def nn_add_one_layer(input, insize, outsize,activation_function=None):
W = tf.Varaible(tf.truncated_normal((insize,outsize)),dtype=tf.float32)
b = tf.Variable(tf.zeros([1, outsize]) + 0.1)
if activation_function is None:
return tf.nn.relu(tf.matmul(input,W)+b)
else:
return activation_function(tf.matmul(input,W)+b)
def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Varaible(initial)
t1 = tf.Variable(test_list) t2 = tf.Variable(test_np) print(t1) print(t2) print(type(t1)) print(type(t2)) # %% t1 = tf.constant(test_list) t2 = tf.Variable(test_list) # t3 = tf.constant(t2) t4 = tf.Varaible(t1) # %% t1 = tf.convert_to_tensor(test_list) t2 = tf.convert_to_tensor(test_np) t3 = tf.Variable(test_list) t4 = tf.convert_to_tensor(t3) print(type(t3)) print(type(t4)) # %% t1 = tf.constant(test_list) t2 = tf.constant(test_list)
import tensorflow as tf
import numpy as np
import matplotlib as plt
num_points = 1000
vectors_set=[]
for i in range(num_points):
x1 = np.random.normal(0.0,0.55)
y1 = x1*0.1+0.3+np.random.normal(0.0,0.03)
vectors_set.append([x1, y1])
x_data = [v[0] for v in vectors_set]
y_data = [v[1] for v in vectors_set]
w = tf.Varaible(tf.random_uniform([1], -1.0, 1.0))
b = tf.Variable(tf.zeros([1]))
y = w*x_data+b
loss = tf.reduce_sean(tf.square(y - y_data))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
for i in range(8):
sess.run(train)
print(sess.run(w), sess.run(b))
plt.plot(x_data, y_data, 'ro')
W3 = tf.Variable(tf.random_normal([3,3,64,128],stddev=0.01))
L3 = tf.nn.conv2d(L2,W3,strides=[1,1,1,1],padding = 'SAME')
L3 = tf.nn.relu(L3)
L3 = tf.nn.max_pool(L3, ksize=[1,2,2,1],strides=[1,2,2,1], padding='SAME')
L3 = tf.nn.dropout(L3,keep_prob=keep_prob)
L3 = tf.reshape(L3,[-1,128*4*4])
W4 = tf.get_variable("W4",shape=[128*4*4,625],initializer=tf.contrib.layers.xavier_initializer())
b = tf.Variable(tf.random_normal([625]))
L4 = tf.nn.relu(tf.matmul(L3,W4)+b)
L4 = tf.nn.dropout(L4,keep_prop=keep_prob)
W5 = tf.get_variable("W5",shape=[625,10],initializer=tf.conrib.layers.xavier_initializer())
b2 = tf.Varaible(tf.random_normal([10]))
hypothesis = tf.matmul(L4,W5)+b2
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=hypothesis,labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
training_epoch = 15
batch_size = 100
for epoch in range(training_epoch):
avg_cost = 0
total_batch = int(mnist.train.num_examples / batch_size)
for i in range(total_batch):
reader = tf.TextLineReader() key, value = reader.read(filename_queue) #Default values, in case of empty columns, Also specifies the type of the decoded result. record_defaults = [[0.], [0.], [0.], [0.]] xy = tf.decode_csv(value, record_defulats=record_defaults) #collect batches of csf in train_x_batch, train_y_batch = \tf.train.batch([xy.[0:-1], xy[-1:]], batch_size = 10) #placeholder for a tensor that will be always fed X = tf.placeholder(tf.float32, shape = [None, 3]) Y = tf.placeholder(tf.flaot32, shpae = [None, 1]) W = tf.Variable(tf.random_normal([3, 1]), name = 'weight') b = tf.Varaible(tf.random_normal([1]), name = 'bias') #Hypothesis hypothesis = tf.matmul(X, W) + b #Simplified cost/loss function cost = tf.reduce_mean(tf.square(hypothesis - Y)) #Minimize optimizer = tf.train.GradientDescentOptimizer(learning_rate = 1e-5) train = optimizer.minimize(cost) #Launch the graph in a session sess = tf.Session() #Initialize global variables in the graph sess.run(tf.global_variables_initializer())
# Generator G_Weight1 = tf.Variable(tf.random_normal([128, 256], stddev = 0.01)) G_Weight2 = tf.Variable(tf.random_normal([256, 28 * 28], stddev = 0.01)) G_Bias1 = tf.Variable(tf.zeros([256])) G_Bias2 = tf.Variable(tf.zeros([28 * 28])) def generator(noise): G_Hidden_Layer = tf.nn.relu(tf.matmul(noise, G_Weight1) + G_Bias1) output = tf.nn.sigmoid(tf.matmul(G_Hidden_Layer, G_Weight2) + G_Bias2) return output # Discriminator D_Weight1 = tf.Variable(tf.random_normal([28 * 28, 256], stddev = 0.01)) D_Weight2 = tf.Variable(tf.random_normal([256, 1], stddev = 0.01)) D_Bias1 = tf.Varaible(tf.zeros([256])) D_Bias2 = tf.Variable(tf.zeros([1])) def discriminator(inputs): D_Hidden_Layer = tf.nn.relu(tf.matmul(inputs, D_Weight1) + D_Bias1) output = tf.nn.sigmoid(tf.matmul(D_Hidden_Layer, D_Weight2) + D_Bias2) return output # Main G = generator(Z) Loss_D = -tf.reduce_mean(tf.log(discriminator(X)) - tf.log(1 - discriminator(G))) Loss_G = -tf.reduce_mean(tf.log(discriminator(G))) Train_D = tf.train.AdamOptimizer(learning_rate = 0.0001).minimize(loss_D, var_list = [D_Weight1, D_Bias1, D_Weight2, D_Bias2]) Train_G = tf.train.AdamOptimizer(learning_rate = 0.0001).minimize(loss_G, var_list = [G_Weight1, G_Bias1, G_Weight2, G_Bias2])
def bias_variable(shape, type, metadata):
return tf.Varaible(type(shape, metadata))