def train(model, model_name):
loader = DataLoader()
pretrain_data, pretrain_labels, pretrain_names = loader.load_pretrain_datasets(
)
# pretrain model
model.fit(pretrain_data,
pretrain_labels,
batch_size=BATCH_SIZE,
epochs=PRETRAIN_EPOCHS)
deep_utils.create_directory("../models")
model_filename = "../models/pretrained_" + model_name + ".h5"
model.save(model_filename)
train_data, train_labels, train_names = loader.load_train_datasets()
test_data, test_labels, test_names = loader.load_test_datasets()
# train model
model.fit(train_data,
train_labels,
validation_data=(test_data, test_labels),
batch_size=BATCH_SIZE,
epochs=TRAIN_EPOCHS)
deep_utils.create_directory("../models")
model_filename = "../models/fine_tuned_" + model_name + ".h5"
model.save(model_filename)
# evaluate model
scores = model.evaluate(test_data, test_labels, verbose=1)
return scores
def train(model, model_name, train_datasets, test_datasets):
train_data = train_datasets[0]
train_labels = train_datasets[1]
train_names = train_datasets[2]
test_data = test_datasets[0]
test_labels = test_datasets[1]
test_names = test_datasets[2]
# train model
model.fit(train_data,
train_labels,
validation_data=(test_data, test_labels),
batch_size=BATCH_SIZE,
epochs=EPOCHS)
# save model
if SAVE_MODEL:
deep_utils.create_directory("../models")
model_filename = "../models/allmirbase_" + model_name + ".h5"
model.save(model_filename)
scores = model.evaluate(test_data, test_labels, verbose=1)
return scores
def pretrain(model, model_name, pretrain_datasets):
pretrain_data = pretrain_datasets[0]
pretrain_labels = pretrain_datasets[1]
# pretrain model
model.fit(pretrain_data,
pretrain_labels,
batch_size=BATCH_SIZE,
epochs=PRETRAIN_EPOCHS,
verbose=2)
deep_utils.create_directory("../models")
model_filename = "../models/kfold_hsa_pretrain_" + model_name + ".h5"
model.save(model_filename)
return model_filename
def train(model, model_name):
loader = DataLoader()
train_data, train_labels, train_names = loader.load_train_datasets()
test_data, test_labels, test_names = loader.load_test_datasets()
model.fit(train_data,
train_labels,
batch_size=BATCH_SIZE,
epochs=TRAIN_EPOCHS,
validation_data=(test_data, test_labels),
shuffle=True)
# save trained model
deep_utils.create_directory("../models")
model_filename = "../models/base_" + model_name + ".h5"
model.save(model_filename)
scores = model.evaluate(test_data, test_labels, verbose=1)
return scores
def train(model, model_name):
# load data
loader = DataLoaderAllmirbase()
train_data, train_labels, train_names = loader.load_train_datasets()
test_data, test_labels, test_names = loader.load_test_datasets()
# train model
model.fit(train_data,
train_labels,
validation_data=(test_data, test_labels),
batch_size=BATCH_SIZE,
epochs=EPOCHS)
# save model
if SAVE_MODEL:
deep_utils.create_directory("../models")
model_filename = "../models/allmirbase_" + model_name + ".h5"
model.save(model_filename)
# evaluate model
scores = model.evaluate(test_data, test_labels, verbose=1)
return scores
def train(model, pretrain_datasets, train_datasets, test_datasets, model_name):
pretrain_data = pretrain_datasets[0]
pretrain_labels = pretrain_datasets[1]
pretrain_names = pretrain_datasets[2]
train_data = train_datasets[0]
train_labels = train_datasets[1]
train_names = train_datasets[2]
test_data = test_datasets[0]
test_labels = test_datasets[1]
test_names = test_datasets[2]
model.fit(pretrain_data,
pretrain_labels,
batch_size=BATCH_SIZE,
epochs=PRETRAIN_EPOCHS,
shuffle=True)
# train_model
model.fit(train_data,
train_labels,
batch_size=BATCH_SIZE,
epochs=TRAIN_EPOCHS,
validation_data=(test_data, test_labels),
shuffle=True)
# save trained model
if SAVE_MODEL:
deep_utils.create_directory("../models")
model_filename = "../models/hsa_" + model_name + ".h5"
model.save(model_filename)
scores = model.evaluate(test_data, test_labels, verbose=1)
return scores