本文整理汇总了Python中model_utils.SampleRandomFrames方法的典型用法代码示例。如果您正苦于以下问题：Python model_utils.SampleRandomFrames方法的具体用法？Python model_utils.SampleRandomFrames怎么用？Python model_utils.SampleRandomFrames使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类model_utils的用法示例。
在下文中一共展示了model_utils.SampleRandomFrames方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: create_model
# 需要导入模块: import model_utils [as 别名]
# 或者: from model_utils import SampleRandomFrames [as 别名]
def create_model(self, model_input, vocab_size, num_frames, is_training=True, **unused_params):
"""Creates a model which uses a stack of LSTMs to represent the video.
Args:
model_input: A 'batch_size' x 'max_frames' x 'num_features' matrix of
input features.
vocab_size: The number of classes in the dataset.
num_frames: A vector of length 'batch' which indicates the number of
frames for each video (before padding).
Returns:
A dictionary with a tensor containing the probability predictions of the
model in the 'predictions' key. The dimensions of the tensor are
'batch_size' x 'num_classes'.
"""
lstm_size = FLAGS.lstm_cells
number_of_layers = FLAGS.lstm_layers
random_frames = FLAGS.lstm_random_sequence
iterations = FLAGS.iterations
backward = FLAGS.lstm_backward
if random_frames:
num_frames_2 = tf.cast(tf.expand_dims(num_frames, 1), tf.float32)
model_input = utils.SampleRandomFrames(model_input, num_frames_2,
iterations)
if backward:
model_input = tf.reverse_sequence(model_input, num_frames, seq_axis=1)
stacked_lstm = tf.contrib.rnn.MultiRNNCell(
[
tf.contrib.rnn.BasicLSTMCell(
lstm_size, forget_bias=1.0, state_is_tuple=False)
for _ in range(number_of_layers)
], state_is_tuple=False)
loss = 0.0
with tf.variable_scope("RNN"):
outputs, state = tf.nn.dynamic_rnn(stacked_lstm, model_input,
sequence_length=num_frames,
dtype=tf.float32)
aggregated_model = getattr(video_level_models,
FLAGS.video_level_classifier_model)
return aggregated_model().create_model(
model_input=state,
vocab_size=vocab_size,
is_training=is_training,
**unused_params)