def initialize_dataset(self, tf_record, batch_size, shuffle_buffer=512):
"""
Initialize and prepare TFRecord dataset for training.
Args:
tf_record: TFRecord file.
batch_size: int, training batch size
shuffle_buffer: Buffer size for shuffling dataset.
Returns:
dataset.
"""
dataset = read_tfr(
tf_record, self.classes_file, get_feature_map(), self.max_boxes
)
dataset = dataset.shuffle(shuffle_buffer)
dataset = dataset.batch(batch_size)
dataset = dataset.map(
lambda x, y: (
transform_images(x, self.input_shape[0]),
transform_targets(
y, self.anchors, self.masks, self.input_shape[0]
),
)
)
dataset = dataset.prefetch(buffer_size=tf.data.experimental.AUTOTUNE)
return dataset
def make_predictions(
self,
trained_weights,
merge=False,
workers=16,
shuffle_buffer=512,
batch_size=64,
):
"""
Make predictions on both training and validation data sets
and save results as csv in Output folder.
Args:
trained_weights: Trained .tf weights or .weights file(in case self.classes = 80).
merge: If True a single file will be saved for training
and validation sets predictions combined.
workers: Parallel predictions.
shuffle_buffer: int, shuffle dataset buffer size.
batch_size: Prediction batch size.
Returns:
1 combined pandas DataFrame for entire dataset predictions
or 2 pandas DataFrame(s) for training and validation
data sets respectively.
"""
self.create_models()
self.load_weights(trained_weights)
features = get_feature_map()
train_dataset = read_tfr(
self.train_tf_record,
self.classes_file,
features,
self.max_boxes,
get_features=True,
)
valid_dataset = read_tfr(
self.valid_tf_record,
self.classes_file,
features,
self.max_boxes,
get_features=True,
)
train_dataset.shuffle(shuffle_buffer)
valid_dataset.shuffle(shuffle_buffer)
train_dataset = iter(train_dataset)
valid_dataset = iter(valid_dataset)
train_predictions = self.predict_dataset(
train_dataset, workers, 'train', batch_size
)
valid_predictions = self.predict_dataset(
valid_dataset, workers, 'valid', batch_size
)
if merge:
predictions = pd.concat([train_predictions, valid_predictions])
save_path = os.path.join(
'..', 'Output', 'Data', 'full_dataset_predictions.csv'
)
predictions.to_csv(save_path, index=False)
return predictions
train_path = os.path.join(
'..', 'Output', 'Data', 'train_dataset_predictions.csv'
)
valid_path = os.path.join(
'..', 'Output', 'Data', 'valid_dataset_predictions.csv'
)
train_predictions.to_csv(train_path, index=False)
valid_predictions.to_csv(valid_path, index=False)
return train_predictions, valid_predictions
