I am trying to use a fine-tuning approach to retrain a model. As a sanity check I tried to retrain it while first freezing all of its the layers. I expected that the model will not change; I was surprised to see this:
Epoch 1/50
16/16 [==============================] - 25s - loss: 4.0006 - acc: 0.5000 - val_loss: 1.3748e-04 - val_acc: 1.0000
Epoch 2/50
16/16 [==============================] - 24s - loss: 3.8861 - acc: 0.5000 - val_loss: 1.7333e-04 - val_acc: 1.0000
Epoch 3/50
16/16 [==============================] - 25s - loss: 3.9560 - acc: 0.5000 - val_loss: 3.0870e-04 - val_acc: 1.0000
Epoch 4/50
16/16 [==============================] - 26s - loss: 3.9730 - acc: 0.5000 - val_loss: 7.5931e-04 - val_acc: 1.0000
Epoch 5/50
16/16 [==============================] - 26s - loss: 3.7195 - acc: 0.5000 - val_loss: 0.0021 - val_acc: 1.0000
Epoch 6/50
16/16 [==============================] - 25s - loss: 3.9514 - acc: 0.5000 - val_loss: 0.0058 - val_acc: 1.0000
Epoch 7/50
16/16 [==============================] - 26s - loss: 3.9459 - acc: 0.5000 - val_loss: 0.0180 - val_acc: 1.0000
Epoch 8/50
16/16 [==============================] - 26s - loss: 3.8744 - acc: 0.5000 - val_loss: 0.0489 - val_acc: 1.0000
Epoch 9/50
16/16 [==============================] - 27s - loss: 3.8914 - acc: 0.5000 - val_loss: 0.1100 - val_acc: 1.0000
Epoch 10/50
16/16 [==============================] - 26s - loss: 4.0585 - acc: 0.5000 - val_loss: 0.2092 - val_acc: 0.7500
Epoch 11/50
16/16 [==============================] - 27s - loss: 4.0232 - acc: 0.5000 - val_loss: 0.3425 - val_acc: 0.7500
Epoch 12/50
16/16 [==============================] - 25s - loss: 3.9073 - acc: 0.5000 - val_loss: 0.4566 - val_acc: 0.7500
Epoch 13/50
16/16 [==============================] - 27s - loss: 4.1036 - acc: 0.5000 - val_loss: 0.5454 - val_acc: 0.7500
Epoch 14/50
16/16 [==============================] - 26s - loss: 3.7854 - acc: 0.5000 - val_loss: 0.6213 - val_acc: 0.7500
Epoch 15/50
16/16 [==============================] - 27s - loss: 3.7907 - acc: 0.5000 - val_loss: 0.7120 - val_acc: 0.7500
Epoch 16/50
16/16 [==============================] - 27s - loss: 4.0540 - acc: 0.5000 - val_loss: 0.7226 - val_acc: 0.7500
Epoch 17/50
16/16 [==============================] - 26s - loss: 3.8669 - acc: 0.5000 - val_loss: 0.8032 - val_acc: 0.7500
Epoch 18/50
16/16 [==============================] - 28s - loss: 3.9834 - acc: 0.5000 - val_loss: 0.9523 - val_acc: 0.7500
Epoch 19/50
16/16 [==============================] - 27s - loss: 3.9495 - acc: 0.5000 - val_loss: 2.5764 - val_acc: 0.6250
Epoch 20/50
16/16 [==============================] - 25s - loss: 3.7534 - acc: 0.5000 - val_loss: 3.0939 - val_acc: 0.6250
Epoch 21/50
16/16 [==============================] - 29s - loss: 3.8447 - acc: 0.5000 - val_loss: 3.0467 - val_acc: 0.6250
Epoch 22/50
16/16 [==============================] - 28s - loss: 4.0613 - acc: 0.5000 - val_loss: 3.2160 - val_acc: 0.6250
Epoch 23/50
16/16 [==============================] - 28s - loss: 4.1428 - acc: 0.5000 - val_loss: 3.8793 - val_acc: 0.6250
Epoch 24/50
16/16 [==============================] - 27s - loss: 3.7868 - acc: 0.5000 - val_loss: 4.1935 - val_acc: 0.6250
Epoch 25/50
16/16 [==============================] - 28s - loss: 3.8437 - acc: 0.5000 - val_loss: 4.5031 - val_acc: 0.6250
Epoch 26/50
16/16 [==============================] - 28s - loss: 3.9798 - acc: 0.5000 - val_loss: 4.5121 - val_acc: 0.6250
Epoch 27/50
16/16 [==============================] - 28s - loss: 3.8727 - acc: 0.5000 - val_loss: 4.5341 - val_acc: 0.6250
Epoch 28/50
16/16 [==============================] - 28s - loss: 3.8343 - acc: 0.5000 - val_loss: 4.5198 - val_acc: 0.6250
Epoch 29/50
16/16 [==============================] - 28s - loss: 4.2144 - acc: 0.5000 - val_loss: 4.5341 - val_acc: 0.6250
Epoch 30/50
16/16 [==============================] - 28s - loss: 3.8348 - acc: 0.5000 - val_loss: 4.5684 - val_acc: 0.6250
This is the code I used:
from keras import backend as K
import inception_v4
import numpy as np
import cv2
import os
import re
from keras import optimizers
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.layers import Activation, Dropout, Flatten, Dense, Input
from keras.models import Model
os.environ['CUDA_VISIBLE_DEVICES'] = ''
v4 = inception_v4.create_model(weights='imagenet')
#v4.summary()
my_batch_size=1
train_data_dir ='//shared_directory/projects/try_CDFxx/data/train/'
validation_data_dir ='//shared_directory/projects/try_CDFxx/data/validation/'
top_model_weights_path= 'bottleneck_fc_model.h5'
class_num=2
img_width, img_height = 299, 299
nbr_train_samples=16
nbr_validation_samples=8
num_classes=2
nb_epoch=50
main_input= v4.layers[1].input
main_output=v4.layers[-1].output
flatten_output= v4.layers[-2].output
BN_model = Model(input=[main_input], output=[main_output, flatten_output])
### DEF
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.1,
zoom_range=0.1,
rotation_range=10.,
width_shift_range=0.1,
height_shift_range=0.1,
horizontal_flip=True)
val_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size = (img_width, img_height),
batch_size = my_batch_size,
shuffle = True,
class_mode = 'categorical')
validation_generator = val_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=my_batch_size,
shuffle = True,
class_mode = 'categorical') # sparse
###
def save_BN(BN_model): # but we will need to get the get_processed_image into it!!!!
#
datagen = ImageDataGenerator(rescale=1./255) # here!
#
generator = datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=my_batch_size,
class_mode='categorical',
shuffle=False)
nb_train_samples = generator.classes.size
bottleneck_features_train = BN_model.predict_generator(generator, nb_train_samples)
#
np.save(open('bottleneck_flat_features_train.npy', 'wb'), bottleneck_features_train[1])
np.save(open('bottleneck_train_labels.npy', 'wb'), generator.classes)
# generator is probably a tuple - and the second thing in it is a label! OKAY, its not :(
generator = datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=my_batch_size,
class_mode='categorical',
shuffle=False)
nb_validation_samples = generator.classes.size
bottleneck_features_validation = BN_model.predict_generator(generator, nb_validation_samples)
#bottleneck_features_validation = model.train_generator(generator, nb_validation_samples)
#
np.save(open('bottleneck_flat_features_validation.npy', 'wb'), bottleneck_features_validation[1])
np.save(open('bottleneck_validation_labels.npy', 'wb'), generator.classes)
def train_top_model ():
train_data = np.load(open('bottleneck_flat_features_train.npy'))
train_labels = np.load(open('bottleneck_train_labels.npy'))
#
validation_data = np.load(open('bottleneck_flat_features_validation.npy'))
validation_labels = np.load(open('bottleneck_validation_labels.npy'))
#
top_m = Sequential()
top_m.add(Dense(class_num,input_shape=train_data.shape[1:], activation='softmax', name='top_dense1'))
top_m.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
#
top_m.fit(train_data, train_labels,
nb_epoch=nb_epoch, batch_size=my_batch_size,
validation_data=(validation_data, validation_labels))
#
#
#top_m.save_weights (top_model_weights_path)
# validation_data[0]
# train_data[0]
Dense_layer=top_m.layers[-1]
top_layer_weights=Dense_layer.get_weights()
np.save(open('retrained_top_layer_weight.npy', 'wb'), top_layer_weights)
def fine_tune_model ():
predictions = Flatten()(v4.layers[-3].output)
predictions = Dense(output_dim=num_classes, activation='softmax', name="newDense")(predictions)
main_input= v4.layers[1].input
main_output=predictions
FT_model = Model(input=[main_input], output=[main_output])
top_layer_weights = np.load(open('retrained_top_layer_weight.npy'))
Dense_layer=FT_model.layers[-1]
Dense_layer.set_weights(top_layer_weights)
for layer in FT_model.layers:
layer.trainable = False
# FT_model.layers[-1].trainable=True
FT_model.compile(optimizer=optimizers.SGD(lr=1e-4, momentum=0.9), loss='categorical_crossentropy', metrics=['accuracy'])
FT_model.fit_generator(
train_generator,
samples_per_epoch = nbr_train_samples,
nb_epoch = nb_epoch,
validation_data = validation_generator,
nb_val_samples = nbr_validation_samples)
########################################################
###########
save_BN(BN_model)
train_top_model()
fine_tune_model()
Thanks.
P.S. I'm using keras 1.
You are using dropout so metrics may vary across different runs as different units are turned off.