args = parser.parse_args()
# Load model
if args.multi:
args.arch = 'multi_resnet3d50'
model = models.load_model(args.arch)
# Get dataset categories
if args.multi:
categories = models.load_categories('category_multi_momentsv2.txt')
else:
categories = models.load_categories('category_momentsv2.txt')
# Load the video frame transform
transform = models.load_transform()
# Obtain video frames
if args.frame_folder is not None:
print('Loading frames in {}'.format(args.frame_folder))
import glob
# here make sure after sorting the frame paths have the correct temporal order
frame_paths = sorted(glob.glob(os.path.join(args.frame_folder, '*.jpg')))
frames = load_frames(frame_paths)
else:
print('Extracting frames using ffmpeg...')
frames = extract_frames(args.video_file, args.num_segments)
# Prepare input tensor
if 'resnet3d50' in args.arch:
# [1, num_frames, 3, 224, 224]
def load_video(video_hash):
yt = YouTube('https://youtube.com/embed/%s?start=%d&end=%d' %
(video_hash, start, end))
video = yt.streams.all()[0]
name = video.download('/tmp')
# Load model
model = models.load_model(arch)
av_categories = pd.read_csv('CVS_Actions(NEW).csv',
delimiter=';').values.tolist()
trax = pd.read_csv('audioTracks_urls.csv')
# Get dataset categories
#categories = models.load_categories()
# Load the video frame transform
transform = models.load_transform()
# Obtain video frames
if frame_folder is not None:
print('Loading frames in {}'.format(frame_folder))
import glob
# here make sure after sorting the frame paths have the correct temporal order
frame_paths = sorted(glob.glob(os.path.join(frame_folder, '*.jpg')))
print(frame_paths)
frames = load_frames(frame_paths)
else:
print('Extracting frames using ffmpeg...')
frames = extract_frames(name, num_segments)
# Prepare input tensor
if arch == 'resnet3d50':
# [1, num_frames, 3, 224, 224]
input = torch.stack([transform(frame) for frame in frames],
1).unsqueeze(0)
else:
# [num_frames, 3, 224, 224]
input = torch.stack([transform(frame) for frame in frames])
# Make video prediction
with torch.no_grad():
logits = model(input)
h_x = F.softmax(logits, 1).mean(dim=0)
probs, idx = h_x.sort(0, True)
# Output the prediction.
print('RESULT ON ' + name)
y = float(av_categories[idx[0]][1]) * 125
x = float(av_categories[idx[0]][2]) * 125
trax = trax.assign(
dist=lambda row: np.sqrt((x - row.valence)**2 + (y - row.energy)**2))
print('min', trax['dist'].min())
best = trax.nsmallest(100, 'dist')
print(best)
rand = randint(0, 9)
print(rand)
choice = best.iloc[rand, [1, 2, 5]]
print('choice', choice)
song = 'valence: ' + str(x) + ' arousal: ' + str(
y) + " " + choice[0] + ' ' + choice[1]
print(song)
print(x, y)
for i in range(0, 5):
print('{:.3f} -> {} ->{}'.format(probs[i], idx[i],
av_categories[idx[i]]))
print('result cutegories', av_categories[idx[i]][0],
av_categories[idx[i]][1])
#r = requests.get(match.iloc[0,2], allow_redirects=True)
r = requests.get(choice[2], allow_redirects=True)
open('./tmp/preview.mp3', 'wb').write(r.content)
# Render output frames with prediction text.
rendered_output = './tmp/' + video_hash + '_' + str(x) + '_' + str(
y) + '.mp4'
if rendered_output is not None:
clip = VideoFileClip(name).subclip(30, 60)
audioclip = AudioFileClip('./tmp/preview.mp3')
txt_clip = TextClip(song, fontsize=16, color='white')
clip_final = clip.set_audio(audioclip)
video = CompositeVideoClip([clip_final, txt_clip])
video.set_duration(30).write_videofile(rendered_output)