neural_network.convolution_neural_network¶

– - - - - - - - - - - - - - - - - - - - - - -

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¶

Module Contents¶

class neural_network.convolution_neural_network.CNN(conv1_get, size_p1, bp_num1, bp_num2, bp_num3, rate_w=0.2, rate_t=0.2)¶

_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]

_expand(data)¶

_expand_mat(data_mat)¶

convolute(data, convs, w_convs, thre_convs, conv_step)¶

convolution(data)¶

do_round(x)¶

pooling(featuremaps, size_pooling, pooling_type='average_pool')¶

predict(datas_test)¶

classmethod read_model(model_path)¶

save_model(save_path)¶

sig(x)¶

train(patterns, datas_train, datas_teach, n_repeat, error_accuracy, draw_e=bool)¶

conv1¶

num_bp1¶

num_bp2¶

num_bp3¶

rate_thre¶

rate_weight¶

size_pooling1¶

step_conv1¶

thre_bp2¶

thre_bp3¶

thre_conv1¶

vji¶

w_conv1¶

wkj¶