neural_network.convolution_neural_network ========================================= .. py:module:: neural_network.convolution_neural_network .. autoapi-nested-parse:: - - - - - -- - - - - - - - - - - - - - - - - - - - - - - Name - - CNN - Convolution Neural Network For Photo Recognizing Goal - - Recognize Handwriting Word Photo Detail: Total 5 layers neural network * Convolution layer * Pooling layer * Input layer layer of BP * Hidden layer of BP * Output layer of BP Author: Stephen Lee Github: 245885195@qq.com Date: 2017.9.20 - - - - - -- - - - - - - - - - - - - - - - - - - - - - - Classes ------- .. autoapisummary:: neural_network.convolution_neural_network.CNN Module Contents --------------- .. py:class:: CNN(conv1_get, size_p1, bp_num1, bp_num2, bp_num3, rate_w=0.2, rate_t=0.2) .. py:method:: _calculate_gradient_from_pool(out_map, pd_pool, num_map, size_map, size_pooling) calculate the gradient from the data slice of pool layer pd_pool: list of matrix out_map: the shape of data slice(size_map*size_map) return: pd_all: list of matrix, [num, size_map, size_map] .. py:method:: _expand(data) .. py:method:: _expand_mat(data_mat) .. py:method:: convolute(data, convs, w_convs, thre_convs, conv_step) .. py:method:: convolution(data) .. py:method:: do_round(x) .. py:method:: pooling(featuremaps, size_pooling, pooling_type='average_pool') .. py:method:: predict(datas_test) .. py:method:: read_model(model_path) :classmethod: .. py:method:: save_model(save_path) .. py:method:: sig(x) .. py:method:: train(patterns, datas_train, datas_teach, n_repeat, error_accuracy, draw_e=bool) .. py:attribute:: conv1 .. py:attribute:: num_bp1 .. py:attribute:: num_bp2 .. py:attribute:: num_bp3 .. py:attribute:: rate_thre :value: 0.2 .. py:attribute:: rate_weight :value: 0.2 .. py:attribute:: size_pooling1 .. py:attribute:: step_conv1 .. py:attribute:: thre_bp2 .. py:attribute:: thre_bp3 .. py:attribute:: thre_conv1 .. py:attribute:: vji .. py:attribute:: w_conv1 .. py:attribute:: wkj