Use soft device placement in the training session

a0de5ca9 · kaiix · dab1517e · a0de5ca9
Commit a0de5ca9 authored Aug 31, 2016 by kaiix
Hide whitespace changes
Inline Side-by-side

Showing with 2 additions and 1 deletion

textsum/seq2seq_attention.py textsum/seq2seq_attention.py +2 -1

No files found.
--- a/textsum/seq2seq_attention.py
+++ b/textsum/seq2seq_attention.py
@@ -94,7 +94,8 @@ def _Train(model, data_batcher):
                             save_summaries_secs=60,
                             save_model_secs=FLAGS.checkpoint_secs,
                             global_step=model.global_step)
-    sess = sv.prepare_or_wait_for_session()
+    sess = sv.prepare_or_wait_for_session(config=tf.ConfigProto(
+        allow_soft_placement=True))
    running_avg_loss = 0
    step = 0
    while not sv.should_stop() and step < FLAGS.max_run_steps: