-
- libigfat 2020-06-27
Dense全连接层
Activation激活层
SGD随机梯度下降算法
标签先独热码化
- 0赞 · 0采集
-
- AY9717 2019-07-21
给你们代码，写的啥咱也不知道，咱也不敢问 # __author__ = 'aaron' __date__ = '7/20/2019 11:19 AM' import numpy from keras.models import Sequential from keras.layers import Dense, Activation from keras.optimizers import SGD def main(): from sklearn.datasets import load_iris iris = load_iris() print(iris["target"]) from sklearn.preprocessing import LabelBinarizer print(LabelBinarizer().fit_transform(iris["target"])) from sklearn.model_selection import train_test_split train_data, test_data, train_target, test_target = train_test_split(iris.data, iris.target, test_size=0.2, random_state=1) labels_train = LabelBinarizer().fit_transform(train_target) labels_test = LabelBinarizer().fit_transform(test_target) model = Sequential( [ Dense(5, input_dim=4), Activation("relu"), Dense(3), Activation("sigmoid"), ] ) sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True) model.compile(optimizer=sgd, loss="categorical_crossentropy") model.fit(train_data, labels_train, nb_epoch=200, batch_size=40) print(model.predict_classes(test_data)) if __name__ == "__main__": main()- 0赞 · 0采集
-
- 慕UI606399 2019-01-14
由于Anaconda不包含keras,所以需要额外安装，操作如下：
- 0赞 · 0采集
-
- MOOC扛把子 2018-11-18
markmark
- 0赞 · 0采集
-
- 人在梦游中 2018-05-23
keras安装
-
截图0赞 · 0采集
-
- Uestc_L 2017-08-01
- from keras.models import Sequential #sequential神经网络各个层的容器 from keras.layers import Dense, Activation #dense是加权求和的层，后者是激活函数 from keras.optimizers import SGD from sklearn.datasets import load_iris from sklearn.cross_validation import train_test_split from sklearn.preprocessing import LabelBinarizer def main(): iris = load_iris() train_data, test_data, train_target, test_target = train_test_split(iris.data, iris.target, test_size=0.2, random_state=1) labels_train = LabelBinarizer().fit_transform(train_target) model = Sequential( [ Dense(5, input_dim=4), Activation("relu"), Dense(3), # label 0 1 2 Activation("sigmoid") ] ) sgd=SGD(lr=0.01, decay=1e-6, momentum=0.9) model.compile(optimizer=sgd, loss="categorical_crossentropy") model.fit(train_data, labels_train, nb_epoch=200, batch_size=40) print(model.predict_classes(test_data)) print(test_target) if __name__=="__main__" : main()
- 1赞 · 1采集
-
- Uestc_L 2017-08-01
- keras 的安装 1.Anaconda CMD 2.conda install mingw libpython 3.pip install keras
- 0赞 · 0采集
-
- 隔壁王爷爷 2017-07-26
- #encoding=utf-8 from keras.models import Sequential from keras.layers import Dense, Activation from keras.optimizers import SGD from sklearn.datasets import load_iris from sklearn.cross_validation import train_test_split from sklearn.preprocessing import LabelBinarizer def main(): iris = load_iris() train_data, test_data, train_target, test_target = train_test_split(iris.data, iris.target, test_size=0.2, random_state=1) labels_train = LabelBinarizer().fit_transform(train_target) model = Sequential( [ Dense(5, input_dim=4), Activation("relu"), Dense(3), # label 0 1 2 Activation("sigmoid") ] ) sgd=SGD(lr=0.01, decay=1e-6, momentum=0.9) model.compile(optimizer=sgd, loss="categorical_crossentropy") model.fit(train_data, labels_train, nb_epoch=200, batch_size=40) print(model.predict_classes(test_data)) print(test_target) if __name__=="__main__" : main()
- 0赞 · 0采集
-
- qq_大饼光_0 2017-07-23
- from keras.models import Sequential from keras.layers import Dense, Activation from keras.optimizers import SGD from sklearn.cross_validation import train_test_split def main(): pass if __name__=="__main__": main()
- 0赞 · 0采集
数据加载中...