def main():
file_name = os.path.basename(__file__).split('.')[0]
name = str(file_name)
experiment_logger = utils.ExperimentLogger(name)
for i, (samples_train,
samples_val) in enumerate(utils.mask_stratified_k_fold()):
print("Running split {}".format(i))
model = Model(name, i)
stats = model.fit(samples_train, samples_val)
experiment_logger.set_split(i, stats)
# Load the best performing checkpoint
model.load()
# Do a final validation
model.validate(DataParallel(model.net), samples_val, -1)
# Predict the test data
test_predictions = utils.TestPredictions(name + '-split_{}'.format(i),
mode='test')
test_predictions.add_predictions(model.test(utils.get_test_samples()))
test_predictions.save()
experiment_logger.save()
description='Validate a experiment with different test time augmentations.'
)
parser.add_argument(
'name',
help='Use one of the experiment names here excluding the .py ending.')
parser.add_argument('test_set', help='Specify the path to the new test_set')
parser.add_argument(
'output_dir',
help='Specify the path to the output dir for the test-predictions.')
args = parser.parse_args()
name = args.name
test_set = args.test_set
output_dir = args.output_dir
experiment_logger = utils.ExperimentLogger(name, mode='val')
for i, (samples_train,
samples_val) in enumerate(utils.mask_stratified_k_fold()):
# Get the model architecture
Model = locate('experiments.' + name + '.Model')
model = Model(name, i)
# Load the best performing checkpoint
model.load()
# Predict the test data
test_predictions = utils.TestPredictions(name + '-split_{}'.format(i),
mode=output_dir)
test_predictions.add_predictions(
model.test(utils.get_test_samples(test_set)))
import pandas as pd
import utils
import settings
parser = argparse.ArgumentParser(
description='Validate a experiment with different test time augmentations.'
)
parser.add_argument(
'name',
help='Use one of the experiment names here excluding the .py ending.')
args = parser.parse_args()
name = args.name
experiment_logger = utils.ExperimentLogger(name)
for i in range(5):
df_split = pd.read_csv('logs/epochs/{}-split_{}'.format(name, i),
delim_whitespace=True,
index_col=0)
split = df_split.as_matrix(
columns=['train_loss', 'train_iou', 'train_mAP', 'val_iou', 'val_mAP'])
best = split[split[:, 3].argsort()][-1]
best = {
'train_loss': best[0],
'train_iou': best[1],
'train_mAP': best[2],
'val_iou': best[3],
'val_mAP': best[4],
}
