def train_from_graphs(self,
train_graphs,
train_targets,
validation_graphs=None,
validation_targets=None,
epochs=1000,
batch_size=128,
verbose=1,
callbacks=None,
prev_model=None,
lr_scaling_factor=0.5,
patience=500,
**kwargs):
# load from saved model
if prev_model:
self.load_weights(prev_model)
# is_classification = 'entropy' in self.model.loss
# monitor = 'val_acc' if is_classification else 'val_mae'
# mode = 'max' if is_classification else 'min'
dirname = kwargs.pop('dirname', 'callback')
if not os.path.isdir(dirname):
os.makedirs(dirname)
if callbacks is None:
# with this call back you can stop the model training by `touch STOP`
callbacks = [ManualStop()]
train_nb_atoms = [len(i['atom']) for i in train_graphs]
train_targets = [
self.target_scaler.transform(i, j)
for i, j in zip(train_targets, train_nb_atoms)
]
if validation_graphs is not None:
# filepath = os.path.join(dirname, '%s_{epoch:05d}_{%s:.6f}.hdf5' % (monitor, monitor))
val_nb_atoms = [len(i['atom']) for i in validation_graphs]
validation_targets = [
self.target_scaler.transform(i, j)
for i, j in zip(validation_targets, val_nb_atoms)
]
val_inputs = self.graph_converter.get_flat_data(
validation_graphs, validation_targets)
val_generator = self._create_generator(*val_inputs,
batch_size=batch_size)
steps_per_val = int(np.ceil(len(validation_graphs) / batch_size))
# callbacks.extend([ReduceLRUponNan(filepath=filepath,
# monitor=monitor,
# mode=mode,
# factor=lr_scaling_factor,
# patience=patience,
# )])
# callbacks.extend([ModelCheckpointMAE(filepath=filepath,
# monitor=monitor,
# mode=mode,
# save_best_only=True,
# save_weights_only=False,
# val_gen=val_generator,
# steps_per_val=steps_per_val,
# target_scaler=self.target_scaler)])
else:
val_generator = None
steps_per_val = None
train_inputs = self.graph_converter.get_flat_data(
train_graphs, train_targets)
# check dimension match
self.check_dimension(train_graphs[0])
train_generator = self._create_generator(*train_inputs,
batch_size=batch_size)
steps_per_train = int(np.ceil(len(train_graphs) / batch_size))
self.fit_generator(train_generator,
steps_per_epoch=steps_per_train,
validation_data=val_generator,
validation_steps=steps_per_val,
epochs=epochs,
verbose=verbose,
callbacks=callbacks,
**kwargs)
Args:
ids (List): list of ids
Returns:
list of graphs and list of target values
"""
ids = [i for i in ids if i in final_graphs]
return [final_graphs[i] for i in ids], [final_targets[i] for i in ids]
train_graphs, train_targets = get_graphs_targets(train_ids)
val_graphs, val_targets = get_graphs_targets(val_ids)
# 5. Model training
callbacks = [ReduceLRUponNan(patience=500), ManualStop()]
model.train_from_graphs(train_graphs,
train_targets,
val_graphs,
val_targets,
epochs=EPOCHS,
verbose=2,
initial_epoch=0,
callbacks=callbacks)
# 6. Model testing
## load the best model with lowest validation error
files = glob('./callback/*.hdf5')
best_model = sorted(files, key=os.path.getctime)[-1]
