def load_model():
model_weights_path = 'models/model.89-0.90.hdf5'
img_width, img_height = 224, 224
num_channels = 3
num_classes = 196
model = resnet50_model(img_height, img_width, num_channels, num_classes)
model.load_weights(model_weights_path, by_name=True)
return model
def load_model():
model_weights_path = 'G:/fyp/resnet_50/model/epoch_100_aug/model.48-0.89.hdf5'
img_width, img_height = 224, 224
num_channels = 3
num_classes = 196
model = resnet50_model(img_height, img_width, num_channels, num_classes)
model.load_weights(model_weights_path, by_name=True)
return model
def load_model():
model_weights_path = 'models/model.09-0.98.hdf5'
# img_width, img_height = 224, 224
num_channels = 3
num_classes = 3
# num_classes = 196
# model = resnet152_model(IMG_WIDTH, IMG_HEIGHT, num_channels, num_classes)
model = resnet50_model(IMG_WIDTH, IMG_HEIGHT, num_channels, num_classes)
model.load_weights(model_weights_path, by_name=True)
return model
import keras
from resnet_50 import resnet50_model
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import CSVLogger, ModelCheckpoint, EarlyStopping
from keras.callbacks import ReduceLROnPlateau
from keras.models import Model
img_width, img_height = 224, 224
num_channels = 3
num_classes = 196
resnet = resnet50_model(img_height, img_width, num_channels, num_classes)
for layer in resnet.layers:
layer.trainable = False
model = Model(inputs=resnet.input, outputs=resnet.output)
model.summary()
def getResNet50(self, train_images, train_labels, load_saved_model,
model_save_path, use_pretraining, pretrained_weights_path, train_dir,
val_dir, fine_tuning_method, batch_size, num_epochs, optimizer, loss, initial_epoch, sample, lr=None):
"""
:param load_saved_model: boolean (whether to just load the model from weights path)
:param model_save_path: (final model weights path, if load_pretrained is true)
:param pretrained_weights_path: if load_trained is false and if use_pretraining is true, the path of weights to load for pre-training
:param train_dir: training data directory
:param val_dir: validation data directory
:param use_pretraining: boolean, whether to use pre-training or train from scratch
:param fine_tuning_method: whether to use end-to-end pre-training or phase-by-phase pre-training
:param initial_epoch: starting epoch to start training
:return: Returns the AlexNet model according to the parameters provided
"""
print(get_time_string() + 'Creating ResNet50 model..')
img_rows, img_cols = 224, 224 # Resolution of inputs
channels = 3
if load_saved_model:
if model_save_path is None:
raise Exception('Unable to load trained model as model_save_path is None!')
print(get_time_string() + 'Loading saved model from ' + model_save_path + '..')
model = load_model(model_save_path)
else:
model = resnet50_model(img_rows, img_cols, channels, NUM_CLASSES_YEARBOOK, use_pretraining,
pretrained_weights_path,
fine_tuning_method, optimizer, loss)
if initial_epoch >= num_epochs:
print(get_time_string() + 'Not fitting the model since initial_epoch is >= num_epochs. Returning model..')
return model
# Start Fine-tuning
print(get_time_string() + 'Fitting the model..')
for e in range(initial_epoch, num_epochs):
print_line()
print('Starting epoch ' + str(e))
print_line()
completed = 0
for x_chunk, y_chunk in chunks(train_images, train_labels, batch_size, RESNET50_ARCHITECTURE):
print(get_time_string() + 'Fitting model for chunk of size ' + str(len(x_chunk)) + '...')
model.fit(x_chunk, y_chunk,
batch_size=batch_size,
nb_epoch=1,
verbose=1
)
completed += len(x_chunk)
print(get_time_string() + str(completed) + ' of ' + str(len(train_images)) + ' complete. ')
file_name = self.getCheckpointFileName(base_model_save_path=model_save_path, epoch=e)
print(get_time_string() + 'Saving model to ' + file_name)
model.save(file_name)
if (e % 5 == 0):
print(get_time_string() + 'Epoch ' + str(e) + ' complete. Evaluating on validation set..')
evaluateYearbookFromModel(model=model, architecture=RESNET50_ARCHITECTURE, sample=sample)
print_line()
print(get_time_string() + 'Fitting complete. Returning model..')
if model_save_path is not None:
print(get_time_string() + 'Saving final model to ' + model_save_path + '..')
model.save(model_save_path)
return model