model_utils.py
3.44 KB
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
# Copyright 2016 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS-IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Contains a collection of util functions for model construction."""
import numpy
import tensorflow as tf
from tensorflow import logging
from tensorflow import flags
import tensorflow.contrib.slim as slim
def SampleRandomSequence(model_input, num_frames, num_samples):
"""Samples a random sequence of frames of size num_samples.
Args:
model_input: A tensor of size batch_size x max_frames x feature_size
num_frames: A tensor of size batch_size x 1
num_samples: A scalar
Returns:
`model_input`: A tensor of size batch_size x num_samples x feature_size
"""
batch_size = tf.shape(model_input)[0]
frame_index_offset = tf.tile(tf.expand_dims(tf.range(num_samples), 0),
[batch_size, 1])
max_start_frame_index = tf.maximum(num_frames - num_samples, 0)
start_frame_index = tf.cast(
tf.multiply(tf.random_uniform([batch_size, 1]),
tf.cast(max_start_frame_index + 1, tf.float32)), tf.int32)
frame_index = tf.minimum(start_frame_index + frame_index_offset,
tf.cast(num_frames - 1, tf.int32))
batch_index = tf.tile(tf.expand_dims(tf.range(batch_size), 1),
[1, num_samples])
index = tf.stack([batch_index, frame_index], 2)
return tf.gather_nd(model_input, index)
def SampleRandomFrames(model_input, num_frames, num_samples):
"""Samples a random set of frames of size num_samples.
Args:
model_input: A tensor of size batch_size x max_frames x feature_size
num_frames: A tensor of size batch_size x 1
num_samples: A scalar
Returns:
`model_input`: A tensor of size batch_size x num_samples x feature_size
"""
batch_size = tf.shape(model_input)[0]
frame_index = tf.cast(
tf.multiply(tf.random_uniform([batch_size, num_samples]),
tf.tile(tf.cast(num_frames, tf.float32), [1, num_samples])),
tf.int32)
batch_index = tf.tile(tf.expand_dims(tf.range(batch_size), 1),
[1, num_samples])
index = tf.stack([batch_index, frame_index], 2)
return tf.gather_nd(model_input, index)
def FramePooling(frames, method, **unused_params):
"""Pools over the frames of a video.
Args:
frames: A tensor with shape [batch_size, num_frames, feature_size].
method: "average", "max", "attention", or "none".
Returns:
A tensor with shape [batch_size, feature_size] for average, max, or
attention pooling. A tensor with shape [batch_size*num_frames, feature_size]
for none pooling.
Raises:
ValueError: if method is other than "average", "max", "attention", or
"none".
"""
if method == "average":
return tf.reduce_mean(frames, 1)
elif method == "max":
return tf.reduce_max(frames, 1)
elif method == "none":
feature_size = frames.shape_as_list()[2]
return tf.reshape(frames, [-1, feature_size])
else:
raise ValueError("Unrecognized pooling method: %s" % method)