def test(epoch, mode=1):
import matplotlib.pyplot as plt
from PIL import Image
from networks.capsulenet.helper_function import combine_images
if mode == 1:
num_classes =10
_,(x_test,y_test) = load_cifar_10()
else:
num_classes = 100
_,(x_test,y_test) = load_cifar_100()
model = CapsNetv2(input_shape=[32, 32, 3],
n_class=num_classes,
n_route=3)
model.load_weights('weights/capsule_weights/capsule-cifar-'+str(num_classes)+'weights-{:02d}.h5'.format(epoch))
print("Weights loaded, start validation")
# model.load_weights('weights/capsule-weights-{:02d}.h5'.format(epoch))
y_pred, x_recon = model.predict([x_test, y_test], batch_size=100)
print('-'*50)
# Test acc: 0.7307
print('Test acc:', np.sum(np.argmax(y_pred, 1) == np.argmax(y_test, 1))/y_test.shape[0])
img = combine_images(np.concatenate([x_test[:50],x_recon[:50]]))
image = img*255
Image.fromarray(image.astype(np.uint8)).save("results/real_and_recon.png")
print('Reconstructed images are saved to ./results/real_and_recon.png')
print('-'*50)
plt.imshow(plt.imread("results/real_and_recon.png", ))
plt.show()
def train(epochs=50, batch_size=64, mode=1):
import numpy as np
import os
from keras import callbacks
from keras.utils.vis_utils import plot_model
if mode == 1:
num_classes = 10
(x_train, y_train), (x_test, y_test) = load_cifar_10()
else:
num_classes = 100
(x_train, y_train), (x_test, y_test) = load_cifar_100()
model = CapsNetv1(input_shape=[32, 32, 3], n_class=num_classes, n_route=3)
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
model.summary()
log = callbacks.CSVLogger('networks/models/results/capsule-cifar-' +
str(num_classes) + '-log.csv')
tb = callbacks.TensorBoard(
log_dir='networks/models/results/tensorboard-capsule-cifar-' +
str(num_classes) + '-logs',
batch_size=batch_size,
histogram_freq=True)
checkpoint = callbacks.ModelCheckpoint('networks/models/capsnet.h5',
save_best_only=True,
verbose=1)
lr_decay = callbacks.LearningRateScheduler(
schedule=lambda epoch: 0.001 * np.exp(-epoch / 10.))
# plot_model(model, to_file='models/capsule-cifar-'+str(num_classes)+'.png', show_shapes=True)
model.compile(optimizer=optimizers.Adam(lr=0.001),
loss=[margin_loss, 'mse'],
loss_weights=[1., 0.1],
metrics={
'output_recon': 'accuracy',
'output': 'accuracy'
})
from networks.capsulenet.helper_function import data_generator
generator = data_generator(x_train, y_train, batch_size)
# Image generator significantly increase the accuracy and reduce validation loss
model.fit_generator(generator,
steps_per_epoch=x_train.shape[0] // batch_size,
validation_data=([x_test, y_test], [y_test, x_test]),
epochs=epochs,
verbose=1,
max_q_size=100,
callbacks=[log, tb, checkpoint, lr_decay])
return model
def train(epochs=50,batch_size=64,mode=1):
import numpy as np
import os
from keras import callbacks
from keras.utils.vis_utils import plot_model
if mode==1:
num_classes = 10
(x_train,y_train),(x_test,y_test) = load_cifar_10()
else:
num_classes = 100
(x_train,y_train),(x_test,y_test) = load_cifar_100()
model = CapsNetv1(input_shape=[32, 32, 3],
n_class=num_classes,
n_route=3)
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
model.summary()
log = callbacks.CSVLogger('networks/models/results/capsule-cifar-'+str(num_classes)+'-log.csv')
tb = callbacks.TensorBoard(log_dir='networks/models/results/tensorboard-capsule-cifar-'+str(num_classes)+'-logs',
batch_size=batch_size, histogram_freq=True)
checkpoint = callbacks.ModelCheckpoint('networks/models/capsnet.h5',
save_best_only=True, verbose=1)
lr_decay = callbacks.LearningRateScheduler(schedule=lambda epoch: 0.001 * np.exp(-epoch / 10.))
# plot_model(model, to_file='models/capsule-cifar-'+str(num_classes)+'.png', show_shapes=True)
model.compile(optimizer=optimizers.Adam(lr=0.001),
loss=[margin_loss, 'mse'],
loss_weights=[1., 0.1],
metrics={'output_recon':'accuracy','output':'accuracy'})
from networks.capsulenet.helper_function import data_generator
generator = data_generator(x_train,y_train,batch_size)
# Image generator significantly increase the accuracy and reduce validation loss
model.fit_generator(generator,
steps_per_epoch=x_train.shape[0] // batch_size,
validation_data=([x_test, y_test], [y_test, x_test]),
epochs=epochs, verbose=1, max_q_size=100,
callbacks=[log,tb,checkpoint,lr_decay])
return model