分类标签归档：keras
import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense,Dropout,Convolution2D,MaxPooling2D,Flatten # Flatten扁平化
from keras.optimizers import Adam# 载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_dat我们有时候训练集的数据不够时，可以尝试把一张图片做做变换，生成多张图片。
from keras.preprocessing.image import ImageDataGenerator, array_to_img ,img_to_array, load_img
import numpy as np
from keras.applications.vgg16 import VGG16
from keras.models import Sequential
from keras.layers import Conv2D,MaxPool2D,Activation,Dropout,Flatten,Dense
from keras.optimizers import SGD
from keras.preprocessing.image import ImageDataGenerator,img_to_array,load_img
import numpy as np
#VGG16是用image
import keras
from keras.models import Sequential
from keras.layers import Conv2D,MaxPool2D,Dense,Dropout,Flatten
from keras.optimizers import Adam
from keras.preprocessing.image import load_img,ImageDataGenerator,img_to_array
# 定义模型
model = Sequential()
model.add(Conv2D(input_shape=(150,150,3),fimport numpy as np
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten, Reshape
from keras.layers import Conv2D, Conv2DTranspose, UpSampling2D
from keras.layers import LeakyReLU, Dropout
from keras.layers import BatchNormalization
from keras.preprocessing.image import load_img, img_to_array
#from scipy.misc import imsave # 最新版本的imsvae方法被弃用了
# from imageio import imwrite,imread
from imageio import imwrite as imsave
import numpy as np
from scipy.optimize import fmin_l_bfgs_b
import time
import matplotlib.pyplot as plt
import keras
import numpy as np
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense
# 生成随机点
x_data = np.random.rand(100)
noise = np.random.normal(0,0.01,x_data.shape)
y_data = x_data*0.1+0.5+noise
# 显示
plt.scatter(x_data,y_data)
plt.show()
# 构建序构建模型
# 构建一个线性模型
d = tf.Variable(np.random.rand(1)) # 截距
k = tf.Variable(np.random.rand(1)) #斜率
y = k*x_data + d # 映射函数
网络设置
# 二次代价函数
loss = tf.losses.mean_squared_error(y_data, y)
# 定义一个梯度下降法优化器
optimizer = tf.train.GradientDescentOptimizer(0.4) # 经测试0.3~0.7之间较合适
# 最小化代价函数
train