Question

from sklearn.model_selection import KFold
from sklearn.model_selection import StratifiedKFold
seed = 7
np.random.seed(seed)
kfold = StratifiedKFold(n_splits=5, shuffle=True, random_state=seed)
cvscores = []

for train, test in kfold.split(x_train, y_train):

# create model

  densenet=keras.applications.densenet.DenseNet121(include_top=False,
  weights='imagenet', input_shape=(32,32,3))
  for layer in densenet.layers:
       layer.trainable=False

  classes = 18

 x = GlobalAveragePooling2D()(densenet.output)
 x = Dropout(0.25)(x)
 x = BatchNormalization(axis=-1)(x)
 x = Dense(classes, name='fc6',activation='sigmoid')(x)


 #create graph of your new model
 model = Model(inputs = densenet.input, outputs = x)
 model.compile(loss='binary_crossentropy', optimizer='adam', metrics= 
 ['accuracy'])
 # Fit the model
 model.fit(x_train[train], y_train[train], epochs=150, batch_size=10, 
 verbose=0)
 # evaluate the model
 scores = model.evaluate(x_test[test], y_test[test], verbose=0)
 print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
 cvscores.append(scores[1] * 100)
 print("%.2f%% (+/- %.2f%%)" % (numpy.mean(cvscores), numpy.std(cvscores)))

对于多标签分类，我必须在keras中进行k折交叉验证。上面的代码不起作用，因为y_train是矩阵而不是向量。在多标签分类的情况下，如何执行k折交叉验证？

k元组多标签分类

0 个答案: