Xc@`sddlmZmZmZddlmZmZmZmZm Z m Z m Z m Z m Z mZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZm Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)m*Z*m+Z+ddl,m-Z-ddl.m/Z/ddl0Tddl1Tddl2Tddl3m4Z4m5Z5m6Z6m7Z7m8Z8m9Z9ddl:m;Z;dd l<Z<dd l=m>Z?dd l=m@Z@dd l=mAZAd d d deCd ddZ>d d deCddZDd S(i(tabsolute_importtprint_functiontdivisioni('tCrossentropyCategorical1HottCrossentropyCategorical1HotGradt!CrossentropySoftmax1HotWithBiasDxt%CrossentropySoftmaxArgmax1HotWithBiast LogSoftmaxt#Prepend_scalar_constant_to_each_rowtPrepend_scalar_to_each_rowtSoftmaxt SoftmaxGradtSoftmaxWithBiastbinary_crossentropytcategorical_crossentropytcrossentropy_categorical_1hott"crossentropy_categorical_1hot_gradtcrossentropy_softmax_1hott#crossentropy_softmax_1hot_with_biast&crossentropy_softmax_1hot_with_bias_dxt*crossentropy_softmax_argmax_1hot_with_biast(crossentropy_softmax_max_and_argmax_1hott2crossentropy_softmax_max_and_argmax_1hot_with_biast)crossentropy_to_crossentropy_with_softmaxt3crossentropy_to_crossentropy_with_softmax_with_biast-graph_merge_softmax_with_crossentropy_softmaxt h_softmaxt logsoftmaxt logsoftmax_optprepend_0_to_each_rowtprepend_1_to_each_rowtprepend_scalar_to_each_rowtrelutsoftmaxt softmax_gradt softmax_grapht softmax_optsoftmax_simplifiertsoftmax_with_biastelutconfusion_matrixtsoftsign(topt(tConvOp(t*(tsoftplustsigmoidtsigmoid_inplacetscalar_sigmoidtultra_fast_sigmoidt hard_sigmoid(tbatch_normalizationN(tconv2d(tconv2d_grad_wrt_inputs(tconv3dtvalidc K`sd| ksd| kr'tdnt| jdkretjt| jdddn|d k rtjddd|d kr|}qtd nt||||||||S( sC This function will build the symbolic graph for convolving a mini-batch of a stack of 2D inputs with a set of 2D filters. The implementation is modelled after Convolutional Neural Networks (CNN). Parameters ---------- input: symbolic 4D tensor Mini-batch of feature map stacks, of shape (batch size, input channels, input rows, input columns). See the optional parameter ``input_shape``. filters: symbolic 4D tensor Set of filters used in CNN layer of shape (output channels, input channels, filter rows, filter columns). See the optional parameter ``filter_shape``. input_shape: None, tuple/list of len 4 of int or Constant variable The shape of the input parameter. Optional, possibly used to choose an optimal implementation. You can give ``None`` for any element of the list to specify that this element is not known at compile time. filter_shape: None, tuple/list of len 4 of int or Constant variable The shape of the filters parameter. Optional, possibly used to choose an optimal implementation. You can give ``None`` for any element of the list to specify that this element is not known at compile time. border_mode: str, int or tuple of two int Either of the following: ``'valid'``: apply filter wherever it completely overlaps with the input. Generates output of shape: input shape - filter shape + 1 ``'full'``: apply filter wherever it partly overlaps with the input. Generates output of shape: input shape + filter shape - 1 ``'half'``: pad input with a symmetric border of ``filter rows // 2`` rows and ``filter columns // 2`` columns, then perform a valid convolution. For filters with an odd number of rows and columns, this leads to the output shape being equal to the input shape. ``int``: pad input with a symmetric border of zeros of the given width, then perform a valid convolution. ``(int1, int2)``: pad input with a symmetric border of ``int1`` rows and ``int2`` columns, then perform a valid convolution. subsample: tuple of len 2 Factor by which to subsample the output. Also called strides elsewhere. filter_flip: bool If ``True``, will flip the filter rows and columns before sliding them over the input. This operation is normally referred to as a convolution, and this is the default. If ``False``, the filters are not flipped and the operation is referred to as a cross-correlation. image_shape: None, tuple/list of len 4 of int or Constant variable Deprecated alias for input_shape. filter_dilation: tuple of len 2 Factor by which to subsample (stride) the input. Also called dilation elsewhere. kwargs: Any other keyword arguments are accepted for backwards compatibility, but will be ignored. Returns ------- Symbolic 4D tensor Set of feature maps generated by convolutional layer. Tensor is of shape (batch size, output channels, output rows, output columns) Notes ----- If cuDNN is available, it will be used on the GPU. Otherwise, it is the *CorrMM* convolution that will be used "caffe style convolution". This is only supported in Theano 0.8 or the development version until it is released. The parameter filter_dilation is an implementation of `dilated convolution `_. t imshp_logicalt kshp_logicalsKeyword arguments 'imshp_logical' and 'kshp_logical' for conv2d are not supported anymore (and have not been a reliable way to perform upsampling). That feature is still available by calling theano.tensor.nnet.conv.conv2d() for the time being.isX are now deprecated in `tensor.nnet.abstract_conv.conv2d` interface and will be ignored.t stacklevelisoThe `image_shape` keyword argument to `tensor.nnet.conv2d` is deprecated, it has been renamed to `input_shape`.sDinput_shape and image_shape should not be provided at the same time.N(t ValueErrortlentkeystwarningstwarntstrtNonetabstract_conv2d( tinputtfilterst input_shapet filter_shapet border_modet subsamplet filter_flipt image_shapetfilter_dilationtkwargs((s;/tmp/pip-build-X4mzal/theano/theano/tensor/nnet/__init__.pyR4's Y       cC`s7td|d|d|d|d|d|d|d|S( s This function will build the symbolic graph for applying a transposed convolution over a mini-batch of a stack of 2D inputs with a set of 2D filters. Parameters ---------- input: symbolic 4D tensor Mini-batch of feature map stacks, of shape (batch size, input channels, input rows, input columns). See the optional parameter ``input_shape``. filters: symbolic 4D tensor Set of filters used in CNN layer of shape (input channels, output channels, filter rows, filter columns). See the optional parameter ``filter_shape``. **Note: the order for ``output_channels`` and ``input_channels`` is reversed with respect to ``conv2d``.** output_shape: tuple/list of len 4 of int or Constant variable The shape of the output of ``conv2d_transpose``. The last two elements are allowed to be ``tensor.scalar`` variables. filter_shape: None, tuple/list of len 4 of int or Constant variable The shape of the filters parameter. Optional, possibly used to choose an optimal implementation. You can give ``None`` for any element of the list to specify that this element is not known at compile time. border_mode: str, int or tuple of two int Refers to the ``border_mode`` argument of the corresponding forward (non-transposed) convolution. See the argument description in ``conv2d``. What was ``padding`` for the forward convolution means ``cropping`` the output of the transposed one. ``valid`` corresponds to no cropping, ``full`` to maximal cropping. input_dilation: tuple of len 2 Corresponds to ``subsample`` (also called strides elsewhere) in the non-transposed convolution. filter_flip: bool If ``True``, will flip the filter rows and columns before sliding them over the input. This operation is normally referred to as a convolution, and this is the default. If ``False``, the filters are not flipped and the operation is referred to as a cross-correlation. filter_dilation: tuple of len 2 Factor by which to subsample (stride) the input. Also called dilation elsewhere. Returns ------- Symbolic 4D tensor Set of feature maps generated by the transposed convolution. Tensor is of shape (batch size, output channels, output rows, output columns) Notes ----- If cuDNN is available, it will be used on the GPU. Otherwise, it is the *CorrMM* convolution that will be used "caffe style convolution". This operation is also sometimes called "deconvolution". The parameter filter_dilation is an implementation of `dilated convolution `_. t output_gradRDRERFRGRHRIRK(R5(RCRDt output_shapeRFRGtinput_dilationRIRK((s;/tmp/pip-build-X4mzal/theano/theano/tensor/nnet/__init__.pytconv2d_transposesI (ii(ii(ii(ii(Et __future__RRRtnnetRRRRRRR R R R R RRRRRRRRRRRRRRRRRRR R!R"R#R$R%R&R'R(R)tR*tconvR+tConv3Dt ConvGrad3Dt ConvTransp3DtsigmR-R.R/R0R1R2tbnR3R>t abstract_convR4RBR5R6RAtTrueRP(((s;/tmp/pip-build-X4mzal/theano/theano/tensor/nnet/__init__.pyts$   .  t