-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathlipTest.py
166 lines (123 loc) · 6.07 KB
/
lipTest.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
def load_video(path:str) -> List[float]:
cap = cv2.VideoCapture(path)
frames = []
for _ in range(int(cap.get(cv2.CAP_PROP_FRAME_COUNT))):
ret, frame = cap.read()
frame = tf.image.rgb_to_grayscale(frame)
frames.append(frame[190:236,80:220,:])
cap.release()
mean = tf.math.reduce_mean(frames)
std = tf.math.reduce_std(tf.cast(frames, tf.float32))
return tf.cast((frames - mean), tf.float32) / std
vocab = [x for x in "abcdefghijklmnopqrstuvwxyz'?!123456789 "]
char_to_num = tf.keras.layers.StringLookup(vocabulary=vocab, oov_token="")
num_to_char = tf.keras.layers.StringLookup(
vocabulary=char_to_num.get_vocabulary(), oov_token="", invert=True
)
print(
f"The vocabulary is: {char_to_num.get_vocabulary()} "
f"(size ={char_to_num.vocabulary_size()})"
)
def load_alignments(path:str) -> tf.RaggedTensor:
with open(path, 'r') as f:
lines = f.readlines()
tokens = ""
for line in lines:
line = line.split()
if line[2] != 'sil':
tokens += " " + line[2]
tokens = tokens.strip()
return char_to_num(tf.strings.unicode_split(tokens, input_encoding='UTF-8'))
def load_data(path: str):
path = bytes.decode(path.numpy())
#file_name = path.split('/')[-1].split('.')[0]
# File name splitting for windows
file_name = path.split('\\')[-1].split('.')[0]
video_path = os.path.join('data','s1',f'{file_name}.mpg')
alignment_path = os.path.join('data','alignments','s1',f'{file_name}.align')
frames = load_video(video_path)
alignments = load_alignments(alignment_path)
return frames, alignments
def mappable_function(path:str) ->List[str]:
result = tf.py_function(load_data, [path], (tf.float32, tf.int64))
return result
data = tf.data.Dataset.list_files('./data/s1/*.mpg')
data = data.shuffle(500, reshuffle_each_iteration=False)
data = data.map(mappable_function)
data = data.padded_batch(2, padded_shapes=([75,None,None,None],[40]))
data = data.prefetch(tf.data.AUTOTUNE)
# Path: lipModel.pyfrom tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv3D, LSTM, Dense, Dropout, Bidirectional, MaxPool3D, Activation, Reshape, SpatialDropout3D, BatchNormalization, TimeDistributed, Flatten
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import ModelCheckpoint, LearningRateScheduler
model = Sequential()
model.add(Conv3D(128, 3, input_shape=(75,46,140,1), padding='same'))
model.add(Activation('relu'))
model.add(MaxPool3D((1,2,2)))
model.add(Conv3D(256, 3, padding='same'))
model.add(Activation('relu'))
model.add(MaxPool3D((1,2,2)))
model.add(Conv3D(75, 3, padding='same'))
model.add(Activation('relu'))
model.add(MaxPool3D((1,2,2)))
model.add(TimeDistributed(Flatten()))
model.add(Bidirectional(LSTM(128, kernel_initializer='Orthogonal', return_sequences=True)))
model.add(Dropout(.5))
model.add(Bidirectional(LSTM(128, kernel_initializer='Orthogonal', return_sequences=True)))
model.add(Dropout(.5))
model.add(Dense(char_to_num.vocabulary_size()+1, kernel_initializer='he_normal', activation='softmax'))
def scheduler(epoch, lr):
if epoch < 30:
return lr
else:
return lr * tf.math.exp(-0.1)
def CTCLoss(y_true, y_pred):
batch_len = tf.cast(tf.shape(y_true)[0], dtype="int64")
input_length = tf.cast(tf.shape(y_pred)[1], dtype="int64")
label_length = tf.cast(tf.shape(y_true)[1], dtype="int64")
input_length = input_length * tf.ones(shape=(batch_len, 1), dtype="int64")
label_length = label_length * tf.ones(shape=(batch_len, 1), dtype="int64")
loss = tf.keras.backend.ctc_batch_cost(y_true, y_pred, input_length, label_length)
return loss
class ProduceExample(tf.keras.callbacks.Callback):
def __init__(self, dataset) -> None:
self.dataset = dataset.as_numpy_iterator()
def on_epoch_end(self, epoch, logs=None) -> None:
data = self.dataset.next()
yhat = self.model.predict(data[0])
decoded = tf.keras.backend.ctc_decode(yhat, [75,75], greedy=False)[0][0].numpy()
for x in range(len(yhat)):
print('Original:', tf.strings.reduce_join(num_to_char(data[1][x])).numpy().decode('utf-8'))
print('Prediction:', tf.strings.reduce_join(num_to_char(decoded[x])).numpy().decode('utf-8'))
print('~'*100)
model.compile(optimizer=Adam(learning_rate=0.0001), loss=CTCLoss)
checkpoint_callback = ModelCheckpoint(os.path.join('models','checkpoint'), monitor='loss', save_weights_only=True)
schedule_callback = LearningRateScheduler(scheduler, verbose=1)
example_callback = ProduceExample(data)
train = data.take(450)
test = data.skip(450)
model.fit(train,validation_data=test, epochs=100, callbacks=[checkpoint_callback, schedule_callback, example_callback])
sample = load_data(tf.convert_to_tensor('.\\data\\s1\\bras9a.mpg'))
print('~'*100, 'REAL TEXT')
[tf.strings.reduce_join([num_to_char(word) for word in sentence]) for sentence in [sample[1]]]
yhat = model.predict(tf.expand_dims(sample[0], axis=0))
decoded = tf.keras.backend.ctc_decode(yhat, input_length=[75], greedy=True)[0][0].numpy()
print('~'*100, 'PREDICTIONS')
[tf.strings.reduce_join([num_to_char(word) for word in sentence]) for sentence in decoded]
def load_data(path: str):
path = bytes.decode(path.numpy())
speaker_num = path.split('/')[-3].split('speaker')[1]
file_name = path.split('/')[-1].split('.')[0]
video_path = os.path.join('data', f'speaker{speaker_num}', f's{speaker_num}', f'{file_name}.mpg')
alignment_path = os.path.join('data', f'speaker{speaker_num}', 'alignments', f'{file_name}.align')
frames = load_video(video_path)
alignments = load_alignments(alignment_path)
return frames, alignments
def mappable_function(path:str) ->List[str]:
result = tf.py_function(load_data, [path], (tf.float32, tf.int64))
return result
data = tf.data.Dataset.list_files('./data/speaker*/s*/[0-9]*.mpg')
data = data.shuffle(500, reshuffle_each_iteration=False)
data = data.map(mappable_function)
data = data.padded_batch(2, padded_shapes=([75,None,None,None],[40]))
data = data.prefetch(tf.data.AUTOTUNE)