def run_video_frame_classification(train_dir):
try:
neg_dir = train_dir + '/0'
pos_dir = train_dir + '/1'
while 1:
# Train using initial pos/neg
c = vidfeat.SyntheticFrameFeature().train(vidfeat.load_label_frames(train_dir))
# Predict on dataset
hdfs_input = random.sample(hadoopy.ls('/user/brandyn/aladdin/mp4_devt/'), 96)
start_time = '%f' % time.time()
hdfs_output = '/user/brandyn/aladdin_results/video_grep/%s' % start_time
picarus.vision.run_video_grep_frames(hdfs_input, hdfs_output, c)
unsorted_dir = tempfile.mkdtemp()
try:
for _, y in hadoopy.readtb(hdfs_output):
open('%s/%s.jpg' % (unsorted_dir, hashlib.sha1(y).hexdigest()), 'w').write(y)
# Present results to user and add to list
try:
cmd = 'python -m interactive_learning.image_selector %s %s %s --port 8083' % (unsorted_dir, pos_dir, neg_dir)
print(cmd)
subprocess.call(cmd.split())
except OSError:
pass
finally:
shutil.rmtree(unsorted_dir)
finally:
#shutil.rmtree(temp_root)
pass
def write_boxes():
for label, frame in vidfeat.load_label_frames('/aladdin_data_cropped/person/'):
if label == 1: # Some of the people have a tiling artifact on the bottom
frame = remove_tiling(frame)
boxes = sample_boxes(frame.shape[:2])
save_boxes('/aladdin_data_cropped/boxes/%d' % label, frame, boxes)
print(label)
def write_boxes():
for label, frame in vidfeat.load_label_frames(
'/aladdin_data_cropped/person/'):
if label == 1: # Some of the people have a tiling artifact on the bottom
frame = remove_tiling(frame)
boxes = sample_boxes(frame.shape[:2])
save_boxes('/aladdin_data_cropped/boxes/%d' % label, frame, boxes)
print(label)
import vidfeat
import imfeat
import sklearn.svm
class VisibleLensFrameFeature(vidfeat.ClassifierFrameFeature):
feature = imfeat.MetaFeature(imfeat.TinyImage())
def __init__(self, *args, **kw):
classifier = sklearn.svm.LinearSVC(class_weight='auto')
super(VisibleLensFrameFeature, self).__init__(classifier=classifier,
*args, **kw)
def _feature(self, image):
return self.feature(image)
if __name__ == '__main__':
data_root = '/home/brandyn/playground/visible_lens_data'
c = VisibleLensFrameFeature().train(vidfeat.load_label_frames(data_root))
vidfeat.save_to_py('models/visible_lens_frame_model0.py', classifier=c)
