def generate_img(data):
x = (data
| mp.pshuffle
| mp.take(args.mix)
| mp.apply(['image','landmarks'],'face',transform)
| mp.select_field('face')
| mp.as_list)
return merge(x,np.random.random(len(x)))
def generate_img(data):
n = random.randint(3, 30)
x = (
data
| mp.pshuffle
| mp.take(n)
| mp.apply(
'filename', 'image',
lambda x: cv2.cvtColor(cv2.imread(os.path.splitext(x)[0] + '.jpg'),
cv2.COLOR_BGR2RGB))
| mp.apply(['image', 'descr'], 'face', transform)
#| mp.apply('face','facesmall',functools.partial(im_resize,size=(100,150)))
#| mp.select_field('facesmall')
| mp.select_field('face')
| mp.as_list)
return merge(x, np.random.random(len(x)))
from keras.layers import *
from keras.regularizers import l2
# Get list of test videos from matches.json
test_names = (from_json(os.path.join(source_dir, 'matches.json'))
| mp.where(lambda x: 'Test' in x.keys() and int(x['Test']) > 0)
| mp.apply(['Id', 'Half'], 'pattern',
lambda x: "{}_{}_".format(x[0], x[1]))
| mp.select_field('pattern')
| mp.as_list)
data = (mp.get_datastream(data_dir, ext=".resized.mp4")
| datasplit_by_pattern(test_pattern=test_names)
| stratify_sample_tt(shuffle=True)
| summary()
| mp.take(1000)
| mp.iter('filename', lambda x: print("Processing {}".format(x)))
| mp.apply(
'filename', 'aud',
lambda x: np.load(x.replace('.resized.mp4', '.audiofeatures.npy')))
| normalize_npy_value('aud', interval=(-1, 1))
| mp.as_list)
tr, te = data | mp.apply(
'aud', 'amean', lambda x: np.mean(x, axis=1)) | mp.make_train_test_split
def unzip(l):
t1, t2 = zip(*l)
return list(t1), list(t2)
def transform(args):
image, descr = args
tr = get_transform(descr)
return cv2.warpAffine(image, tr, (size, size))
@mp.Pipe
def savepics(seq, fn):
for i, im in enumerate(seq):
print(im)
cv2.imwrite(fn.format(i), im)
(data
| mp.pshuffle
| mp.take(15)
| mp.apply(
'filename', 'image', lambda x: cv2.cvtColor(
cv2.imread(os.path.splitext(x)[0] + '.jpg'), cv2.COLOR_BGR2RGB))
| mp.apply(['image', 'descr'], 'face', transform)
| mp.apply('face', 'facesmall', functools.partial(im_resize, size=(150, 150)))
| mp.apply(
'descr', 'ypr', lambda x: "Y={},P={},R={}".format(
x['faceAttributes']['headPose']['yaw'], x['faceAttributes'][
'headPose']['pitch'], x['faceAttributes']['headPose']['roll']))
| mp.select_field('facesmall')
| mp.pexec(functools.partial(show_images, cols=3)))
imgs = (
data
| mp.pshuffle
| mp.where(lambda x: 'Test' in x.keys() and int(x['Test']) > 0)
| mp.apply(['Id', 'Half'], 'pattern',
lambda x: "{}_{}_".format(x[0], x[1]))
| mp.select_field('pattern')
| mp.as_list)
no_frames = 126
data = (mp.get_datastream(data_dir, ext=".resized.mp4")
| mp.pshuffle
| datasplit_by_pattern(test_pattern=test_names)
| mp.apply('filename', 'vgg',
lambda x: np.load(x.replace('.resized.mp4', '.vgg.npy')))
| mp.apply('vgg', 'vggflat',
lambda x: np.reshape(x, (no_frames, -1, 1)))
| mp.take(500)
| mp.as_list)
trainstream, valstream = data | mp.make_train_test_split
no_train = data | mp.filter('split',
lambda x: x == mp.SplitType.Train) | mp.count
no_test = data | mp.filter('split',
lambda x: x == mp.SplitType.Test) | mp.count
print("Training samples = {}\nTesting samples = {}".format(no_train, no_test))
batchsize = 2
model = Sequential()
model.add(AveragePooling2D((10, 10), input_shape=(no_frames, 16384, 1)))
model.add(
Conv2D(8, (3, 3),