作业
1.Tensorflow入门
# TensorFlow and tf.keras import tensorflow as tf from tensorflow import keras # Helper libraries import numpy as np import matplotlib.pyplot as plt print(tf.__version__) fashion_mnist = keras.datasets.fashion_mnist (train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data() class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'] plt.figure() plt.imshow(train_images[0]) plt.colorbar() plt.grid(False) plt.show() train_images = train_images / 255.0 test_images = test_images / 255.0 plt.figure(figsize=(10,10)) for i in range(25): plt.subplot(5,5,i+1) plt.xticks([]) plt.yticks([]) plt.grid(False) plt.imshow(train_images[i], cmap=plt.cm.binary) plt.xlabel(class_names[train_labels[i]]) plt.show() model = keras.Sequential([ keras.layers.Flatten(input_shape=(28, 28)), keras.layers.Dense(128, activation='relu'), keras.layers.Dense(10) ]) model.compile(optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy']) model.fit(train_images, train_labels, epochs=10) test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2) print('\nTest accuracy:', test_acc) probability_model = tf.keras.Sequential([model, tf.keras.layers.Softmax()]) predictions = probability_model.predict(test_images) np.argmax(predictions[0]) def plot_image(i, predictions_array, true_label, img): predictions_array, true_label, img = predictions_array, true_label[i], img[i] plt.grid(False) plt.xticks([]) plt.yticks([]) plt.imshow(img, cmap=plt.cm.binary) predicted_label = np.argmax(predictions_array) if predicted_label == true_label: color = 'blue' else: color = 'red' plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label], 100*np.max(predictions_array), class_names[true_label]), color=color) def plot_value_array(i, predictions_array, true_label): predictions_array, true_label = predictions_array, true_label[i] plt.grid(False) plt.xticks(range(10)) plt.yticks([]) thisplot = plt.bar(range(10), predictions_array, color="#777777") plt.ylim([0, 1]) predicted_label = np.argmax(predictions_array) thisplot[predicted_label].set_color('red') thisplot[true_label].set_color('blue') i = 0 plt.figure(figsize=(6, 3)) plt.subplot(1, 2, 1) plot_image(i, predictions[i], test_labels, test_images) plt.subplot(1, 2, 2) plot_value_array(i, predictions[i], test_labels) plt.show() i = 12 plt.figure(figsize=(6, 3)) plt.subplot(1, 2, 1) plot_image(i, predictions[i], test_labels, test_images) plt.subplot(1, 2, 2) plot_value_array(i, predictions[i], test_labels) plt.show() # Plot the first X test images, their predicted labels, and the true labels. # Color correct predictions in blue and incorrect predictions in red. num_rows = 5 num_cols = 3 num_images = num_rows * num_cols plt.figure(figsize=(2 * 2 * num_cols, 2 * num_rows)) for i in range(num_images): plt.subplot(num_rows, 2 * num_cols, 2 * i + 1) plot_image(i, predictions[i], test_labels, test_images) plt.subplot(num_rows, 2 * num_cols, 2 * i + 2) plot_value_array(i, predictions[i], test_labels) plt.tight_layout() plt.show() # Grab an image from the test dataset. img = test_images[1] print(img.shape) # Add the image to a batch where it's the only member. img = (np.expand_dims(img, 0)) print(img.shape) predictions_single = probability_model.predict(img) print(predictions_single) plot_value_array(1, predictions_single[0], test_labels) _ = plt.xticks(range(10), class_names, rotation=45) np.argmax(predictions_single[0])
运行结果：
2.pytorch入门
import torch from torch import nn from torch.utils.data import DataLoader from torchvision import datasets from torchvision.transforms import ToTensor # Download training data from open datasets. training_data = datasets.FashionMNIST( root="data", train=True, download=True, transform=ToTensor(), ) # Download test data from open datasets. test_data = datasets.FashionMNIST( root="data", train=False, download=True, transform=ToTensor(), ) batch_size = 64 # Create data loaders. train_dataloader = DataLoader(training_data, batch_size=batch_size) test_dataloader = DataLoader(test_data, batch_size=batch_size) for X, y in test_dataloader: print(f"Shape of X [N, C, H, W]: {X.shape}") print(f"Shape of y: {y.shape} {y.dtype}") break # Get cpu or gpu device for training. device = "cuda" if torch.cuda.is_available() else "cpu" print(f"Using {device} device") # Define model class NeuralNetwork(nn.Module): def __init__(self): super(NeuralNetwork, self).__init__() self.flatten = nn.Flatten() self.linear_relu_stack = nn.Sequential( nn.Linear(28*28, 512), nn.ReLU(), nn.Linear(512, 512), nn.ReLU(), nn.Linear(512, 10) ) def forward(self, x): x = self.flatten(x) logits = self.linear_relu_stack(x) return logits model = NeuralNetwork().to(device) print(model) loss_fn = nn.CrossEntropyLoss() optimizer = torch.optim.SGD(model.parameters(), lr=1e-3) def train(dataloader, model, loss_fn, optimizer): size = len(dataloader.dataset) model.train() for batch, (X, y) in enumerate(dataloader): X, y = X.to(device), y.to(device) # Compute prediction error pred = model(X) loss = loss_fn(pred, y) # Backpropagation optimizer.zero_grad() loss.backward() optimizer.step() if batch % 100 == 0: loss, current = loss.item(), batch * len(X) print(f"loss: {loss:>7f} [{current:>5d}/{size:>5d}]") def test(dataloader, model, loss_fn): size = len(dataloader.dataset) num_batches = len(dataloader) model.eval() test_loss, correct = 0, 0 with torch.no_grad(): for X, y in dataloader: X, y = X.to(device), y.to(device) pred = model(X) test_loss += loss_fn(pred, y).item() correct += (pred.argmax(1) == y).type(torch.float).sum().item() test_loss /= num_batches correct /= size print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n") epochs = 5 for t in range(epochs): print(f"Epoch {t+1}\n-------------------------------") train(train_dataloader, model, loss_fn, optimizer) test(test_dataloader, model, loss_fn) print("Done!") torch.save(model.state_dict(), "model.pth") print("Saved PyTorch Model State to model.pth") model = NeuralNetwork() model.load_state_dict(torch.load("model.pth")) classes = [ "T-shirt/top", "Trouser", "Pullover", "Dress", "Coat", "Sandal", "Shirt", "Sneaker", "Bag", "Ankle boot", ] model.eval() x, y = test_data[0][0], test_data[0][1] with torch.no_grad(): pred = model(x) predicted, actual = classes[pred[0].argmax(0)], classes[y] print(f'Predicted: "{predicted}", Actual: "{actual}"')
运行结果：
3.VGG实战
# softmax 将实数值转换为概率值 import tensorflow as tf from tensorflow import keras from tensorflow.keras import layers , Sequential , datasets , optimizers , models , regularizers import numpy as np #零均值归一化 def normalize(X_train, X_test): X_train = X_train / 255. X_test = X_test / 255. mean = np.mean(X_train, axis=(0, 1, 2, 3)) std = np.std(X_train, axis=(0, 1, 2, 3)) print('mean:', mean, 'std:', std) X_train = (X_train - mean) / (std + 1e-7) X_test = (X_test - mean) / (std + 1e-7) return X_train, X_test #读取数据 (x_train,y_train), (x_test, y_test) = datasets.cifar10.load_data() (x_train.shape,y_train.shape), (x_test.shape, y_test.shape) #归一化数据 x_train, x_test = normalize(x_train, x_test) # y本身就是标签值（0~9）所以不用进行归一化，只需要做one_hot处理即可 def preprocess(x, y): x = tf.cast(x, tf.float32 )#转换为tftensor y = tf.cast(y, tf.int32) #转换为tftensor y = tf.squeeze(y, axis=1) # 注意y是50000,1但是我们希望y直接是b # atchsize，所以要把1挤压掉 y = tf.one_hot(y, depth=10) # 做hone_hot编码 return x, y # 训练样本 train_db = tf.data.Dataset.from_tensor_slices((x_train,y_train)) train_db = train_db.shuffle(50000).batch(128).map(preprocess) test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test)) test_db = test_db.shuffle(50000).batch(128).map(preprocess) # 由于VGG 16对于这个数据集表现很差，于是做如下改进 num_classes = 10 #如果是imagenet数据集,这里为1000 weight_decay = 0.000 model = models.Sequential() #构造容器 #第一层 model.add( layers.Conv2D(64,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.Dropout(0.3)) # 丢弃一部分神经元，防止过拟合 model.add( layers.Conv2D(64,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.MaxPooling2D(pool_size=(2, 2))) #第二层 model.add( layers.Conv2D(128,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.Dropout(0.4)) # 丢弃一部分神经元，防止过拟合 model.add( layers.Conv2D(128,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.MaxPooling2D(pool_size=(2,2))) #第三层 model.add( layers.Conv2D(256,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.Dropout(0.4)) # 丢弃一部分神经元，防止过拟合 model.add( layers.Conv2D(256,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.Dropout(0.4)) # 丢弃一部分神经元，防止过拟合 model.add( layers.Conv2D(256,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers. MaxPooling2D(pool_size=(2,2))) #第四层 model.add( layers.Conv2D(512,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.Dropout(0.4)) # 丢弃一部分神经元，防止过拟合 model.add( layers.Conv2D(512,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.Dropout(0.4)) # 丢弃一部分神经元，防止过拟合 model.add( layers.Conv2D(512,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers. MaxPooling2D(pool_size=(2,2))) #第五层 model.add( layers.Conv2D(512,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.Dropout(0.4)) # 丢弃一部分神经元，防止过拟合 model.add( layers.Conv2D(512,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.Dropout(0.4)) # 丢弃一部分神经元，防止过拟合 model.add( layers.Conv2D(512,(3,3), padding='same', kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.MaxPooling2D(pool_size=(2,2))) model.add(layers.Dropout(0.5)) # 丢弃一部分神经元，防止过拟合 #拉平 #将三个全神经网络改成两个 model.add(layers.Flatten()) model.add(layers.Dense(512,kernel_regularizer = regularizers.l2(weight_decay))) #做一个l2正则化 model.add(layers.Activation('relu')) model.add(layers.BatchNormalization()) #BN 层 model.add(layers.Dropout(0.5)) # 丢弃一部分神经元，防止过拟合 model.add(layers.Dense(num_classes))# VGG 16 为1000 model.add(layers.Activation('softmax')) model.build(input_shape=(None,32,32,3)) model.summary() # 优化器 model.compile(optimizer=keras.optimizers.Adam(0.0001), loss = keras.losses.CategoricalCrossentropy(from_logits=True),#加上from_logits=True之后，训练会得到更好的结果 metrics=['accuracy']) history = model.fit(train_db,epochs=50) #能保存模型结构 path = 'saved_model_VGG/' model.save(path, save_format='tf') import matplotlib.pyplot as plt plt.plot(history.history['loss']) plt.title("model loss") plt.ylabel("1oss" ) plt.xlabel("epoch") plt.show() model.evaluate(test_db)
运行结果：
浙公网安备 33010602011771号