def main():
args = get_arguments()
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
model.create(charset, latent_rep_size=args.latent_dim)
checkpointer = ModelCheckpoint(filepath=args.model,
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
model.autoencoder.fit(data_train,
data_train,
shuffle=True,
epochs=args.epochs,
batch_size=args.batch_size,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test, data_test))
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from molecules.utils import one_hot_array, one_hot_index, from_one_hot_array, \
decode_smiles_from_indexes, load_dataset
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
model.create(charset, latent_rep_size=args.latent_dim)
checkpointer = ModelCheckpoint(filepath=args.model,
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
model.autoencoder.fit(data_train,
data_train,
shuffle=True,
epochs=args.epochs,
batch_size=args.batch_size,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test, data_test))
def main():
np.random.seed(RANDOM_SEED)
data_train, data_test, charset = load_dataset('data/processed.h5')
print("Charset", charset)
model = MoleculeVAE()
model.create(charset, latent_rep_size=292)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
checkpointer = ModelCheckpoint(filepath='model.h5',
verbose=1,
save_best_only=True)
history = model.autoencoder.fit(data_train[:1000],
data_train[:1000],
shuffle=True,
nb_epoch=NUM_EPOCHS,
batch_size=100,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test[:1000],
data_test[:1000]))
with open('trainHistoryDict', 'wb') as file_pi:
pickle.dump(history.history, file_pi)
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from molecules.utils import one_hot_array, one_hot_index, from_one_hot_array, \
decode_smiles_from_indexes, load_dataset
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size = args.latent_dim)
else:
model.create(charset, latent_rep_size = args.latent_dim)
checkpointer = ModelCheckpoint(filepath = args.model,
verbose = 1,
save_best_only = True)
reduce_lr = ReduceLROnPlateau(monitor = 'val_loss',
factor = 0.2,
patience = 3,
min_lr = 0.0001)
model.autoencoder.fit(
data_train,
data_train,
shuffle = True,
nb_epoch = args.epochs,
batch_size = args.batch_size,
callbacks = [checkpointer, reduce_lr],
validation_data = (data_test, data_test)
)
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data = pd.read_hdf(args.data, 'table')
structures = data['structure']
# import gzip
# filepath = args.data
# structures = [line.split()[0].strip() for line in gzip.open(filepath) if line]
# can also use CanonicalSmilesDataGenerator
datobj = SmilesDataGenerator(structures, MAX_LEN,
test_split=args.test_split,
random_seed=args.random_seed)
test_divisor = int((1 - datobj.test_split) / (datobj.test_split))
train_gen = datobj.train_generator(args.batch_size)
test_gen = datobj.test_generator(args.batch_size)
# reformulate generators to not use weights
train_gen = ((tens, tens) for (tens, _, weights) in train_gen)
test_gen = ((tens, tens) for (tens, _, weights) in test_gen)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(datobj.chars, args.model, latent_rep_size = args.latent_dim)
else:
model.create(datobj.chars, latent_rep_size = args.latent_dim)
checkpointer = ModelCheckpoint(filepath = args.model,
verbose = 1,
save_best_only = True)
reduce_lr = ReduceLROnPlateau(monitor = 'val_loss',
factor = 0.2,
patience = 3,
min_lr = 0.0001)
model.autoencoder.fit_generator(
train_gen,
args.epoch_size,
epochs = args.epochs,
callbacks = [checkpointer, reduce_lr],
validation_data = test_gen,
nb_val_samples = args.epoch_size / test_divisor,
pickle_safe = True
)
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data = pd.read_hdf(args.data, 'table')
structures = data['structure']
# import gzip
# filepath = args.data
# structures = [line.split()[0].strip() for line in gzip.open(filepath) if line]
# can also use CanonicalSmilesDataGenerator
datobj = SmilesDataGenerator(structures, MAX_LEN,
test_split=args.test_split,
random_seed=args.random_seed)
test_divisor = int((1 - datobj.test_split) / (datobj.test_split))
train_gen = datobj.train_generator(args.batch_size)
test_gen = datobj.test_generator(args.batch_size)
# reformulate generators to not use weights
train_gen = ((tens, tens) for (tens, _, weights) in train_gen)
test_gen = ((tens, tens) for (tens, _, weights) in test_gen)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(datobj.chars, args.model, latent_rep_size = args.latent_dim)
else:
model.create(datobj.chars, latent_rep_size = args.latent_dim)
checkpointer = ModelCheckpoint(filepath = args.model,
verbose = 1,
save_best_only = True)
reduce_lr = ReduceLROnPlateau(monitor = 'val_loss',
factor = 0.2,
patience = 3,
min_lr = 0.0001)
model.autoencoder.fit_generator(
train_gen,
args.epoch_size,
nb_epoch = args.epochs,
callbacks = [checkpointer, reduce_lr],
validation_data = test_gen,
nb_val_samples = args.epoch_size / test_divisor,
pickle_safe = True
)
from molecules.model import MoleculeVAE
from molecules.utils import one_hot_array, one_hot_index, from_one_hot_array, \
decode_smiles_from_indexes, load_dataset
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
NUM_EPOCHS = 100
BATCH_SIZE = 10
LATENT_DIM = 128
RANDOM_SEED = 123
np.random.seed(RANDOM_SEED) #args.random_seed)
data_train, data_test, charset = load_dataset('./data/processed.h5')
model = MoleculeVAE()
#model.load(charset, args.model, latent_rep_size = args.latent_dim)
model.create(charset, latent_rep_size=LATENT_DIM)
checkpointer = ModelCheckpoint(
filepath='./test_models/weights.{epoch:02d}-{val_loss:.2f}.hdf5',
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
data_train = data_train[:1]
model.autoencoder.fit(data_train,
data_train,
shuffle=True,