from __future__ import print_function import keras from keras.datasets import mnist from keras.models import Model from keras.layers import Input, Activation, add, Dense, Flatten, Dropout, Multiply, Embedding, Lambda from keras.layers import Conv2D, MaxPooling2D,PReLU from keras import backend as K import numpy as np import sys import scipy.misc from keras.optimizers import SGD, Adam batch_size = 128 num_classes = 10 epochs = 50 #isCenterloss = True isCenterloss = False # input image dimensions img_rows, img_cols = 28, 28 # the data, shuffled and split between train and test sets (x_train, y_train), (x_test, y_test) = mnist.load_data() if K.image_data_format() == 'channels_first': x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols) x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols) input_shape = (1, img_rows, img_cols) else: x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1) x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1) input_shape = (img_rows, img_cols, 1) x_train = x_train.astype('float32') x_test = x_test.astype('float32') x_train /= 255 x_test /= 255 print('x_train shape:', x_train.shape) print(x_train.shape[0], 'train samples') print(x_test.shape[0], 'test samples') for i in range(10): x=x_train[y_train==i] for j in range(np.max(x.shape)): scipy.misc.imsave('G:\\毕业论文\\train\\'+str(i)+'_'+str(j)+'.jpg', x[j])
python中将手写数据数组转换为图片输入出来
猜你喜欢
转载自blog.csdn.net/qq_25964837/article/details/79810328
今日推荐
周排行