首先进行数据预处理，需要生成.tsv、.jpg文件
import matplotlib.pyplot as plt
import numpy as np
import os
from tensorflow.examples.tutorials.mnist import input_data
LOG_DIR = 'log'
SPRITE_FILE = 'mnist_sprite.jpg'
META_FIEL = "mnist_meta.tsv" # 存储索引和标签
def create_sprite_image(images):
if isinstance(images, list):
images = np.array(images)
img_h = images.shape[1]
img_w = images.shape[2]
n_plots = int(np.ceil(np.sqrt(images.shape[0])))
spriteimage = np.ones((img_h * n_plots, img_w * n_plots))
for i in range(n_plots):
for j in range(n_plots):
this_filter = i * n_plots + j
if this_filter < images.shape[0]: # 个数
this_img = images[this_filter]
spriteimage[i * img_h:(i + 1) * img_h,
j * img_w:(j + 1) * img_w] = this_img
return spriteimage
mnist = input_data.read_data_sets("MNIST_data/", one_hot=False)
to_visualise = 1 - np.reshape(mnist.test.images, (-1, 28, 28)) # 取反
sprite_image = create_sprite_image(to_visualise)
path_for_mnist_sprites = os.path.join(LOG_DIR, SPRITE_FILE)
plt.imsave(path_for_mnist_sprites, sprite_image, cmap='gray')
plt.imshow(sprite_image, cmap='gray')
path_for_mnist_metadata = os.path.join(LOG_DIR, META_FIEL) # 下面存储的东西很关键
with open(path_for_mnist_metadata, 'w') as f:
f.write("Index\tLabel\n")
for index, label in enumerate(mnist.test.labels): # 上边是(Index, label)是
f.write("%d\t%d\n" % (index, label))
mnist_inference：
import tensorflow as tf
INPUT_NODE = 784
LAYER1_NODE = 500
OUTPUT_NODE = 10
def get_weight_variable(shape, regularizer):
weights = tf.get_variable("weights", shape, initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer is not None:
tf.add_to_collection('losses', regularizer(weights))
return weights
def inference(input_tensor, regularizer):
# 只有当训练和测试在一个程序时，才用reuse
with tf.variable_scope('layer1'):
weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)
biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)
with tf.variable_scope('layer2'):
weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)
biases = tf.get_variable("biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.0))
layer2 = tf.matmul(layer1, weights) + biases
return layer2
projector_MNIST
import tensorflow as tf
import mnist_inference
import os
from tensorflow.contrib.tensorboard.plugins import projector # 加载用于生成PROJECTOR日志的帮助函数
from tensorflow.examples.tutorials.mnist import input_data
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 10000
MOVING_AVERAGE_DECAY = 0.99
LOG_DIR = 'log'
SPRITE_FILE = 'mnist_sprite.jpg'
META_FIEL = "mnist_meta.tsv"
TENSOR_NAME = "FINAL_LOGITS"
def train(mnist): # 返回的是训练的数据，每行代表一个标签
# 输入数据的命名空间。
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
y = mnist_inference.inference(x, regularizer)
global_step = tf.Variable(0, trainable=False)
9
# 处理滑动平均的命名空间。
with tf.name_scope("moving_average"):
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
# 计算损失函数的命名空间。
with tf.name_scope("loss_function"):
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
# 定义学习率、优化方法及每一轮执行训练的操作的命名空间。
with tf.name_scope("train_step"):
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,
staircase=True)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
# 训练模型。
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(TRAINING_STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
if i % 1000 == 0:
print("After %d training step(s), loss on training batch is %g." % (i, loss_value))
final_result = sess.run(y, feed_dict={x: mnist.test.images})
return final_result
def visualisation(final_result): # 这里才是正儿八经的可视化
y = tf.Variable(final_result, name=TENSOR_NAME) # 用final_result对y初始化
summary_writer = tf.summary.FileWriter(LOG_DIR)
config = projector.ProjectorConfig() # 通过projector.ProjectorConfig来帮助生成日志文件
embedding = config.embeddings.add() # 增加一个需要可视化的embedding结果
embedding.tensor_name = y.name # 指定这个embedding结果对应的Tensorflow变量名称，按照它来分类，y的结果时0-9
# Specify where you find the metadata
embedding.metadata_path = META_FIEL # 注意这里也要.tsv文件
# Specify where you find the sprite (we will create this later)
embedding.sprite.image_path = SPRITE_FILE # 这里同时也要.jpg文件
embedding.sprite.single_image_dim.extend([28, 28])
# Say that you want to visualise the embeddings
projector.visualize_embeddings(summary_writer, config) # 这一步是写入
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.save(sess, os.path.join(LOG_DIR, "model"), TRAINING_STEPS)
summary_writer.close()
def main(argv=None):
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
final_result = train(mnist)
visualisation(final_result)
if __name__ == '__main__':
main()
