def _predict(self, X):
if not self._initialized:
raise NotFittedError()
predict_data_feeder = setup_predict_data_feeder(X)
preds = []
for data in predict_data_feeder:
preds.append(
self._session.run(self._model_predictions,
feed_dict={self._inp.name: data}))
return np.concatenate(preds, axis=0)
def _predict(self, X):
if not self._initialized:
raise NotFittedError()
predict_data_feeder = setup_predict_data_feeder(X)
preds = []
for data in predict_data_feeder:
preds.append(self._session.run(
self._model_predictions,
feed_dict={
self._inp.name: data
}))
return np.concatenate(preds, axis=0)
def _predict(self, X):
if not self._initialized:
raise NotFittedError()
self._graph.add_to_collection("IS_TRAINING", False)
predict_data_feeder = setup_predict_data_feeder(X)
preds = []
dropouts = self._graph.get_collection(DROPOUTS)
feed_dict = {prob: 1.0 for prob in dropouts}
for data in predict_data_feeder:
feed_dict[self._inp] = data
preds.append(self._session.run(self._model_predictions, feed_dict))
return np.concatenate(preds, axis=0)
def _predict(self, X):
if not self._initialized:
raise NotFittedError()
predict_data_feeder = setup_predict_data_feeder(X)
preds = []
dropouts = self._graph.get_collection(DROPOUTS)
feed_dict = {prob: 1.0 for prob in dropouts}
for data in predict_data_feeder:
feed_dict[self._inp] = data
preds.append(self._session.run(
self._model_predictions,
feed_dict))
return np.concatenate(preds, axis=0)
def _predict(self, X, axis=-1, batch_size=-1):
if not self._initialized:
raise NotFittedError()
self._graph.add_to_collection("IS_TRAINING", False)
predict_data_feeder = setup_predict_data_feeder(X,
batch_size=batch_size)
preds = []
dropouts = self._graph.get_collection(DROPOUTS)
feed_dict = {prob: 1.0 for prob in dropouts}
for data in predict_data_feeder:
feed_dict[self._inp] = data
predictions_for_batch = self._session.run(self._model_predictions,
feed_dict)
if self.n_classes > 1 and axis != -1:
preds.append(predictions_for_batch.argmax(axis=axis))
else:
preds.append(predictions_for_batch)
return np.concatenate(preds, axis=0)
def _predict(self, X, axis=-1, batch_size=-1):
if not self._initialized:
raise NotFittedError()
self._graph.add_to_collection("IS_TRAINING", False)
predict_data_feeder = setup_predict_data_feeder(
X, batch_size=batch_size)
preds = []
dropouts = self._graph.get_collection(DROPOUTS)
feed_dict = {prob: 1.0 for prob in dropouts}
for data in predict_data_feeder:
feed_dict[self._inp] = data
predictions_for_batch = self._session.run(
self._model_predictions,
feed_dict)
if self.n_classes > 1 and axis != -1:
preds.append(predictions_for_batch.argmax(axis=axis))
else:
preds.append(predictions_for_batch)
return np.concatenate(preds, axis=0)
def test_iterable_data(self):
X = iter([[1, 2], [3, 4], [5, 6]])
df = setup_predict_data_feeder(X, batch_size=2)
self.assertAllClose(six.next(df), [[1, 2], [3, 4]])
self.assertAllClose(six.next(df), [[5, 6]])
def test_iterable_data(self):
X = iter([[1, 2], [3, 4], [5, 6]])
df = setup_predict_data_feeder(X, batch_size=2)
self.assertAllClose(six.next(df), [[1, 2], [3, 4]])
self.assertAllClose(six.next(df), [[5, 6]])
