Xc@`sdZddlmZmZmZddlZddlZddljZddl m Z ddl Z dZ e j dZdddd d ZdS( sk Contains a wrapper function for tensor.nnet.ConvOp, which can be used to perform generic 2D convolution. i(tabsolute_importtprint_functiontdivisionN(tconvsrestructuredtext enstheano.tensor.signal.convtvalidicK`st|jdkst|jdks*t|r|r|jdkrR|d}nd}dt|d}|jdkr|d} nd} |d} nd\} } d\}}|jdkr|jd} nd} |jdkr|jd} nd} tjdtj| dg|jd} tj|| dd}tjdtj| dg|jd}tj||dd}t j d|d |dd |dd |d | d | d||}|||}|jdkr4|jdkr4t j j jrtj dddntj|jddj}n<|jdksR|jdkrptj|jddj}n|S(s signal.conv.conv2d performs a basic 2D convolution of the input with the given filters. The input parameter can be a single 2D image or a 3D tensor, containing a set of images. Similarly, filters can be a single 2D filter or a 3D tensor, corresponding to a set of 2D filters. Shape parameters are optional and will result in faster execution. Parameters ---------- input : Symbolic theano tensor for images to be filtered. Dimensions: ([num_images], image height, image width) filters : Symbolic theano tensor for convolution filter(s). Dimensions: ([num_filters], filter height, filter width) border_mode: {'valid', 'full'} See scipy.signal.convolve2d. subsample Factor by which to subsample output. image_shape : tuple of length 2 or 3 ([num_images,] image height, image width). filter_shape : tuple of length 2 or 3 ([num_filters,] filter height, filter width). kwargs See theano.tensor.nnet.conv.conv2d. Returns ------- symbolic 2D,3D or 4D tensor Tensor of filtered images, with shape ([number images,] [number filters,] image height, image width). iiiiitndimit output_modetdxtdytimshptkshptnkerntbsizestheano.tensor.signal.conv2d() now outputs a 2d tensor when both inputs are 2d. To disable this warning, set the Theano flag warn.signal_conv2d_interface to Falset stackleveltoutdim(ii(ii(iN(NN(NN(RtAssertionErrorttupletNonetshapettensortjointstacktreshapeRtConvOpttheanotconfigtwarntsignal_conv2d_interfacetwarningstflattentT(tinputtfilterst image_shapet filter_shapet border_modet subsampletkargsR R R R t sym_bsizet sym_nkerntnew_input_shapetinput4Dtnew_filter_shapet filters4Dtoptoutput((s9/tmp/pip-build-X4mzal/theano/theano/tensor/signal/conv.pytconv2dsH"      ++ (ii(t__doc__t __future__RRRRRt theano.tensorRttheano.tensor.nnetRtloggingt __docformat__t getLoggert_loggerRR.(((s9/tmp/pip-build-X4mzal/theano/theano/tensor/signal/conv.pyts