mirror of
https://github.com/wassname/keras-contrib.git
synced 2026-07-25 13:20:46 +08:00
97 lines
3.8 KiB
Python
97 lines
3.8 KiB
Python
"""
|
|
Adapted from keras example cifar10_cnn.py and github.com/raghakot/keras-resnet
|
|
Train ResNet-18 on the CIFAR10 small images dataset.
|
|
|
|
GPU run command with Theano backend (with TensorFlow, the GPU is automatically used):
|
|
THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python cifar10.py
|
|
"""
|
|
from __future__ import print_function
|
|
from keras.datasets import cifar10
|
|
from keras.preprocessing.image import ImageDataGenerator
|
|
from keras.utils import np_utils
|
|
from keras.callbacks import ModelCheckpoint
|
|
from keras.callbacks import ReduceLROnPlateau
|
|
from keras.callbacks import CSVLogger
|
|
from keras.callbacks import EarlyStopping
|
|
from keras_contrib.applications.resnet import ResNet18
|
|
|
|
import numpy as np
|
|
|
|
|
|
weights_file = 'ResNet18v2-CIFAR-10.h5'
|
|
lr_reducer = ReduceLROnPlateau(factor=np.sqrt(0.1), cooldown=0, patience=5, min_lr=0.5e-6)
|
|
early_stopper = EarlyStopping(min_delta=0.001, patience=10)
|
|
csv_logger = CSVLogger('ResNet18v2-CIFAR-10.csv')
|
|
model_checkpoint = ModelCheckpoint(weights_file, monitor='val_acc', save_best_only=True,
|
|
save_weights_only=True, mode='auto')
|
|
|
|
batch_size = 32
|
|
nb_classes = 10
|
|
nb_epoch = 200
|
|
data_augmentation = True
|
|
|
|
# input image dimensions
|
|
img_rows, img_cols = 32, 32
|
|
# The CIFAR10 images are RGB.
|
|
img_channels = 3
|
|
|
|
# The data, shuffled and split between train and test sets:
|
|
(X_train, y_train), (X_test, y_test) = cifar10.load_data()
|
|
|
|
# Convert class vectors to binary class matrices.
|
|
Y_train = np_utils.to_categorical(y_train, nb_classes)
|
|
Y_test = np_utils.to_categorical(y_test, nb_classes)
|
|
|
|
X_train = X_train.astype('float32')
|
|
X_test = X_test.astype('float32')
|
|
|
|
# subtract mean and normalize
|
|
mean_image = np.mean(X_train, axis=0)
|
|
X_train -= mean_image
|
|
X_test -= mean_image
|
|
X_train /= 128.
|
|
X_test /= 128.
|
|
|
|
model = ResNet18((img_rows, img_cols, img_channels), nb_classes)
|
|
model.compile(loss='categorical_crossentropy',
|
|
optimizer='adam',
|
|
metrics=['accuracy'])
|
|
|
|
if not data_augmentation:
|
|
print('Not using data augmentation.')
|
|
model.fit(X_train, Y_train,
|
|
batch_size=batch_size,
|
|
nb_epoch=nb_epoch,
|
|
validation_data=(X_test, Y_test),
|
|
shuffle=True,
|
|
callbacks=[lr_reducer, early_stopper, csv_logger, model_checkpoint])
|
|
else:
|
|
print('Using real-time data augmentation.')
|
|
# This will do preprocessing and realtime data augmentation:
|
|
datagen = ImageDataGenerator(
|
|
featurewise_center=False, # set input mean to 0 over the dataset
|
|
samplewise_center=False, # set each sample mean to 0
|
|
featurewise_std_normalization=False, # divide inputs by std of the dataset
|
|
samplewise_std_normalization=False, # divide each input by its std
|
|
zca_whitening=False, # apply ZCA whitening
|
|
rotation_range=0, # randomly rotate images in the range (degrees, 0 to 180)
|
|
width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)
|
|
height_shift_range=0.1, # randomly shift images vertically (fraction of total height)
|
|
horizontal_flip=True, # randomly flip images
|
|
vertical_flip=False) # randomly flip images
|
|
|
|
# Compute quantities required for featurewise normalization
|
|
# (std, mean, and principal components if ZCA whitening is applied).
|
|
datagen.fit(X_train)
|
|
|
|
# Fit the model on the batches generated by datagen.flow().
|
|
model.fit_generator(datagen.flow(X_train, Y_train, batch_size=batch_size),
|
|
steps_per_epoch=X_train.shape[0] // batch_size,
|
|
validation_data=(X_test, Y_test),
|
|
epochs=nb_epoch, verbose=2,
|
|
callbacks=[lr_reducer, early_stopper, csv_logger, model_checkpoint])
|
|
|
|
scores = model.evaluate(X_test, Y_test, batch_size=batch_size)
|
|
print('Test loss : ', scores[0])
|
|
print('Test accuracy : ', scores[1])
|