def project_details(project):
"""
Show the details for the selected project.
"""
project = urllib.parse.unquote(project)
path = utils.lookup_project_path(project)
config = utils.load_project_config(path)
stats = {}
for class_name, tags in config['classes'].items():
stats[class_name] = {}
for split in SPLITS:
videos_dir = directories.get_videos_dir(path, split, class_name)
tags_dir = directories.get_tags_dir(path, split, class_name)
stats[class_name][split] = {
'total':
len(os.listdir(videos_dir)),
'tagged':
len(os.listdir(tags_dir)) if os.path.exists(tags_dir) else 0,
}
return render_template('project_details.html',
config=config,
path=path,
stats=stats,
project=config['name'])
def edit_class(project, class_name):
"""
Edit the class name and tags for an existing class in the given project.
"""
project = urllib.parse.unquote(project)
class_name = urllib.parse.unquote(class_name)
path = project_utils.lookup_project_path(project)
# Get new class name and tags
new_class_name, new_tag1, new_tag2 = utils.get_class_name_and_tags(
request.form)
# Update project config
config = project_utils.load_project_config(path)
del config['classes'][class_name]
config['classes'][new_class_name] = [new_tag1, new_tag2]
project_utils.write_project_config(path, config)
# Update directory names
data_dirs = []
for split in SPLITS:
data_dirs.extend([
directories.get_videos_dir(path, split),
directories.get_frames_dir(path, split),
directories.get_tags_dir(path, split),
])
# Feature directories follow the format <dataset_dir>/<split>/<model>/<num_layers_to_finetune>/<label>
features_dir = directories.get_features_dir(path, split)
if os.path.exists(features_dir):
model_dirs = [
os.path.join(features_dir, model_dir)
for model_dir in os.listdir(features_dir)
]
data_dirs.extend([
os.path.join(model_dir, tuned_layers)
for model_dir in model_dirs
for tuned_layers in os.listdir(model_dir)
])
logreg_dir = directories.get_logreg_dir(path)
if os.path.exists(logreg_dir):
data_dirs.extend([
os.path.join(logreg_dir, model_dir)
for model_dir in os.listdir(logreg_dir)
])
for base_dir in data_dirs:
class_dir = os.path.join(base_dir, class_name)
if os.path.exists(class_dir):
new_class_dir = os.path.join(base_dir, new_class_name)
os.rename(class_dir, new_class_dir)
return redirect(url_for('project_details', project=project))
def show_video_list(project, split, label):
"""
Show the list of videos for the given split, class label and project.
If the necessary files for annotation haven't been prepared yet, this is done now.
"""
project = urllib.parse.unquote(project)
path = project_utils.lookup_project_path(project)
split = urllib.parse.unquote(split)
label = urllib.parse.unquote(label)
# load feature extractor
inference_engine, model_config = utils.load_feature_extractor(path)
videos_dir = directories.get_videos_dir(path, split, label)
frames_dir = directories.get_frames_dir(path, split, label)
features_dir = directories.get_features_dir(path,
split,
model_config,
label=label)
tags_dir = directories.get_tags_dir(path, split, label)
logreg_dir = directories.get_logreg_dir(path, model_config, label)
os.makedirs(logreg_dir, exist_ok=True)
os.makedirs(tags_dir, exist_ok=True)
# compute the features and frames missing
compute_frames_and_features(inference_engine=inference_engine,
project_path=path,
videos_dir=videos_dir,
frames_dir=frames_dir,
features_dir=features_dir)
videos = os.listdir(frames_dir)
videos = natsorted(videos, alg=ns.IC)
tagged_list = set(os.listdir(tags_dir))
tagged = [f'{video}.json' in tagged_list for video in videos]
num_videos = len(videos)
num_tagged = len(tagged_list)
num_untagged = num_videos - num_tagged
video_list = zip(videos, tagged, list(range(len(videos))))
return render_template('video_list.html',
video_list=video_list,
split=split,
label=label,
path=path,
project=project,
num_videos=num_videos,
num_tagged=num_tagged,
num_untagged=num_untagged)
def submit_annotation():
"""
Submit annotated tags for all frames and save them to a json file.
"""
data = request.form # a multi-dict containing POST data
idx = int(data['idx'])
fps = float(data['fps'])
path = data['path']
project = data['project']
split = data['split']
label = data['label']
video = data['video']
next_frame_idx = idx + 1
frames_dir = directories.get_frames_dir(path, split, label)
tags_dir = directories.get_tags_dir(path, split, label)
description = {'file': f'{video}.mp4', 'fps': fps}
out_annotation = os.path.join(tags_dir, f'{video}.json')
time_annotation = []
for frame_idx in range(int(data['n_images'])):
time_annotation.append(int(data[f'{frame_idx}_tag']))
description['time_annotation'] = time_annotation
with open(out_annotation, 'w') as f:
json.dump(description, f, indent=2)
# Automatic re-training of the logistic regression model
if utils.get_project_setting(path, 'assisted_tagging'):
train_logreg(path=path)
if next_frame_idx >= len(os.listdir(frames_dir)):
return redirect(
url_for('.show_video_list',
project=project,
split=split,
label=label))
return redirect(
url_for('.annotate',
split=split,
label=label,
project=project,
idx=next_frame_idx))
def project_details(project):
"""
Show the details for the selected project.
"""
project = urllib.parse.unquote(project)
path = project_utils.lookup_project_path(project)
config = project_utils.load_project_config(path)
stats = {}
for class_name in config['classes']:
stats[class_name] = {}
for split in SPLITS:
videos_dir = directories.get_videos_dir(path, split, class_name)
tags_dir = directories.get_tags_dir(path, split, class_name)
stats[class_name][split] = {
'total': len(os.listdir(videos_dir)),
'tagged': len(os.listdir(tags_dir)) if os.path.exists(tags_dir) else 0,
'videos': natsorted([video for video in os.listdir(videos_dir) if video.endswith(VIDEO_EXT)], alg=ns.IC)
}
tags = config['tags']
return render_template('project_details.html', config=config, path=path, stats=stats, project=config['name'],
tags=tags)
def train_model(path_in,
path_out,
model_name,
model_version,
num_layers_to_finetune,
epochs,
use_gpu=True,
overwrite=True,
temporal_training=None,
resume=False,
log_fn=print,
confmat_event=None):
os.makedirs(path_out, exist_ok=True)
# Check for existing files
saved_files = [
"last_classifier.checkpoint", "best_classifier.checkpoint",
"config.json", "label2int.json", "confusion_matrix.png",
"confusion_matrix.npy"
]
if not overwrite and any(
os.path.exists(os.path.join(path_out, file))
for file in saved_files):
print(f"Warning: This operation will overwrite files in {path_out}")
while True:
confirmation = input(
"Are you sure? Add --overwrite to hide this warning. (Y/N) ")
if confirmation.lower() == "y":
break
elif confirmation.lower() == "n":
sys.exit()
else:
print('Invalid input')
# Load weights
selected_config, weights = get_relevant_weights(
SUPPORTED_MODEL_CONFIGURATIONS,
model_name,
model_version,
log_fn,
)
backbone_weights = weights['backbone']
if resume:
# Load the last classifier
checkpoint_classifier = torch.load(
os.path.join(path_out, 'last_classifier.checkpoint'))
# Update original weights in case some intermediate layers have been finetuned
update_backbone_weights(backbone_weights, checkpoint_classifier)
# Load backbone network
backbone_network = build_backbone_network(selected_config,
backbone_weights)
# Get the required temporal dimension of feature tensors in order to
# finetune the provided number of layers
if num_layers_to_finetune > 0:
num_timesteps = backbone_network.num_required_frames_per_layer.get(
-num_layers_to_finetune)
if not num_timesteps:
# Remove 1 because we added 0 to temporal_dependencies
num_layers = len(
backbone_network.num_required_frames_per_layer) - 1
msg = (f'ERROR - Num of layers to finetune not compatible. '
f'Must be an integer between 0 and {num_layers}')
log_fn(msg)
raise IndexError(msg)
else:
num_timesteps = 1
# Extract layers to finetune
if num_layers_to_finetune > 0:
fine_tuned_layers = backbone_network.cnn[-num_layers_to_finetune:]
backbone_network.cnn = backbone_network.cnn[0:-num_layers_to_finetune]
# finetune the model
extract_features(path_in,
selected_config,
backbone_network,
num_layers_to_finetune,
use_gpu,
num_timesteps=num_timesteps,
log_fn=log_fn)
# Find label names
label_names = os.listdir(directories.get_videos_dir(path_in, 'train'))
label_names = [x for x in label_names if not x.startswith('.')]
label_names_temporal = ['background']
project_config = load_project_config(path_in)
if project_config:
for temporal_tags in project_config['classes'].values():
label_names_temporal.extend(temporal_tags)
else:
for label in label_names:
label_names_temporal.extend([f'{label}_tag1', f'{label}_tag2'])
label_names_temporal = sorted(set(label_names_temporal))
label2int_temporal_annotation = {
name: index
for index, name in enumerate(label_names_temporal)
}
label2int = {name: index for index, name in enumerate(label_names)}
extractor_stride = backbone_network.num_required_frames_per_layer_padding[
0]
# Create the data loaders
features_dir = directories.get_features_dir(path_in, 'train',
selected_config,
num_layers_to_finetune)
tags_dir = directories.get_tags_dir(path_in, 'train')
train_loader = generate_data_loader(
project_config,
features_dir,
tags_dir,
label_names,
label2int,
label2int_temporal_annotation,
num_timesteps=num_timesteps,
stride=extractor_stride,
temporal_annotation_only=temporal_training,
)
features_dir = directories.get_features_dir(path_in, 'valid',
selected_config,
num_layers_to_finetune)
tags_dir = directories.get_tags_dir(path_in, 'valid')
valid_loader = generate_data_loader(
project_config,
features_dir,
tags_dir,
label_names,
label2int,
label2int_temporal_annotation,
num_timesteps=None,
batch_size=1,
shuffle=False,
stride=extractor_stride,
temporal_annotation_only=temporal_training,
)
# Check if the data is loaded fully
if not train_loader or not valid_loader:
log_fn(
"ERROR - \n "
"\tMissing annotations for train or valid set.\n"
"\tHint: Check if tags_train and tags_valid directories exist.\n")
return
# Modify the network to generate the training network on top of the features
if temporal_training:
num_output = len(label_names_temporal)
else:
num_output = len(label_names)
# modify the network to generate the training network on top of the features
gesture_classifier = LogisticRegression(
num_in=backbone_network.feature_dim,
num_out=num_output,
use_softmax=False)
if resume:
gesture_classifier.load_state_dict(checkpoint_classifier)
if num_layers_to_finetune > 0:
# remove internal padding for training
fine_tuned_layers.apply(set_internal_padding_false)
net = Pipe(fine_tuned_layers, gesture_classifier)
else:
net = gesture_classifier
net.train()
if use_gpu:
net = net.cuda()
lr_schedule = {
0: 0.0001,
int(epochs / 2): 0.00001
} if epochs > 1 else {
0: 0.0001
}
num_epochs = epochs
# Save training config and label2int dictionary
config = {
'backbone_name': selected_config.model_name,
'backbone_version': selected_config.version,
'num_layers_to_finetune': num_layers_to_finetune,
'classifier': str(gesture_classifier),
'temporal_training': temporal_training,
'lr_schedule': lr_schedule,
'num_epochs': num_epochs,
'start_time': str(datetime.datetime.now()),
'end_time': '',
}
with open(os.path.join(path_out, 'config.json'), 'w') as f:
json.dump(config, f, indent=2)
with open(os.path.join(path_out, 'label2int.json'), 'w') as f:
json.dump(
label2int_temporal_annotation if temporal_training else label2int,
f,
indent=2)
# Train model
best_model_state_dict = training_loops(
net,
train_loader,
valid_loader,
use_gpu,
num_epochs,
lr_schedule,
label_names,
path_out,
temporal_annotation_training=temporal_training,
log_fn=log_fn,
confmat_event=confmat_event)
# Save best model
if isinstance(net, Pipe):
best_model_state_dict = {
clean_pipe_state_dict_key(key): value
for key, value in best_model_state_dict.items()
}
torch.save(best_model_state_dict,
os.path.join(path_out, "best_classifier.checkpoint"))
config['end_time'] = str(datetime.datetime.now())
with open(os.path.join(path_out, 'config.json'), 'w') as f:
json.dump(config, f, indent=2)
def _backwards_compatibility_update(path, config):
updated = False
if 'use_gpu' not in config:
config['use_gpu'] = False
updated = True
if 'temporal' not in config:
config['temporal'] = False
updated = True
if 'assisted_tagging' not in config:
config['assisted_tagging'] = False
updated = True
if 'video_recording' not in config:
config['video_recording'] = {
'countdown': 3,
'recording': 5,
}
updated = True
if 'tags' not in config:
# Collect class-wise tags
old_classes = config['classes']
tags_list = []
for class_name, class_tags in old_classes.items():
tags_list.extend(class_tags)
# Assign project-wide unique indices to tags (0 is reserved for 'background')
tags = {
idx + 1: tag_name
for idx, tag_name in enumerate(sorted(tags_list))
}
config['tags'] = tags
config['max_tag_index'] = len(tags_list)
# Setup class dictionary with tag indices
inverse_tags = {
tag_name: tag_idx
for tag_idx, tag_name in tags.items()
}
inverse_tags['background'] = 0
config['classes'] = {
class_name: [inverse_tags[tag_name] for tag_name in class_tags]
for class_name, class_tags in old_classes.items()
}
# Translate existing annotations
for split in SPLITS:
for label, label_tags in old_classes.items():
tags_dir = directories.get_tags_dir(path, split, label)
if os.path.exists(tags_dir):
label_tags = ['background'] + label_tags
for video_name in os.listdir(tags_dir):
annotation_file = os.path.join(tags_dir, video_name)
with open(annotation_file, 'r') as f:
annotation_data = json.load(f)
# Translate relative indices [0, 1, 2] to their names and then to their new absolute indices
new_annotations = [
inverse_tags[label_tags[idx]]
for idx in annotation_data['time_annotation']
]
annotation_data['time_annotation'] = new_annotations
with open(annotation_file, 'w') as f:
json.dump(annotation_data, f, indent=2)
updated = True
else:
# Translate string keys to integers (because JSON does not store integer keys)
config['tags'] = {
int(idx_str): tag_name
for idx_str, tag_name in config['tags'].items()
}
if updated:
# Save updated config
write_project_config(path, config)
return config
def train_logreg(path, split, label):
"""
(Re-)Train a logistic regression model on all annotations that have been submitted so far.
"""
_, model_config = load_feature_extractor(path)
features_dir = directories.get_features_dir(path,
split,
model_config,
label=label)
tags_dir = directories.get_tags_dir(path, split, label)
logreg_dir = directories.get_logreg_dir(path, model_config, label)
logreg_path = os.path.join(logreg_dir, 'logreg.joblib')
annotations = os.listdir(tags_dir) if os.path.exists(tags_dir) else None
if not annotations:
return
features = [
os.path.join(features_dir, x.replace('.json', '.npy'))
for x in annotations
]
annotations = [os.path.join(tags_dir, x) for x in annotations]
x = []
y = []
class_weight = {0: 0.5}
for feature in features:
feature = np.load(feature)
for f in feature:
x.append(f.mean(axis=(1, 2)))
for annotation in annotations:
with open(annotation, 'r') as f:
annotation = json.load(f)['time_annotation']
pos1 = np.where(np.array(annotation).astype(int) == 1)[0]
if len(pos1) > 0:
class_weight.update({1: 2})
for p in pos1:
if p + 1 < len(annotation):
annotation[p + 1] = 1
pos1 = np.where(np.array(annotation).astype(int) == 2)[0]
if len(pos1) > 0:
class_weight.update({2: 2})
for p in pos1:
if p + 1 < len(annotation):
annotation[p + 1] = 2
for a in annotation:
y.append(a)
x = np.array(x)
y = np.array(y)
if len(class_weight) > 1:
logreg = LogisticRegression(C=0.1, class_weight=class_weight)
logreg.fit(x, y)
dump(logreg, logreg_path)
def train_logreg():
"""
(Re-)Train a logistic regression model on all annotations that have been submitted so far.
"""
data = request.form # a multi-dict containing POST data
idx = int(data['idx'])
path = data['path']
project = data['project']
split = data['split']
label = data['label']
_, model_config = utils.load_feature_extractor(path)
features_dir = directories.get_features_dir(path,
split,
model_config,
label=label)
tags_dir = directories.get_tags_dir(path, split, label)
logreg_dir = directories.get_logreg_dir(path, model_config, label)
logreg_path = os.path.join(logreg_dir, 'logreg.joblib')
annotations = os.listdir(tags_dir)
class_weight = {0: 0.5}
if annotations:
features = [
os.path.join(features_dir, x.replace('.json', '.npy'))
for x in annotations
]
annotations = [os.path.join(tags_dir, x) for x in annotations]
X = []
y = []
for feature in features:
feature = np.load(feature)
for f in feature:
X.append(f.mean(axis=(1, 2)))
for annotation in annotations:
with open(annotation, 'r') as f:
annotation = json.load(f)['time_annotation']
pos1 = np.where(np.array(annotation).astype(int) == 1)[0]
if len(pos1) > 0:
class_weight.update({1: 2})
for p in pos1:
if p + 1 < len(annotation):
annotation[p + 1] = 1
pos1 = np.where(np.array(annotation).astype(int) == 2)[0]
if len(pos1) > 0:
class_weight.update({2: 2})
for p in pos1:
if p + 1 < len(annotation):
annotation[p + 1] = 2
for a in annotation:
y.append(a)
X = np.array(X)
y = np.array(y)
if len(class_weight) > 1:
logreg = LogisticRegression(C=0.1, class_weight=class_weight)
logreg.fit(X, y)
dump(logreg, logreg_path)
return redirect(
url_for('.annotate',
split=split,
label=label,
project=project,
idx=idx))
def annotate(project, split, label, idx):
"""
For the given class label, show all frames for annotating the selected video.
"""
project = urllib.parse.unquote(project)
path = utils.lookup_project_path(project)
label = urllib.parse.unquote(label)
split = urllib.parse.unquote(split)
_, model_config = utils.load_feature_extractor(path)
frames_dir = directories.get_frames_dir(path, split, label)
features_dir = directories.get_features_dir(path,
split,
model_config,
label=label)
tags_dir = directories.get_tags_dir(path, split, label)
logreg_dir = directories.get_logreg_dir(path, model_config, label)
videos = os.listdir(frames_dir)
videos.sort()
features = np.load(os.path.join(features_dir, f'{videos[idx]}.npy'))
features = features.mean(axis=(2, 3))
# Load logistic regression model if available
logreg_path = os.path.join(logreg_dir, 'logreg.joblib')
if os.path.isfile(logreg_path):
logreg = load(logreg_path)
classes = list(logreg.predict(features))
else:
classes = [-1] * len(features)
# The list of images in the folder
images = [
image
for image in glob.glob(os.path.join(frames_dir, videos[idx], '*'))
if utils.is_image_file(image)
]
# Natural sort images, so that they are sorted by number
images = natsorted(images, alg=ns.IC)
# Extract image file name (without full path) and include class label
images = [(os.path.basename(image), _class)
for image, _class in zip(images, classes)]
# Load existing annotations
annotations = []
annotations_file = os.path.join(tags_dir, f'{videos[idx]}.json')
if os.path.exists(annotations_file):
with open(annotations_file, 'r') as f:
data = json.load(f)
annotations = data['time_annotation']
# Read tags from config
config = utils.load_project_config(path)
tags = config['classes'][label]
return render_template('frame_annotation.html',
images=images,
annotations=annotations,
idx=idx,
fps=16,
n_images=len(images),
video_name=videos[idx],
split=split,
label=label,
path=path,
tags=tags,
project=project,
n_videos=len(videos))
def annotate(project, split, label, idx):
"""
For the given class label, show all frames for annotating the selected video.
"""
project = urllib.parse.unquote(project)
path = project_utils.lookup_project_path(project)
label = urllib.parse.unquote(label)
split = urllib.parse.unquote(split)
config = project_utils.load_project_config(path)
tags = config['tags'].copy()
tags[0] = 'background'
class_tags = config['classes'][label].copy()
class_tags.append(0) # Always add 'background'
class_tags.sort()
_, model_config = utils.load_feature_extractor(path)
frames_dir = directories.get_frames_dir(path, split, label)
features_dir = directories.get_features_dir(path,
split,
model_config,
label=label)
tags_dir = directories.get_tags_dir(path, split, label)
logreg_dir = directories.get_logreg_dir(path, model_config)
videos = os.listdir(frames_dir)
videos = natsorted(videos, alg=ns.IC)
# The list of images in the folder
images = [
image
for image in glob.glob(os.path.join(frames_dir, videos[idx], '*'))
if utils.is_image_file(image)
]
classes = [-1] * len(images)
# Load logistic regression model if available and assisted tagging is enabled
if utils.get_project_setting(path, 'assisted_tagging'):
logreg_path = os.path.join(logreg_dir, 'logreg.joblib')
features_path = os.path.join(features_dir, f'{videos[idx]}.npy')
if os.path.isfile(logreg_path) and os.path.isfile(features_path):
logreg = load(logreg_path)
features = np.load(features_path).mean(axis=(2, 3))
classes = list(logreg.predict(features))
# Reset tags that have been removed from the class to 'background'
classes = [
tag_idx if tag_idx in class_tags else 0 for tag_idx in classes
]
# Natural sort images, so that they are sorted by number
images = natsorted(images, alg=ns.IC)
# Extract image file name (without full path) and include class label
images = [(os.path.basename(image), _class)
for image, _class in zip(images, classes)]
# Load existing annotations
annotations_file = os.path.join(tags_dir, f'{videos[idx]}.json')
if os.path.exists(annotations_file):
with open(annotations_file, 'r') as f:
data = json.load(f)
annotations = data['time_annotation']
# Reset tags that have been removed from the class to 'background'
annotations = [
tag_idx if tag_idx in class_tags else 0
for tag_idx in annotations
]
else:
# Use "background" label for all frames per default
annotations = [0] * len(images)
return render_template('frame_annotation.html',
images=images,
annotations=annotations,
idx=idx,
fps=16,
n_images=len(images),
video_name=videos[idx],
project_config=config,
split=split,
label=label,
path=path,
project=project,
n_videos=len(videos),
tags=tags,
class_tags=class_tags)
def train_logreg(path):
"""
(Re-)Train a logistic regression model on all annotations that have been submitted so far.
"""
inference_engine, model_config = utils.load_feature_extractor(path)
logreg_dir = directories.get_logreg_dir(path, model_config)
logreg_path = os.path.join(logreg_dir, 'logreg.joblib')
project_config = project_utils.load_project_config(path)
classes = project_config['classes']
all_features = []
all_annotations = []
for split in SPLITS:
for label, class_tags in classes.items():
videos_dir = directories.get_videos_dir(path, split, label)
frames_dir = directories.get_frames_dir(path, split, label)
features_dir = directories.get_features_dir(path,
split,
model_config,
label=label)
tags_dir = directories.get_tags_dir(path, split, label)
if not os.path.exists(tags_dir):
continue
# Compute the respective frames and features
compute_frames_and_features(inference_engine=inference_engine,
project_path=path,
videos_dir=videos_dir,
frames_dir=frames_dir,
features_dir=features_dir)
video_tag_files = os.listdir(tags_dir)
for video_tag_file in video_tag_files:
feature_file = os.path.join(
features_dir, video_tag_file.replace('.json', '.npy'))
annotation_file = os.path.join(tags_dir, video_tag_file)
features = np.load(feature_file)
for f in features:
all_features.append(f.mean(axis=(1, 2)))
with open(annotation_file, 'r') as f:
annotations = json.load(f)['time_annotation']
# Reset tags that have been removed from the class to 'background'
annotations = [
tag_idx if tag_idx in class_tags else 0
for tag_idx in annotations
]
all_annotations.extend(annotations)
# Use low class weight for background and higher weight for all present tags
annotated_tags = set(all_annotations)
class_weight = {tag: 2 for tag in annotated_tags}
class_weight[0] = 0.5
all_features = np.array(all_features)
all_annotations = np.array(all_annotations)
if len(annotated_tags) > 1:
os.makedirs(logreg_dir, exist_ok=True)
logreg = LogisticRegression(C=0.1, class_weight=class_weight)
logreg.fit(all_features, all_annotations)
dump(logreg, logreg_path)
