由于Keras是一种建立在已有深度学习框架上的二次框架,其使用起来非常方便,其后端实现有两种方法,theano和tensorflow。由于自己平时用tensorflow,所以选择后端用tensorflow的Keras,代码写起来更加方便。
1、建立模型
Keras分为两种不同的建模方式,
Sequential models:这种方法用于实现一些简单的模型。你只需要向一些存在的模型中添加层就行了。
Functional API:Keras的API是非常强大的,你可以利用这些API来构造更加复杂的模型,比如多输出模型,有向无环图等等。
这里采用sequential models方法。
构建序列模型。
def define_model(): model = Sequential() # setup first conv layer model.add(Conv2D(32, (3, 3), activation="relu", input_shape=(120, 120, 3), padding='same')) # [10, 120, 120, 32] # setup first maxpooling layer model.add(MaxPooling2D(pool_size=(2, 2))) # [10, 60, 60, 32] # setup second conv layer model.add(Conv2D(8, kernel_size=(3, 3), activation="relu", padding='same')) # [10, 60, 60, 8] # setup second maxpooling layer model.add(MaxPooling2D(pool_size=(3, 3))) # [10, 20, 20, 8] # add bianping layer, 3200 = 20 * 20 * 8 model.add(Flatten()) # [10, 3200] # add first full connection layer model.add(Dense(512, activation='sigmoid')) # [10, 512] # add dropout layer model.add(Dropout(0.5)) # add second full connection layer model.add(Dense(4, activation='softmax')) # [10, 4] return model
可以看到定义模型时输出的网络结构。
2、准备数据
def load_data(resultpath): datapath = os.path.join(resultpath, "data10_4.npz") if os.path.exists(datapath): data = np.load(datapath) X, Y = data["X"], data["Y"] else: X = np.array(np.arange(432000)).reshape(10, 120, 120, 3) Y = [0, 0, 1, 1, 2, 2, 3, 3, 2, 0] X = X.astype('float32') Y = np_utils.to_categorical(Y, 4) np.savez(datapath, X=X, Y=Y) print('Saved dataset to dataset.npz.') print('X_shape:{}\nY_shape:{}'.format(X.shape, Y.shape)) return X, Y
3、训练模型
def train_model(resultpath): model = define_model() # if want to use SGD, first define sgd, then set optimizer=sgd sgd = SGD(lr=0.001, decay=1e-6, momentum=0, nesterov=True) # select loss\optimizer model.compile(loss=categorical_crossentropy, optimizer=Adam(), metrics=['accuracy']) model.summary() # draw the model structure plot_model(model, show_shapes=True, to_file=os.path.join(resultpath, 'model.png')) # load data X, Y = load_data(resultpath) # split train and test data X_train, X_test, Y_train, Y_test = train_test_split( X, Y, test_size=0.2, random_state=2) # input data to model and train history = model.fit(X_train, Y_train, batch_size=2, epochs=10, validation_data=(X_test, Y_test), verbose=1, shuffle=True) # evaluate the model loss, acc = model.evaluate(X_test, Y_test, verbose=0) print('Test loss:', loss) print('Test accuracy:', acc)
可以看到训练时输出的日志。因为是随机数据,没有意义,这里训练的结果不必计较,只是练习而已。
保存下来的模型结构:
4、保存与加载模型并测试
有两种保存方式
4.1 直接保存模型h5
保存:
def my_save_model(resultpath): model = train_model(resultpath) # the first way to save model model.save(os.path.join(resultpath, 'my_model.h5'))
加载:
def my_load_model(resultpath): # test data X = np.array(np.arange(86400)).reshape(2, 120, 120, 3) Y = [0, 1] X = X.astype('float32') Y = np_utils.to_categorical(Y, 4) # the first way of load model model2 = load_model(os.path.join(resultpath, 'my_model.h5')) model2.compile(loss=categorical_crossentropy, optimizer=Adam(), metrics=['accuracy']) test_loss, test_acc = model2.evaluate(X, Y, verbose=0) print('Test loss:', test_loss) print('Test accuracy:', test_acc) y = model2.predict_classes(X) print("predicct is: ", y)
4.2 分别保存网络结构和权重
保存:
def my_save_model(resultpath): model = train_model(resultpath) # the secon way : save trained network structure and weights model_json = model.to_json() open(os.path.join(resultpath, 'my_model_structure.json'), 'w').write(model_json) model.save_weights(os.path.join(resultpath, 'my_model_weights.hd5'))
加载:
def my_load_model(resultpath): # test data X = np.array(np.arange(86400)).reshape(2, 120, 120, 3) Y = [0, 1] X = X.astype('float32') Y = np_utils.to_categorical(Y, 4) # the second way : load model structure and weights model = model_from_json(open(os.path.join(resultpath, 'my_model_structure.json')).read()) model.load_weights(os.path.join(resultpath, 'my_model_weights.hd5')) model.compile(loss=categorical_crossentropy, optimizer=Adam(), metrics=['accuracy']) test_loss, test_acc = model.evaluate(X, Y, verbose=0) print('Test loss:', test_loss) print('Test accuracy:', test_acc) y = model.predict_classes(X) print("predicct is: ", y)
可以看到,两次的结果是一样的。
5、完整代码
from keras.models import Sequential from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Dropout from keras.losses import categorical_crossentropy from keras.optimizers import Adam from keras.utils.vis_utils import plot_model from keras.optimizers import SGD from keras.models import model_from_json from keras.models import load_model from keras.utils import np_utils import numpy as np import os from sklearn.model_selection import train_test_split def load_data(resultpath): datapath = os.path.join(resultpath, "data10_4.npz") if os.path.exists(datapath): data = np.load(datapath) X, Y = data["X"], data["Y"] else: X = np.array(np.arange(432000)).reshape(10, 120, 120, 3) Y = [0, 0, 1, 1, 2, 2, 3, 3, 2, 0] X = X.astype('float32') Y = np_utils.to_categorical(Y, 4) np.savez(datapath, X=X, Y=Y) print('Saved dataset to dataset.npz.') print('X_shape:{}\nY_shape:{}'.format(X.shape, Y.shape)) return X, Y def define_model(): model = Sequential() # setup first conv layer model.add(Conv2D(32, (3, 3), activation="relu", input_shape=(120, 120, 3), padding='same')) # [10, 120, 120, 32] # setup first maxpooling layer model.add(MaxPooling2D(pool_size=(2, 2))) # [10, 60, 60, 32] # setup second conv layer model.add(Conv2D(8, kernel_size=(3, 3), activation="relu", padding='same')) # [10, 60, 60, 8] # setup second maxpooling layer model.add(MaxPooling2D(pool_size=(3, 3))) # [10, 20, 20, 8] # add bianping layer, 3200 = 20 * 20 * 8 model.add(Flatten()) # [10, 3200] # add first full connection layer model.add(Dense(512, activation='sigmoid')) # [10, 512] # add dropout layer model.add(Dropout(0.5)) # add second full connection layer model.add(Dense(4, activation='softmax')) # [10, 4] return model def train_model(resultpath): model = define_model() # if want to use SGD, first define sgd, then set optimizer=sgd sgd = SGD(lr=0.001, decay=1e-6, momentum=0, nesterov=True) # select loss\optimizer model.compile(loss=categorical_crossentropy, optimizer=Adam(), metrics=['accuracy']) model.summary() # draw the model structure plot_model(model, show_shapes=True, to_file=os.path.join(resultpath, 'model.png')) # load data X, Y = load_data(resultpath) # split train and test data X_train, X_test, Y_train, Y_test = train_test_split( X, Y, test_size=0.2, random_state=2) # input data to model and train history = model.fit(X_train, Y_train, batch_size=2, epochs=10, validation_data=(X_test, Y_test), verbose=1, shuffle=True) # evaluate the model loss, acc = model.evaluate(X_test, Y_test, verbose=0) print('Test loss:', loss) print('Test accuracy:', acc) return model def my_save_model(resultpath): model = train_model(resultpath) # the first way to save model model.save(os.path.join(resultpath, 'my_model.h5')) # the secon way : save trained network structure and weights model_json = model.to_json() open(os.path.join(resultpath, 'my_model_structure.json'), 'w').write(model_json) model.save_weights(os.path.join(resultpath, 'my_model_weights.hd5')) def my_load_model(resultpath): # test data X = np.array(np.arange(86400)).reshape(2, 120, 120, 3) Y = [0, 1] X = X.astype('float32') Y = np_utils.to_categorical(Y, 4) # the first way of load model model2 = load_model(os.path.join(resultpath, 'my_model.h5')) model2.compile(loss=categorical_crossentropy, optimizer=Adam(), metrics=['accuracy']) test_loss, test_acc = model2.evaluate(X, Y, verbose=0) print('Test loss:', test_loss) print('Test accuracy:', test_acc) y = model2.predict_classes(X) print("predicct is: ", y) # the second way : load model structure and weights model = model_from_json(open(os.path.join(resultpath, 'my_model_structure.json')).read()) model.load_weights(os.path.join(resultpath, 'my_model_weights.hd5')) model.compile(loss=categorical_crossentropy, optimizer=Adam(), metrics=['accuracy']) test_loss, test_acc = model.evaluate(X, Y, verbose=0) print('Test loss:', test_loss) print('Test accuracy:', test_acc) y = model.predict_classes(X) print("predicct is: ", y) def main(): resultpath = "result" #train_model(resultpath) #my_save_model(resultpath) my_load_model(resultpath) if __name__ == "__main__": main()
以上这篇使用Keras建立模型并训练等一系列操作方式就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。
Keras,建立模型,训练
《魔兽世界》大逃杀!60人新游玩模式《强袭风暴》3月21日上线
暴雪近日发布了《魔兽世界》10.2.6 更新内容,新游玩模式《强袭风暴》即将于3月21 日在亚服上线,届时玩家将前往阿拉希高地展开一场 60 人大逃杀对战。
艾泽拉斯的冒险者已经征服了艾泽拉斯的大地及遥远的彼岸。他们在对抗世界上最致命的敌人时展现出过人的手腕,并且成功阻止终结宇宙等级的威胁。当他们在为即将于《魔兽世界》资料片《地心之战》中来袭的萨拉塔斯势力做战斗准备时,他们还需要在熟悉的阿拉希高地面对一个全新的敌人──那就是彼此。在《巨龙崛起》10.2.6 更新的《强袭风暴》中,玩家将会进入一个全新的海盗主题大逃杀式限时活动,其中包含极高的风险和史诗级的奖励。
《强袭风暴》不是普通的战场,作为一个独立于主游戏之外的活动,玩家可以用大逃杀的风格来体验《魔兽世界》,不分职业、不分装备(除了你在赛局中捡到的),光是技巧和战略的强弱之分就能决定出谁才是能坚持到最后的赢家。本次活动将会开放单人和双人模式,玩家在加入海盗主题的预赛大厅区域前,可以从强袭风暴角色画面新增好友。游玩游戏将可以累计名望轨迹,《巨龙崛起》和《魔兽世界:巫妖王之怒 经典版》的玩家都可以获得奖励。
更新动态
- 凤飞飞《我们的主题曲》飞跃制作[正版原抓WAV+CUE]
- 刘嘉亮《亮情歌2》[WAV+CUE][1G]
- 红馆40·谭咏麟《歌者恋歌浓情30年演唱会》3CD[低速原抓WAV+CUE][1.8G]
- 刘纬武《睡眠宝宝竖琴童谣 吉卜力工作室 白噪音安抚》[320K/MP3][193.25MB]
- 【轻音乐】曼托凡尼乐团《精选辑》2CD.1998[FLAC+CUE整轨]
- 邝美云《心中有爱》1989年香港DMIJP版1MTO东芝首版[WAV+CUE]
- 群星《情叹-发烧女声DSD》天籁女声发烧碟[WAV+CUE]
- 刘纬武《睡眠宝宝竖琴童谣 吉卜力工作室 白噪音安抚》[FLAC/分轨][748.03MB]
- 理想混蛋《Origin Sessions》[320K/MP3][37.47MB]
- 公馆青少年《我其实一点都不酷》[320K/MP3][78.78MB]
- 群星《情叹-发烧男声DSD》最值得珍藏的完美男声[WAV+CUE]
- 群星《国韵飘香·贵妃醉酒HQCD黑胶王》2CD[WAV]
- 卫兰《DAUGHTER》【低速原抓WAV+CUE】
- 公馆青少年《我其实一点都不酷》[FLAC/分轨][398.22MB]
- ZWEI《迟暮的花 (Explicit)》[320K/MP3][57.16MB]