def fit(self, db: Dataset,
epochs: int = 1000001,
batch_size: int = 128,
patience: int = 20,
callbacks: list = []) -> History:
history = {'loss': [],
'val_loss': []}
epoch = []
for i in range(epochs):
anchor, positive, negetive = self._get_batch(
db.X_train, db.y_train, db.info['n_cls'], batch_size)
loss = self.model.train_on_batch(
[anchor, positive, negetive], anchor)
history['loss'].append(loss)
anchor, positive, negetive = self._get_batch(
db.X_test, db.y_test, db.info['n_cls'], batch_size)
val_loss = self.model.test_on_batch(
[anchor, positive, negetive], anchor)
history['val_loss'].append(val_loss)
epoch.append(i)
if not i % 100:
print("Batch %d --> loss: %.5f - val_loss: %.5f" %
(i, loss, val_loss))
if i and history['val_loss'][-101] <= val_loss:
patience -= 1
if not patience:
break
return History(epoch=epoch, history=history)
def fit_on_batch(self,
db: Dataset,
gen: BaseGenerator,
epochs: int = 1000000,
batch_size: int = 128,
patience: int = 100,
verbose: int = 2,
callbacks: list = []) -> History:
history = {}
for item in self.model.metrics_names:
history.update({item: []})
history.update({'val_' + item: []})
def _print_report(ltype, metrics_value):
i = 0
for item in self.model.metrics_names:
if ltype == 'train':
print("%s: %.5f - " % (item, metrics_value[i]), end='')
elif ltype == 'test':
print("%s: %.5f - " % ('val_' + item, metrics_value[i]),
end='')
i += 1
def _update_history(ltype, metrics_value):
i = 0
for item in self.model.metrics_names:
if ltype == 'train':
history[item].append(metrics_value[i])
elif ltype == 'test':
history['val_' + item].append(metrics_value[i])
i += 1
epoch = []
for i in range(epochs):
X_data, y_data = gen.get_batch()
metrics_value = self.model.train_on_batch(
X_data, to_categorical(y_data, num_classes=db.info['n_cls']))
_update_history('train', metrics_value)
val_metrics_value = self.model.test_on_batch(
db.X_test, db.Y_test())
_update_history('test', val_metrics_value)
epoch.append(i)
if not i % 100:
print("Batch %d --> " % i, end='')
_print_report('train', metrics_value)
_print_report('test', val_metrics_value)
print('')
if i and history['val_loss'][-101] <= val_metrics_value[0]:
patience -= 1
if not patience:
break
return History(epoch=epoch, history=history)
def fit(self,
db: Dataset,
epochs: int = 1000001,
batch_size: int = 128,
patience: int = 20) -> History:
history = {}
for item in self.model.metrics_names:
history.update({item: []})
history.update({'val_' + item: []})
def _print_report(ltype, metrics_value):
i = 0
for item in self.model.metrics_names:
if ltype == 'train':
print("%s: %.5f - " % (item, metrics_value[i]), end='')
elif ltype == 'test':
print("%s: %.5f - " % ('val_' + item, metrics_value[i]),
end='')
i += 1
def _update_history(ltype, metrics_value):
i = 0
for item in self.model.metrics_names:
if ltype == 'train':
history[item].append(metrics_value[i])
elif ltype == 'test':
history['val_' + item].append(metrics_value[i])
i += 1
epoch = []
for i in range(epochs):
in_1, in_2, out = self._get_batch(db.X_train, db.y_train,
db.info['n_cls'], batch_size)
metrics_value = self.model.train_on_batch([in_1, in_2], out)
_update_history('train', metrics_value)
in_1, in_2, out = self._get_batch(db.X_test, db.y_test,
db.info['n_cls'], batch_size)
val_metrics_value = self.model.test_on_batch([in_1, in_2], out)
_update_history('test', val_metrics_value)
epoch.append(i)
if not i % 100:
print("Batch %d --> " % i, end='')
_print_report('train', metrics_value)
_print_report('test', val_metrics_value)
print('')
if i and history['val_loss'][-101] <= val_metrics_value[0]:
patience -= 1
if not patience:
break
return History(epoch=epoch, history=history)
def fit(self,
db: Dataset,
epochs: int = 1000,
batch_size: int = 128,
verbose: int = 2,
callbacks: list = []) -> History:
history = self.model.fit(db.X_train,
db.Y_train(),
validation_data=(db.X_test, db.Y_test()),
epochs=epochs,
batch_size=batch_size,
verbose=verbose,
callbacks=callbacks)
return History(history.epoch, history.params, history.history)