本文整理汇总了Python中sklearn.neural_network.BernoulliRBM.batch_size方法的典型用法代码示例。如果您正苦于以下问题：Python BernoulliRBM.batch_size方法的具体用法？Python BernoulliRBM.batch_size怎么用？Python BernoulliRBM.batch_size使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类sklearn.neural_network.BernoulliRBM的用法示例。
在下文中一共展示了BernoulliRBM.batch_size方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: train_new
# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import batch_size [as 别名]
def train_new(path):
thumbnail = get_thumbnail(Image.open('images/{0}'.format(path)))
vectors = []
for pixel_tuple in thumbnail.getdata():
vec = []
for val in pixel_tuple:
vec.append(float(val))
vectors.append(vec)
X = np.asarray(vectors, 'float32')
Y = np.array(X.shape)
X = (X - np.min(X, 0)) / (np.max(X, 0) + 0.0001)
rbm = BernoulliRBM(random_state=1, verbose=True)
rbm.learning_rate = 0.09
rbm.n_iter = 1
rbm.n_components = 16
rbm.batch_size = 2
return rbm.fit(X).components_示例2: train
# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import batch_size [as 别名]
def train(image_matrix, images):
X = np.asarray(image_matrix, 'float32')
Y = np.array(X.shape)
X = (X - np.min(X, 0)) / (np.max(X, 0) + 0.0001)
rbm = BernoulliRBM(random_state=1, verbose=True)
rbm.learning_rate = 0.09
rbm.n_iter = 1
rbm.n_components = 16
rbm.batch_size = 2
y_new = np.zeros(X.shape)
for i in range(len(X)):
x_new = rbm.fit(X[i])
y_new[i] = x_new.components_
global model
model = {
'matrix': y_new,
'images': images
}示例3: BernoulliRBM
# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import batch_size [as 别名]
# Models we will use
logistic = linear_model.LogisticRegression()
rbm = BernoulliRBM(random_state=0, verbose=True)
classifier = Pipeline(steps=[("rbm", rbm), ("logistic", logistic)])
###############################################################################
# Training
# Hyper-parameters. These were set by cross-validation,
# using a GridSearchCV. Here we are not performing cross-validation to
# save time.
rbm.learning_rate = learning_rate
rbm.n_iter = training_epochs
rbm.batch_size = batch_size
# More components tend to give better prediction performance, but larger
# fitting time
rbm.n_components = n_hidden
logistic.C = 1000.0
# Training RBM-Logistic Pipeline
classifier.fit(np_train_set[:, n_labels:], Y_train)
# Training Logistic regression
logistic_classifier = linear_model.LogisticRegression(C=100.0)
logistic_classifier.fit(X_train, Y_train)
###############################################################################
# Evaluation