diff options
| -rw-r--r-- | cli/app/search/search_class.py | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/cli/app/search/search_class.py b/cli/app/search/search_class.py index 105fc9f..3a56f68 100644 --- a/cli/app/search/search_class.py +++ b/cli/app/search/search_class.py @@ -110,7 +110,8 @@ def find_nearest_vector(sess, generator, opt_fp_in, opt_dims, out_images, out_la # normalized_labels = tf.nn.l2_normalize(input_y) # tf.reduce_mean(tf.abs(encoding - gen_encoding)) normalized_labels = input_y / tf.reduce_sum(input_y) - clip_labels = tf.assign(input_y, normalized_labels) + normalized_alpha = tf.compat.v1.placeholder(dtype=np.float32, shape=()) + clip_labels = tf.assign(input_y, normalized_labels * (1 - normalized_alpha) + input_y * normalized_alpha) ## if computing Feature loss, use these encoders if opt_use_feature_detector: @@ -189,9 +190,9 @@ 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: - sess.run(clip_latent) + sess.run(clip_latent, { normalized_alpha: i / opt_steps }) if opt_label_clipping and (i % opt_clip_interval) == 0: - sess.run(clip_labels) + sess.run(clip_labels, { normalized_alpha: i / opt_steps }) if opt_video and opt_snapshot_interval != 0 and (i % opt_snapshot_interval) == 0: phi_guess = sess.run(output) guess_im = imgrid(imconvert_uint8(phi_guess), cols=1) |