我已经训练了一个卷积神经网络(CNN),其中包含我在二进制文件中的以下数据(标签,文件名,数据(像素))：[array([2, 1, 0, 2, 1, 0, 2, 1, 0, 2, 1, 0, 2, 1, 0, 2, 1, 0, 2, 1, 0, 2, 1,0, 2, 1, 0, 2, 1, 0]), array(['10_c.jpg', '10_m.jpg', '10_n.jpg', '1_c.jpg','1_m.jpg', '1_n.jpg', '2_c.jpg', '2_m.jpg','2_n.jpg', '3_c.jpg', '3_m.jpg', '3_n.jpg','4_c.jpg', '4_m.jpg', '4_n.jpg', '5_c.jpg','5_m.jpg', '5_n.jpg', '6_...
首先，看一下神经网络反向传播优化流程图： 反向传播算法实现了一个迭代的过程。每次迭代的开始，都选取一部分训练数据batch。然后，这个batch的样例会通过前向传播算法得到神经网络模型的预测结果。因为训练数据都是有正确答案标注的，所以可以计算出当前神经网络模型的预测答案与正确答案之间的差距。最后，基于这个差距，通过反向传播算法会更新神经网络参数的取值，使得在这个batch上神经网络的预测结果与真实答案更加接近。 ...
import tensorflow as tfq = tf.FIFOQueue(2, "int32") init = q.enqueue_many(([0, 10],)) x = q.dequeue() y = x + 1 q_inc = q.enqueue([y]) with tf.Session() as sess:init.run()for _ in range(5):v, _ = sess.run([x, q_inc])print(v)import time import threading import numpy as npdef MyLoop(coord, worker_id):while not coord.should_stop():if np.random.rand()<0.1:print("Stoping from id: %d\n" % worker_id,coor...
import tensorflow as tfqueue = tf.FIFOQueue(100,"float") enqueue_op = queue.enqueue([tf.random_normal([1])]) qr = tf.train.QueueRunner(queue, [enqueue_op] * 5) tf.train.add_queue_runner(qr) out_tensor = queue.dequeue()with tf.Session() as sess:coord = tf.train.Coordinator()threads = tf.train.start_queue_runners(sess=sess, coord=coord)for _ in range(3): print(sess.run(out_tensor)[0])coord.request_s...
import numpy as np import tensorflow as tf import matplotlib.pyplot as pltimage_raw_data = tf.gfile.FastGFile("F:\\TensorFlowGoogle\\201806-github\\datasets\\cat.jpg",rb).read()with tf.Session() as sess:img_data = tf.image.decode_jpeg(image_raw_data)# 输出解码之后的三维矩阵。print(img_data.eval())img_data.set_shape([1797, 2673, 3])print(img_data.get_shape())with tf.Session() as sess:plt.imshow(im...
import numpy as np import tensorflow as tf import matplotlib.pyplot as pltdef distort_color(image, color_ordering=0):if color_ordering == 0:image = tf.image.random_brightness(image, max_delta=32./255.)image = tf.image.random_saturation(image, lower=0.5, upper=1.5)image = tf.image.random_hue(image, max_delta=0.2)image = tf.image.random_contrast(image, lower=0.5, upper=1.5)else:image = tf.image.rand...
# -*- coding: utf-8 -*-import glob import os.path import numpy as np import tensorflow as tf from tensorflow.python.platform import gfile import tensorflow.contrib.slim as slimimport tensorflow.contrib.slim.python.slim.nets.inception_v3 as inception_v3# 处理好之后的数据文件。 INPUT_DATA = E:\\flower_processed_data\\flower_processed_data.npy # 保存训练好的模型的路径。这里我们可以将使用新数据训练得到...
import glob import os.path import numpy as np import tensorflow as tf from tensorflow.python.platform import gfile import tensorflow.contrib.slim as slim# 加载通过TensorFlow-Slim定义好的inception_v3模型。 import tensorflow.contrib.slim.python.slim.nets.inception_v3 as inception_v3# 处理好之后的数据文件。 INPUT_DATA = F:\\flower_processed_data.npy # 保存训练好的模型的路径。 TRAIN_FILE = E:\\train_d...
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_dataINPUT_NODE = 784 # 输入节点 OUTPUT_NODE = 10 # 输出节点 LAYER1_NODE = 500 # 隐藏层数 BATCH_SIZE = 100 # 每次batch打包的样本个数 # 模型相关的参数 LEARNING_RATE_BASE = 0.8 LEARNING_RATE_DECAY = 0.99 REGULARAZTION_RATE = 0.0001 TRAINING_STEPS = 5000 def inference(input_ten...
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_dataINPUT_NODE = 784 # 输入节点 OUTPUT_NODE = 10 # 输出节点 LAYER1_NODE = 500 # 隐藏层数 BATCH_SIZE = 100 # 每次batch打包的样本个数 # 模型相关的参数 LEARNING_RATE = 0.1 REGULARAZTION_RATE = 0.0001 TRAINING_STEPS = 5000 MOVING_AVERAGE_DECAY = 0.99 def inference(input_tensor, a...
import tensorflow as tf from tensorflow.python.framework import graph_utilv1 = tf.Variable(tf.constant(1.0, shape=[1]), name = "v1") v2 = tf.Variable(tf.constant(2.0, shape=[1]), name = "v2") result = v1 + v2init_op = tf.global_variables_initializer() with tf.Session() as sess:sess.run(init_op)graph_def = tf.get_default_graph().as_graph_def()output_graph_def = graph_util.convert_variables_to_const...
import tensorflow as tfv1 = tf.Variable(tf.random_normal([1], stddev=1, seed=1)) v2 = tf.Variable(tf.random_normal([1], stddev=1, seed=1)) result = v1 + v2init_op = tf.global_variables_initializer() saver = tf.train.Saver()with tf.Session() as sess:sess.run(init_op)saver.save(sess, "E:\\Saved_model\\model.ckpt")with tf.Session() as sess:saver.restore(sess, "E:\\Saved_model\\model.ckpt")print(sess....
from tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("E:\\datasets\\MNIST_data\\", one_hot=True)print("Training data size: ", mnist.train.num_examples) print("Validating data size: ", mnist.validation.num_examples) print("Testing data size: ", mnist.test.num_examples)print("Example training data: ", mnist.train.images[0]) print("Example training data label: "...
#-*- coding:utf-8 -*-import time import keras import skimage import numpy as np import tensorflow as tf import matplotlib.image as imgfrom scipy import ndimage from skimage import color, data, transform%matplotlib inline#设置文件目录 Training = rF:\\data\\fruits-360\\Training Test = rF:\\data\\fruits-360\\Test import os from natsort import natsorted#获取每类水果中的第五张图像 def load_print_img(r...
训练集是生成的随机数，x和y的对应关系是y=2x。先生成100个随机数x,然后再计算出y=2x，并在结果上加上一些噪声，测试线性回归模型能否拟合好出y=2x。 1、代码如下：import tensorflow as tf #导入TensorFlow模块 import numpy as np import matplotlib.pyplot as plttrain_X=np.linspace(-1,1,100) #产生训练样本X.函数np.linspace用于产生随机数，5个参数，常用前三个，前两个代表产生随机数的范围，第三个代表数目，默认50. trai...