diff options
Diffstat (limited to 'cli/app/search/search_class.py')
| -rw-r--r-- | cli/app/search/search_class.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/cli/app/search/search_class.py b/cli/app/search/search_class.py index 0fcfdfd..8825ca5 100644 --- a/cli/app/search/search_class.py +++ b/cli/app/search/search_class.py @@ -105,7 +105,7 @@ def find_nearest_vector(sess, generator, opt_fp_in, opt_dims, out_images, out_la clipped_latent = tf.where(tf.abs(input_z) >= opt_clip, tf.random.uniform([batch_size, z_dim], minval=-opt_clip, maxval=opt_clip), input_z) clipped_alpha = tf.compat.v1.placeholder(dtype=np.float32, shape=()) - clip_latent = tf.assign(input_z, clipped_latent * (1 - normalized_alpha) + input_z * normalized_alpha) + clip_latent = tf.assign(input_z, clipped_latent * (1 - clipped_alpha) + input_z * clipped_alpha) ## normalize the Y encoding # normalized_labels = tf.nn.l2_normalize(input_y) @@ -191,7 +191,7 @@ def find_nearest_vector(sess, generator, opt_fp_in, opt_dims, out_images, out_la print('iter: {}, loss: {}'.format(i, curr_loss)) if i > 0: if opt_stochastic_clipping and (i % opt_clip_interval) == 0 and i < opt_steps * 0.45: - sess.run(clip_latent, { normalized_alpha: i / opt_steps }) + sess.run(clip_latent, { clipped_alpha: i / opt_steps }) if opt_label_clipping and (i % opt_clip_interval) == 0: sess.run(clip_labels, { normalized_alpha: i / opt_steps }) if opt_video and opt_snapshot_interval != 0 and (i % opt_snapshot_interval) == 0: |