I have some problem when I use centerloss in image classification with keras.
1、in custom_vgg_model.fit(y = {'fc2':y_train,'predictions':y_train}),'fc2':y_train have error that
ValueError: Error when checking target: expected fc2 to have shape (None, 4096) but got array with shape (6300, 45)
y_train is the labels. If I do like this custom_vgg_model.fit(y = {'fc2':dummy1,'predictions':y_train}),the model will train successful. The dummy1 have same shape with 'fc2' output(feature).
dummy1 = np.zeros((y_train.shape[0],4096))
But can't improve the accuracy of the model.So it is wrong coding.
2、It is wrong to use ImageDataGenerator.flow(x = X_train, y = {'fc2':dummy1,'predictions':y_train}, batch_size=batch_Sizes) .So I can't expand my data.
image_input = Input(shape=(224, 224, 3))
model = VGG16(input_tensor=image_input, include_top=True,weights='imagenet')
model.summary()
last_layer = model.get_layer('fc2').output
feature = last_layer
out = Dense(num_classes,activation = 'softmax',name='predictions')(last_layer)
custom_vgg_model = Model(inputs = image_input, outputs = [out,feature])
custom_vgg_model.summary()
for layer in custom_vgg_model.layers[:-3]:
layer.trainable = False
custom_vgg_model.layers[3].trainable
sgd = optimizers.SGD(lr=learn_Rate,decay=decay_Rate,momentum=0.9,nesterov=True)
center_loss = lossclass.get_center_loss(alpha=0.5, num_classes=45,feature_dim = 4096)
custom_vgg_model.compile(loss={'predictions': "categorical_crossentropy", 'fc2': center_loss},
loss_weights={'fc2': 1, 'predictions': 1},optimizer= sgd,
metrics={'predictions': 'accuracy'})
t=time.time()
dummy1 = np.zeros((y_train.shape[0],4096))
dummy2 = np.zeros((y_test.shape[0],4096))
if not data_Augmentation:
hist = custom_vgg_model.fit(x = X_train,y = {'fc2':y_train,'predictions':y_train},batch_size=batch_Sizes,
epochs=epoch_Times, verbose=1,validation_data=(X_test, {'fc2':y_test,'predictions':y_test}))
else:
datagen = ImageDataGenerator(
featurewise_center=False,
samplewise_center=False,
featurewise_std_normalization=False,
samplewise_std_normalization=False,
zca_whitening=False,
rotation_range=20,
width_shift_range=0.2,
height_shift_range=0.2,
horizontal_flip=True,
vertical_flip=True,
rescale=None,
preprocessing_function=None,
data_format=None)
print('x_train.shape[0]:{:d}'.format(X_train.shape[0]))
hist = custom_vgg_model.fit_generator(datagen.flow(x = X_train, y = {'fc2':dummy1,'predictions':y_train}, batch_size=batch_Sizes),
steps_per_epoch=X_train.shape[0]/batch_Sizes,epochs=epoch_Times,
verbose=1, validation_data=(X_test, {'fc2':y_test,'predictions':y_test}))
# lossclass.py
def _center_loss_func(labels,features, alpha, num_classes, centers, feature_dim):
assert feature_dim == features.get_shape()[1]
labels = K.argmax(labels, axis=1)
labels = tf.to_int32(labels)
centers_batch = K.gather(centers, labels)
diff = (1 - alpha) * (centers_batch - features)
centers = tf.scatter_sub(centers, labels, diff)
centers_batch = K.gather(centers, labels)
loss = K.mean(K.square(features - centers_batch))
return loss
def get_center_loss(alpha, num_classes, feature_dim):
"""Center loss based on the paper "A Discriminative
Feature Learning Approach for Deep Face Recognition"
(http://ydwen.github.io/papers/WenECCV16.pdf)
"""
# Each output layer use one independed center: scope/centers
centers = K.zeros([num_classes, feature_dim], dtype='float32')
@functools.wraps(_center_loss_func)
def center_loss(y_true, y_pred):
return _center_loss_func(y_true, y_pred, alpha, num_classes, centers, feature_dim)
return center_loss