INNER CODE UNIT · Python

batch_complete

zuruoke/watermark-removal · inpaint_model.py:163

        batch_complete = batch_predicted*mask + batch_incomplete*(1.-mask)
        # local patches
        losses['ae_loss'] = FLAGS.l1_loss_alpha * tf.reduce_mean(tf.abs(batch_pos - x1))
        losses['ae_loss'] += FLAGS.l1_loss_alpha * tf.reduce_mean(tf.abs(batch_pos - x2))
        if summary:
            scalar_summary('losses/ae_loss', losses['ae_loss'])
            if FLAGS.guided:
                viz_img = [
                    batch_pos,
                    batch_incomplete + edge,
                    batch_complete]
            else:
                viz_img = [batch_pos, batch_incomplete, batch_complete]
            if offset_flow is not None:
                viz_img.append(
                    resize(offset_flow, scale=4,
                           func=tf.image.resize_bilinear))
            images_summary(

View source record →