Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

modify lstm ouput for aggregated model #45

Merged
merged 2 commits into from Apr 15, 2017
Merged

modify lstm ouput for aggregated model #45

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5951a84
lstm ouput to aggregated
rickymf4 Apr 7, 2017
21cc44e
modify lstm ouput for aggregated model
rickymf4 Apr 14, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
6 changes: 3 additions & 3 deletions frame_level_models.py
View file
Open in desktop
Expand Up @@ -218,9 +218,9 @@ def create_model(self, model_input, vocab_size, num_frames, **unused_params):
stacked_lstm = tf.contrib.rnn.MultiRNNCell(
[
tf.contrib.rnn.BasicLSTMCell(
lstm_size, forget_bias=1.0, state_is_tuple=False)
lstm_size, forget_bias=1.0)
for _ in range(number_of_layers)
], state_is_tuple=False)
])

loss = 0.0
with tf.variable_scope("RNN"):
Expand All @@ -231,6 +231,6 @@ def create_model(self, model_input, vocab_size, num_frames, **unused_params):
aggregated_model = getattr(video_level_models,
FLAGS.video_level_classifier_model)
return aggregated_model().create_model(
model_input=state,
model_input=state[-1].h,
vocab_size=vocab_size,
**unused_params)