddddfS|jdk(r |dddd|dfSy)NrArr1rBr:rCr4s rrz!SpatialDropout3D._get_noise_shapesdii'   / /NKNAq!< <    0NAq![^< <1rcHt|}d|ji}i||SrErFrGs rr"zSpatialDropout3D.get_configrJrrKrLr(s@rrNrNs$$NCG,=))rrNN) keras.srcrrkeras.src.api_exportrkeras.src.layers.input_specr'keras.src.layers.regularization.dropoutrr r*r8rNrrrXs-1;  .-.$3)$3/$3N-.:)):)/:)z-.:)):)/:)r