def main():
set_determinstic_mode(seed=1538574472)
args = _parse_args()
trainer = Trainer(args.config, args.device)
train_data = breakfast.get_mstcn_data('train')
test_data = breakfast.get_mstcn_data('test')
trainer.train(train_data, test_data)
def main():
set_determinstic_mode()
args = _parse_args()
if args.model == 'mstcn':
from scripts.action_segmentation.train_mstcn import Trainer
elif args.model == 'coarse-inputs':
from scripts.action_segmentation.train_coarse_inputs import Trainer
elif args.model == 'coarse-inputs-boundary-true':
from scripts.action_segmentation.train_coarse_inputs_boundary_true import Trainer
else:
raise ValueError('no such model')
submission_dir = os.path.join(SUBMISSION_DIR, args.model, args.config)
if not os.path.exists(submission_dir):
os.makedirs(submission_dir)
else:
raise ValueError(
submission_dir +
' exists, please delete if you want a new submission with this name'
)
trainer = Trainer(args.config, args.device)
if 'boundary' in args.model: # this is for boundary aware models
i3d_feats, timestamps = get_boundary_aware_submission_data()
frame_level_predictions = trainer.predict(i3d_feats, timestamps)
else:
submission_segments, _, _ = breakfast.get_mstcn_data(split='test')
frame_level_predictions = trainer.predict(submission_segments)
return get_cls_results(frame_level_predictions, submission_dir)
def main():
set_determinstic_mode()
args = _parse_args()
trainer = Trainer(args.config, args.device)
train_videos = get_train_videos()
test_videos = get_test_videos()
trainer.train(train_videos, test_videos)
def main():
set_determinstic_mode()
args = _parse_args()
trainer = Trainer(args.config, args.device)
train_data = _parse_split_data('train', trainer.i3d_length)
test_data = _parse_split_data('test', trainer.i3d_length)
trainer.train(train_data, test_data)
def main():
set_determinstic_mode()
args = _parse_args()
submission_dir = os.path.join(SUBMISSION_DIR, 'zhangcan', args.config)
submission_feats, _, _ = breakfast.get_mstcn_data(split='test')
frame_prediction_dir = submission_dir
video_names = [
os.path.split(feat_file)[-1] for feat_file in submission_feats
]
video_names = [feat_file.split('.')[0] for feat_file in video_names]
mapping_dict = breakfast.read_mapping_file()
frame_level_predictions = []
for i, video_name in enumerate(video_names):
frame_prediction_file = os.path.join(frame_prediction_dir, video_name)
with open(frame_prediction_file, 'r') as f:
frame_predictions = f.readlines()[1]
frame_predictions = frame_predictions.strip().split(' ')
frame_predictions = [
mapping_dict[prediction] for prediction in frame_predictions
]
frame_level_predictions.append(frame_predictions)
with open(breakfast.SUBMISSION_LABEL_FILE, 'r') as f:
submission_timestamps = f.readlines()
submission_timestamps = [
line.strip().split(' ') for line in submission_timestamps
]
submission_timestamps = [
np.array(timestamps).astype(int)
for timestamps in submission_timestamps
]
n_segments = 0
submission_str = 'Id,Category\n'
for i, video_name in enumerate(video_names):
video_timestamps = submission_timestamps[i]
n_timestamps = len(video_timestamps)
video_frame_predictions = frame_level_predictions[i]
for j in range(n_timestamps - 1):
start = video_timestamps[j]
end = video_timestamps[j + 1]
segment_frame_predictions = video_frame_predictions[start:end]
counts = np.bincount(segment_frame_predictions)
segment_prediction = np.argmax(counts).item()
submission_str += '{0},{1}\n'.format(n_segments,
segment_prediction)
n_segments += 1
submission_file = os.path.join(submission_dir, 'submission.csv')
with open(submission_file, 'w') as f:
f.write(submission_str)
get_submission_accuracy(submission_file)