这次是P2项目——交通路牌识别，用到的是简单的卷积网络，2层的卷积层加上4层全连接层，因为用的数据集的图片大小是32x32的，所以不用很复杂的神经网络。
数据地址在这里：https://s3-us-west-/udacity-selfdrivingcar/traffic-signs-data.zip
直接粘贴到迅雷下载就好了。
下载好后解压是有3个文件，test.p train.p valid.p
我这次做到的准确率是93%，网上还有大神做到了98%，/kenshiro-o/CarND-Traffic-Sign-Classifier-Project，这是他的github，大家可以看看。
下面开始我的代码
首先先读取数据
# Load pickled dataimport pickle# TODO: Fill this in based on where you saved the training and testing datatraining_file = 'train.p'validation_file='valid.p'testing_file = 'test.p'with open(training_file, mode='rb') as f:train = pickle.load(f)with open(validation_file, mode='rb') as f:valid = pickle.load(f)with open(testing_file, mode='rb') as f:test = pickle.load(f)X_train, y_train = train['features'], train['labels']X_valid, y_valid = valid['features'], valid['labels']X_test, y_test = test['features'], test['labels']
然后分析数据
### Replace each question mark with the appropriate value. ### Use python, pandas or numpy methods rather than hard coding the results# TODO: Number of training examplesn_train = len(X_train)# TODO: Number of validation examplesn_validation = len(X_valid)# TODO: Number of testing examples.n_test = len(X_test)# TODO: What's the shape of an traffic sign image?image_shape = X_train[0].shape# TODO: How many unique classes/labels there are in the dataset.n_classes = len(set(y_train))print("Number of training examples =", n_train)print("Number of testing examples =", n_test)print("Image data shape =", image_shape)print("Number of classes =", n_classes)
可以看到train有3万多张图片 大小是32x32x3 总共有43种分类
下面是随机show一张图片和分析train，valid，test中各各类别图片的数量
### Data exploration visualization code goes here.### Feel free to use as many code cells as needed.import matplotlib.pyplot as pltfrom collections import Counterimport numpy as np# Visualizations will be shown in the notebook.%matplotlib inlineindex=np.random.randint(n_train)plt.imshow(X_train[index],cmap='gray')print(y_train[index])sign_count_test = Counter(y_train)range_x = np.array(range(n_classes))range_y = [sign_count_test[i] for i in range_x]plt.figure(figsize=(9,5))plt.bar(range_x,range_y)plt.xticks(list(range(n_classes)))plt.xlabel("class")plt.ylabel("numbers")plt.title("the train data distribution")plt.showsign_count_valid = Counter(y_valid)range_x = np.array(range(n_classes))range_y = [sign_count_valid[i] for i in range_x]plt.figure(figsize=(9,5))plt.bar(range_x,range_y)plt.xticks(list(range(n_classes)))plt.xlabel("class")plt.ylabel("numbers")plt.title("the valid data distribution")plt.showsign_count_test = Counter(y_test)range_x = np.array(range(n_classes))range_y = [sign_count_test[i] for i in range_x]plt.figure(figsize=(9,5))plt.bar(range_x,range_y)plt.xticks(list(range(n_classes)))plt.xlabel("class")plt.ylabel("numbers")plt.title("the test data distribution")plt.show
下面开始一些图像的预处理，有normalized，grayscale等等都是一些很简单的函数
### Preprocess the data here. It is required to normalize the data. Other preprocessing steps could include ### converting to grayscale, etc.### Feel free to use as many code cells as needed.import cv2def normalized(images):xmin = np.min(images)xmax = np.max(images)image = (images - xmin)/(xmax-xmin)return imagedef grayscale(image):gray = cv2.cvtColor(image,cv2.COLOR_RGB2GRAY)return np.expand_dims(gray,axis = 2)def preprocess(images):list1 = []for image in images:list1.append(grayscale(image))list1 = np.array(list1)return normalized(list1)def one_hot(images):list1 = np.zeros((len(images),n_classes))for i,label in enumerate(images):list1[i][label] = 1return list1
import tensorflow as tffrom sklearn.utils import shuffleX_train,y_train = shuffle(X_train,y_train)X_train = preprocess(X_train)y_train = one_hot(y_train)X_valid = preprocess(X_valid)y_valid = one_hot(y_valid)X_test = preprocess(X_test)y_test = one_hot(y_test)print(X_train.shape,y_train.shape)
这里的输出为：(34799, 32, 32, 1) (34799, 43)
可以看到 我们通过预处理把原来是3通道的图变成灰度图，然后把y_train,y_valid,y_test变成one_hot格式，为后面做准备
下面就是开始设计我们的神经网络层了
### Define your architecture here.### Feel free to use as many code cells as needed.inputs = tf.placeholder(tf.float32,shape = [None,32,32,1],name = 'inputs')labels = tf.placeholder(tf.int32,shape = [None,n_classes],name = 'labels')from tensorflow.contrib.layers import flattendef model(images,add_dropout = True):mu = 0sigma = 0.1dropout = 0.5#0.5和0.75算出来的精确度都差不多conv1_W = tf.Variable(tf.truncated_normal(shape = (5,5,1,12),mean = mu,stddev=sigma))conv1_b = tf.Variable(tf.zeros(12))conv1 = tf.nn.conv2d(images,conv1_W,strides=[1,1,1,1],padding='VALID') + conv1_bconv1 = tf.nn.relu(conv1)conv1 = tf.nn.max_pool(conv1,ksize=[1,2,2,1],strides=[1,2,2,1],padding='VALID',name = 'conv1')#14x14x12conv2_W = tf.Variable(tf.truncated_normal(shape = (5,5,12,24),mean = mu,stddev=sigma))conv2_b = tf.Variable(tf.zeros(24))conv2 = tf.nn.conv2d(conv1,conv2_W,strides = [1,1,1,1],padding='VALID',name = 'conv2') + conv2_bconv2 = tf.nn.relu(conv2)conv2 = tf.nn.max_pool(conv2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='VALID')#5,5,24fc0 = flatten(conv2)#600fc1_W = tf.Variable(tf.truncated_normal(shape = (600,400),mean = mu,stddev = sigma))fc1_b = tf.Variable(tf.zeros(400))fc1 = tf.matmul(fc0,fc1_W) + fc1_bfc1 = tf.nn.relu(fc1)if add_dropout:fc1 = tf.nn.dropout(fc1,dropout)fc2_W = tf.Variable(tf.truncated_normal(shape=(400, 120), mean = mu, stddev = sigma))fc2_b = tf.Variable(tf.zeros(120))fc2 = tf.matmul(fc1, fc2_W) + fc2_bfc2 = tf.nn.relu(fc2)if add_dropout:fc2 = tf.nn.dropout(fc2,dropout)fc3_W = tf.Variable(tf.truncated_normal(shape = (120,84),mean = mu,stddev=sigma))fc3_b = tf.Variable(tf.zeros(84))fc3 = tf.matmul(fc2,fc3_W) +fc3_bfc3 = tf.nn.relu(fc3)if add_dropout:fc3 = tf.nn.dropout(fc3,dropout)fc4_w = tf.Variable(tf.truncated_normal(shape = (84,43),mean=mu,stddev=sigma))fc4_b = tf.Variable(tf.zeros(43))logits = tf.matmul(fc3,fc4_w) + fc4_breturn logits
这里我们的输入是32x32x1,第一层是5x5x12的网路层，输出是28x28x12，然后跟着一个max_pooling，变成14X14X12
第二层是5x5x24，输出是10x10x24，后面也是跟着一个max_pooling，变成5x5x24。
下面开始时全连接层，因为5x5x24=600,所以我的全连接层就是(600,400),(400,120),(120,84),(84,43)
然后加上0.5的dropout，我试了试0.5和0.75最后的accuracy都差不多
下面开始训练神经网络了
def get_batches(X,y,batch_size=128):length=len(X)n_batches=length//batch_size+1for i in range(n_batches):yield X[batch_size*i:min(length,batch_size*(i+1))], y[batch_size*i:min(length,batch_size*(i+1))]
### Train your model here.### Calculate and report the accuracy on the training and validation set.### Once a final model architecture is selected, ### the accuracy on the test set should be calculated and reported as well.### Feel free to use as many code cells as needed.EPOCHS = 40max_acc = 0save_model_path = 'Traffice_sign_classifier'logits = model(inputs)logits = tf.identity(logits,name = 'logits')cost = tf.reduce_mean(tf.losses.softmax_cross_entropy(labels,logits),name = 'cost')#使用tf.nn.softmax_cross_entropy_with_logits创建交叉熵损失optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)#这句里的minimize不知道什么意思correct_pred = tf.equal(tf.argmax(labels,1),tf.argmax(logits,1))accuracy = tf.reduce_mean(tf.cast(correct_pred,tf.float32),name = 'accuracy')with tf.Session() as sess:sess.run(tf.global_variables_initializer())for epoch in range(EPOCHS):for i,(X,y) in enumerate(get_batches(X_train,y_train)):sess.run(optimizer,feed_dict = {inputs:X,labels:y})if i%50==0:valid_acc=sess.run(accuracy, feed_dict={inputs:X_valid, labels:y_valid})train_acc=sess.run(accuracy, feed_dict={inputs:X, labels:y})print('epoch : ',epoch+1,' training accuracy is : ',train_acc,' valid accuracy is :',valid_acc)if valid_acc > max_acc:max_acc = valid_accsaver = tf.train.Saver(max_to_keep=1)#模型保存，先要创建一个Saver对象：如 saver=tf.train.Saver()#当然，如果你只想保存最后一代的模型，则只需要将max_to_keep设置为1即可save_path = saver.save(sess,save_model_path)
最后在测试集上进行测试
import pandas as pdloaded_graph = tf.Graph()save_model_path = './Traffice_sign_classifier'
with tf.Session(graph=loaded_graph) as sees:loader = tf.train.import_meta_graph(save_model_path + '.meta')loader.restore(sees, save_model_path)loaded_inputs=loaded_graph.get_tensor_by_name('inputs:0')loaded_labels=loaded_graph.get_tensor_by_name('labels:0')loaded_logits = loaded_graph.get_tensor_by_name('logits:0')loaded_acc=loaded_graph.get_tensor_by_name('accuracy:0')test_acc=sees.run(loaded_acc,feed_dict={loaded_inputs:X_test,loaded_labels:y_test})print('The test accuracy is:',test_acc)
到这里就算是完结了，谢谢大家看到最后。
