【发布时间】：2018-04-27 00:59:21
【问题描述】：
我想在 keras 中使用 fit_generator 作为输入对模型的参数进行网格搜索
我在堆栈溢出中找到下面的代码并更改它
1- 但我不明白如何将 fit_generator 或 flow_from_directory 赋予 fit 函数（代码中的最后一行）
2-如何添加提前停止？
谢谢
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.wrappers.scikit_learn import KerasClassifier
from keras import backend as K
from sklearn.grid_search import GridSearchCV
from tqdm import tqdm # a nice pretty percentage bar for tasks. Thanks to viewer Daniel Bühler for this suggestion
import os # dealing with directories
import numpy as np # dealing with arrays
from random import shuffle # mixing up or currently ordered data that might lead our network astray in training.
num_classes = 10
# input image dimensions
img_rows, img_cols = 28, 28
input_shape = (img_rows, img_cols, 1)
def make_model(dense_layer_sizes, filters, kernel_size, pool_size):
'''Creates model comprised of 2 convolutional layers followed by dense layers
dense_layer_sizes: List of layer sizes.
This list has one number for each layer
filters: Number of convolutional filters in each convolutional layer
kernel_size: Convolutional kernel size
pool_size: Size of pooling area for max pooling
'''
model = Sequential()
model.add(Conv2D(filters, kernel_size,
padding='valid',
input_shape=input_shape))
model.add(Activation('relu'))
model.add(Conv2D(filters, kernel_size))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten())
for layer_size in dense_layer_sizes:
model.add(Dense(layer_size))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy'])
return model
class KerasClassifier(KerasClassifier):
""" adds sparse matrix handling using batch generator
"""
def fit(self, x, y, **kwargs):
""" adds sparse matrix handling """
if not issparse(x):
return super().fit(x, y, **kwargs)
############ adapted from KerasClassifier.fit ######################
if self.build_fn is None:
self.model = self.__call__(**self.filter_sk_params(self.__call__))
elif not isinstance(self.build_fn, types.FunctionType):
self.model = self.build_fn(
**self.filter_sk_params(self.build_fn.__call__))
else:
self.model = self.build_fn(**self.filter_sk_params(self.build_fn))
loss_name = self.model.loss
if hasattr(loss_name, '__name__'):
loss_name = loss_name.__name__
if loss_name == 'categorical_crossentropy' and len(y.shape) != 2:
y = to_categorical(y)
### fit => fit_generator
fit_args = copy.deepcopy(self.filter_sk_params(Sequential.fit_generator))
fit_args.update(kwargs)
############################################################
self.model.fit_generator(
self.get_batch(x, y, self.sk_params["batch_size"]),
samples_per_epoch=x.shape[0],
**fit_args)
return self
def get_batch(self, x, y=None, batch_size=32):
""" batch generator to enable sparse input """
index = np.arange(x.shape[0])
start = 0
while True:
if start == 0 and y is not None:
np.random.shuffle(index)
batch = index[start:start+batch_size]
if y is not None:
yield x[batch].toarray(), y[batch]
else:
yield x[batch].toarray()
start += batch_size
if start >= x.shape[0]:
start = 0
def predict_proba(self, x):
""" adds sparse matrix handling """
if not issparse(x):
return super().predict_proba(x)
preds = self.model.predict_generator(
self.get_batch(x, None, self.sk_params["batch_size"]),
val_samples=x.shape[0])
return preds
dense_size_candidates = [[32], [64], [32, 32], [64, 64]]
my_classifier = KerasClassifier(make_model, batch_size=32)
validator = GridSearchCV(my_classifier,
param_grid={'dense_layer_sizes': dense_size_candidates,
# epochs is avail for tuning even when not
# an argument to model building function
'epochs': [3, 6],
'filters': [8],
'kernel_size': [3],
'pool_size': [2]},
scoring='neg_log_loss',
n_jobs=1)
batch_size = 20
validation_datagen = ImageDataGenerator(rescale=1./255)
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
'd:/train', # this is the target directory
target_size=(width, height), # all images will be resized to 150x150
batch_size=batch_size,
color_mode= "grayscale",
class_mode='binary',
shuffle=True
# ,save_to_dir='preview', save_prefix='cat', save_format='png'
) # since we use binary_crossentropy loss, we need binary labels
# this is a similar generator, for validation data
validation_generator = validation_datagen.flow_from_directory(
'd:/validation',
target_size=(width, height),
batch_size=batch_size,
color_mode= "grayscale",
class_mode='binary')
test_generator = test_datagen.flow_from_directory(
'd:/test',
target_size=(width, height),
batch_size=batch_size,
color_mode= "grayscale",
class_mode='binary')
validator.fit(??????
【问题讨论】：
标签： python scikit-learn keras cross-validation hyperparameters