python字典python-neural-network.rar

""" - - - - - -- - - - - - - - - - - - - - - - - - - - - - - Name - - CNN - Convolution Neural Network For Photo Recognizing Goal - - Recognize Handing Writing 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 - - - - - -- - - - - - - - - - - - - - - - - - - - - - - """ import pickle import numpy as np from matplotlib import pyplot as plt class CNN: def __init__( self, conv1_get, size_p1, bp_num1, bp_num2, bp_num3, rate_w=0.2, rate_t=0.2 ): """ :param conv1_get: [a,c,d], size, number, step of convolution kernel :param size_p1: pooling size :param bp_num1: units number of flatten layer :param bp_num2: units number of hidden layer :param bp_num3: units number of output layer :param rate_w: rate of weight learning :param rate_t: rate of threshold learning """ self.num_bp1 = bp_num1 self.num_bp2 = bp_num2 self.num_bp3 = bp_num3 self.conv1 = conv1_get[:2] self.step_conv1 = conv1_get[2] self.size_pooling1 = size_p1 self.rate_weight = rate_w self.rate_thre = rate_t rng = np.random.default_rng() self.w_conv1 = [ np.asmatrix(-1 * rng.random((self.conv1[0], self.conv1[0])) + 0.5) for i in range(self.conv1[1]) ] self.wkj = np.asmatrix(-1 * rng.random((self.num_bp3, self.num_bp2)) + 0.5) self.vji = np.asmatrix(-1 * rng.random((self.num_bp2, self.num_bp1)) + 0.5) self.thre_conv1 = -2 * rng.random(self.conv1[1]) + 1 self.thre_bp2 = -2 * rng.random(self.num_bp2) + 1 self.thre_bp3 = -2 * rng.random(self.num_bp3) + 1 def save_model(self, save_path): # save model dict with pickle model_dic = { "num_bp1": self.num_bp1, "num_bp2": self.num_bp2, "num_bp3": self.num_bp3, "conv1": self.conv1, "step_conv1": self.step_conv1, "size_pooling1": self.size_pooling1, "rate_weight": self.rate_weight, "rate_thre": self.rate_thre, "w_conv1": self.w_conv1, "wkj": self.wkj, "vji": self.vji, "thre_conv1": self.thre_conv1, "thre_bp2": self.thre_bp2, "thre_bp3": self.thre_bp3, } with open(save_path, "wb") as f: pickle.dump(model_dic, f) print(f"Model saved: {save_path}") @classmethod def read_model(cls, model_path): # read saved model with open(model_path, "rb") as f: model_dic = pickle.load(f) # noqa: S301 conv_get = model_dic.get("conv1") conv_get.append(model_dic.get("step_conv1")) size_p1 = model_dic.get("size_pooling1") bp1 = model_dic.get("num_bp1") bp2 = model_dic.get("num_bp2") bp3 = model_dic.get("num_bp3") r_w = model_dic.get("rate_weight") r_t = model_dic.get("rate_thre") # create model instance conv_ins = CNN(conv_get, size_p1, bp1, bp2, bp3, r_w, r_t) # modify model parameter conv_ins.w_conv1 = model_dic.get("w_conv1") conv_ins.wkj = model_dic.get("wkj") conv_ins.vji = model_dic.get("vji") conv_ins.thre_conv1 = model_dic.get("thre_conv1") conv_ins.thre_bp2 = model_dic.get("thre_bp2") conv_ins.thre_bp3 = model_dic.get("thre_bp3") return conv_ins def sig(self, x): return 1 / (1 + np.exp(-1 * x)) def do_round(self, x): return round(x, 3) def convolute(self, data, convs, w_convs, thre_convs, conv_step): # convolution process size_conv = convs[0] num_conv = convs[1] size_data = np.shape(data)[0] # get the data slice of original image data, data_focus data_focus = [] for i_focus in range(0, size_data - size_conv + 1, conv_step): for j_focus in range(0, size_data - size_conv + 1, conv_step): focus = data[ i_focus : i_focus + size_conv, j_focus : j_focus + size_conv ] data_focus.append(focus) # calculate the feature map of every single kernel, and saved as list of matrix data_featuremap = [] size_feature_map = int((size_data - size_conv) / conv_step + 1) for i_map in range(num_conv): featuremap = [] for i_focus in range(len(data_focus)): net_focus = ( np.sum(np.multiply(data_focus[i_focus], w_convs[i_map])) - thre_convs[i_map] ) featuremap.append(self.sig(net_focus)) featuremap = np.asmatrix(featuremap).reshape( size_feature_map, size_feature_map ) data_featuremap.append(featuremap) # expanding the data slice to One dimenssion focus1_list = [] for each_focus in data_focus: focus1_list.extend(self.Expand_Mat(each_focus)) focus_list = np.asarray(focus1_list) return focus_list, data_featuremap def pooling(self, featuremaps, size_pooling, pooling_type="average_pool"): # pooling process size_map = len(featuremaps[0]) size_pooled = int(size_map / size_pooling) featuremap_pooled = [] for i_map in range(len(featuremaps)): feature_map = featuremaps[i_map] map_pooled = [] for i_focus in range(0, size_map, size_pooling): for j_focus in range(0, size_map, size_pooling): focus = feature_map[ i_focus : i_focus + size_pooling, j_focus : j_focus + size_pooling, ] if pooling_type == "average_pool": # average pooling map_pooled.append(np.average(focus)) elif pooling_type == "max_pooling": # max pooling map_pooled.append(np.max(focus)) map_pooled = np.asmatrix(map_pooled).reshape(size_pooled, size_pooled) featuremap_pooled.append(map_pooled) return featuremap_pooled def _expand(self, data): # expanding three dimension data to one dimension list data_expanded = [] for i in range(len(data)): shapes = np.shape(data[i]) data_listed = data[i].reshape(1, shapes[0] * shapes[1]) data_listed = data_listed.getA().tolist()[0] data_expanded.extend(data_listed) data_expanded = np.asarray(data_expanded) return data_expanded def _expand_mat(self, data_mat): # expanding matrix to one dimension list data_mat = np.asarray(data_mat) shapes = np.shape(data_mat) data_expanded = data_mat.reshape(1, shapes[0] * shapes[1]) return data_expanded def _calculate_gradient_from_pool( self, 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] """ pd_all = [] i_pool = 0 for i_map in range(num_map): pd_conv1 = np.ones((size_map, size_map)) for i in range(0, size_map, size_pooling): for j in range(0, size_map, size_pooling): pd_conv1[i : i + size_pooling, j : j + size_pooling] = pd_pool[ i_pool ] i_pool = i_pool + 1 pd_conv2 = np.multiply( pd_conv1, np.multiply(out_map[i_map],