文章目錄

• 目錄
• • 1.神經網絡知識概覽
  • • 1.1深度學習頂會
    • 1.2相關比賽
    • 1.3神經網絡知識概覽
    • 1.4神經網絡編程一般實現過程
  • 2.簡單神經網絡ANN
  • • 2.1 數據集：
    • 2.2 網絡結構：
    • 2.3 代碼實現
    • • 2.3.1 讀取數據，并做處理
      • 2.3.2 構建網絡結構
      • 2.3.3 訓練網絡

目錄

1.神經網絡知識概覽

1.1深度學習頂會

• CVPR : IEEE Conference on Computer Vision and Pattern Recognition
  • CVPR是計算機視覺與模式識別頂會
• ICCV：IEEE International Conference on Computer Vision
  • ICCV論文錄用率非常低，是三大會議中公認級別最高的
• ECCV：European Conference on Computer Vision

1.2相關比賽

1.ImageNet

• ImageNet 數據集最初由斯坦福大學李飛飛等人在 CVPR 2009 的一篇論文中推出
• 
  
  2.webvision
  

1.3神經網絡知識概覽

1.4神經網絡編程一般實現過程

1.數據預處理
2.定義神經網絡結構
3.初始化網絡模型中的參數
4.開始訓練模型

loop(number_iterations):forward propagationcompute costbackward propagationupdate parameters

5.對新的數據進行預測

2.簡單神經網絡ANN

2.1 數據集：

• 訓練集 + 測試集
• 訓練集：訓練集 + 評估集

• 數據信息：
  

2.2 網絡結構：

• 網絡結構 linear -> relu -> linear -> relu -> linear -> softmax
• 網絡結構12288 -> 25 -> 12 -> 6
• 迭代次數1000，學習率0.0001，minibatch_size=32，優化算法Adam
• 將RGB圖片轉換為向量（損失空間結構信息）
• 出現過擬合，應該使用正則化（L2、Dropout、早停）

2.3 代碼實現

2.3.1 讀取數據，并做處理

import math import h5py import numpy as np import tensorflow as tf import matplotlib.pyplot as plt import scipy from PIL import Image from scipy import ndimage from tensorflow.python.framework import ops from improv_utils import *%matplotlib inline np.random.seed(1)# 下載數據 X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset()# 顯示圖片 index = 2 plt.imshow(X_train_orig[index]) plt.show() print("y = " + str(np.squeeze(Y_train_orig[:, index])))# 將數據平鋪，歸一化，標簽one-hot X_train_flatten = X_train_orig.reshape(X_train_orig.shape[0], -1).T X_test_flatten = X_test_orig.reshape(X_test_orig.shape[0], -1).TX_train = X_train_flatten/255. X_test = X_test_flatten/255.Y_train = convert_to_one_hot(Y_train_orig, 6) Y_test = convert_to_one_hot(Y_test_orig, 6)print ("number of training examples = " + str(X_train.shape[1])) print ("number of test examples = " + str(X_test.shape[1])) print ("X_train shape: " + str(X_train.shape)) print ("Y_train shape: " + str(Y_train.shape)) print ("X_test shape: " + str(X_test.shape)) print ("Y_test shape: " + str(Y_test.shape))

y = 2
number of training examples = 1080
number of test examples = 120
X_train shape: (12288, 1080)
Y_train shape: (6, 1080)
X_test shape: (12288, 120)
Y_test shape: (6, 120)

2.3.2 構建網絡結構

# 1-1、創建占位符 def create_placeholders(n_x, n_y):"""Creates the placeholders for the tensorflow session.Arguments:n_x -- scalar, size of an image vector (num_px * num_px = 64 * 64 * 3 = 12288)n_y -- scalar, number of classes (from 0 to 5, so -> 6)Returns:X -- placeholder for the data input, of shape [n_x, None] and dtype "float"Y -- placeholder for the input labels, of shape [n_y, None] and dtype "float"Tips:- You will use None because it let's us be flexible on the number of examples you will for the placeholders.In fact, the number of examples during test/train is different."""X = tf.placeholder(tf.float32, shape = [n_x, None])Y = tf.placeholder(tf.float32, shape = [n_y, None])return X, Y# 1-2、初始化參數 def initialize_parameters():"""Initializes parameters to build a neural network with tensorflow. The shapes are:W1 : [25, 12288]b1 : [25, 1]W2 : [12, 25]b2 : [12, 1]W3 : [6, 12]b3 : [6, 1]Returns:parameters -- a dictionary of tensors containing W1, b1, W2, b2, W3, b3"""tf.set_random_seed(1) # so that your "random" numbers match oursW1 = tf.get_variable("W1", [25,12288], initializer = tf.contrib.layers.xavier_initializer(seed = 1))b1 = tf.get_variable("b1", [25,1], initializer = tf.zeros_initializer())W2 = tf.get_variable("W2", [12,25], initializer = tf.contrib.layers.xavier_initializer(seed = 1))b2 = tf.get_variable("b2", [12,1], initializer = tf.zeros_initializer())W3 = tf.get_variable("W3", [6,12], initializer = tf.contrib.layers.xavier_initializer(seed = 1))b3 = tf.get_variable("b3", [6,1], initializer = tf.zeros_initializer())parameters = {"W1": W1,"b1": b1,"W2": W2,"b2": b2,"W3": W3,"b3": b3}return parameters# 1-3、TensorFlow中的前向傳播 # tf中前向傳播停止在z3，是因為tf中最后的線性層輸出是被作為輸入計算loss，不需要a3 def forward_propagation(X, parameters):"""Implements the forward propagation for the model: LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SOFTMAXArguments:X -- input dataset placeholder, of shape (input size, number of examples)parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3"the shapes are given in initialize_parametersReturns:Z3 -- the output of the last LINEAR unit"""W1 = parameters['W1']b1 = parameters['b1']W2 = parameters['W2']b2 = parameters['b2']W3 = parameters['W3']b3 = parameters['b3']Z1 = tf.add(tf.matmul(W1, X), b1) # Z1 = np.dot(W1, X) + b1A1 = tf.nn.relu(Z1) # A1 = relu(Z1)Z2 = tf.add(tf.matmul(W2, A1), b2) # Z2 = np.dot(W2, a1) + b2A2 = tf.nn.relu(Z2) # A2 = relu(Z2)Z3 = tf.add(tf.matmul(W3, A2), b3) # Z3 = np.dot(W3,Z2) + b3return Z3# 1-4、計算成本函數 def compute_cost(Z3, Y):"""Computes the costArguments:Z3 -- output of forward propagation (output of the last LINEAR unit), of shape (6, number of examples)Y -- "true" labels vector placeholder, same shape as Z3Returns:cost - Tensor of the cost function"""# to fit the tensorflow requirement for tf.nn.softmax_cross_entropy_with_logits(...,...)logits = tf.transpose(Z3)labels = tf.transpose(Y)# 函數輸入：shape =（樣本數，類數）# tf.reduce_mean()cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = logits, labels = labels))return cost def predict(X, parameters):W1 = tf.convert_to_tensor(parameters["W1"])b1 = tf.convert_to_tensor(parameters["b1"])W2 = tf.convert_to_tensor(parameters["W2"])b2 = tf.convert_to_tensor(parameters["b2"])W3 = tf.convert_to_tensor(parameters["W3"])b3 = tf.convert_to_tensor(parameters["b3"])params = {"W1": W1,"b1": b1,"W2": W2,"b2": b2,"W3": W3,"b3": b3}x = tf.placeholder("float", [12288, 1])z3 = forward_propagation(x, params)p = tf.argmax(z3)with tf.Session() as sess:prediction = sess.run(p, feed_dict = {x: X})return prediction

2.3.3 訓練網絡

my_image = "my_image.jpg" fname = "images/" + my_imageimage = np.array(ndimage.imread(fname, flatten=False)) my_image = scipy.misc.imresize(image, size=(64,64)).reshape((1, 64*64*3)).T parameters = model(X_train, Y_train, X_test, Y_test)plt.imshow(image) plt.show()my_image_prediction = predict(my_image, parameters) print("Your algorithm predicts: y = " + str(np.squeeze(my_image_prediction)))

總結

以上是生活随笔為你收集整理的深度学习（02）-- ANN学习的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。