This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
@dkurt, Thanks for fast response. I was using tf.nn.dropout and now I see... tf.nn.dropout is not adding information about is_training thus freezing is not removing it and it slips through to deployed model. So when I do graph_freeze -> optimize_for_inference -> (if necessary graph_transform) it is working now. Thanks! You are doing great job.
| | 2 | No.2 Revision |
@dkurt, Thanks for fast response. I was using tf.nn.dropout and now I see... tf.nn.dropout is not adding information about is_training thus freezing is not removing it and it slips through to deployed model. So when I've changed it to tf.layers.dropout and than I do graph_freeze -> optimize_for_inference -> (if necessary graph_transform) it is working now. Thanks! You are doing great job.
| | 3 | No.3 Revision |
@dkurt, Thanks for fast response. I was using tf.nn.dropout and now I see... tf.nn.dropout is not adding information about is_training thus freezing is not removing it and it slips through to deployed model. So when I've changed it to tf.layers.dropout and than then I do graph_freeze -> optimize_for_inference -> (if necessary graph_transform) it is working now. Thanks! You are doing a great job.
