1. TiledTexture

TiledTexture

Creates a simple tiled texture based on a style using:
  1. Random plasma initialization
  2. Standard VGG16 layers
  3. Operators constraining and enhancing style
  4. Progressive resolution increase
  5. View layer to enforce tiling

Code from TiledTexture.scala:67 executed in 0.00 seconds (0.000 gc):

      implicit val _ = log
      // First, basic configuration so we publish to our s3 site
      log.setArchiveHome(URI.create(s"s3://$s3bucket/${getClass.getSimpleName.stripSuffix("$")}/${log.getId}/"))
      log.onComplete(() => upload(log): Unit)
      // Fetch image (user upload prompt) and display a rescaled copy
      log.p(log.jpg(load(log, styleUrl, (maxResolution * Math.sqrt(magnification)).toInt), "Input Style"))
      val canvas = new AtomicReference[Tensor](null)
  
      // Generates a pretiled image (e.g. 3x3) to display
      def tiledCanvas = {
        val input = canvas.get()
        if (null == input) input else {
          val layer = new ImgTileAssemblyLayer(rowsAndCols, rowsAndCols)
          val tensor = layer.eval((1 to (rowsAndCols * rowsAndCols)).map(_ => input): _*).getDataAndFree.getAndFree(0)
          layer.freeRef()
          tensor
        }
      }
  
      // Tiling layer used by the optimization engine.
      // Expands the canvas by a small amount, using tile wrap to draw in the expanded boundary.
      def tilingLayer(dims: Seq[Int]) = {
        val padding = Math.min(256, Math.max(16, dims(0) / 2))
        new ImgViewLayer(dims(0) + padding, dims(1) + padding, true)
          .setOffsetX(-padding / 2).setOffsetY(-padding / 2)
      }
  
      // Execute the main process while registered with the site index
      val registration = registerWithIndexJPG(tiledCanvas)
      try {
        // Display a pre-tiled image inside the report itself
        withMonitoredJpg(() => tiledCanvas.toImage) {
          // Display an additional, non-tiled image of the canvas
          withMonitoredJpg(() => Option(canvas.get()).map(_.toRgbImage).orNull) {
            log.subreport("Painting", (sub: NotebookOutput) => {
              paint(styleUrl, initUrl, canvas, new VisualStyleNetwork(
                styleLayers = List(
                  // We select all the lower-level layers to achieve a good balance between speed and accuracy.
                  VGG16.VGG16_0,
                  VGG16.VGG16_1a,
                  VGG16.VGG16_1b1,
                  VGG16.VGG16_1b2,
                  VGG16.VGG16_1c1,
                  VGG16.VGG16_1c2,
                  VGG16.VGG16_1c3
                ),
                styleModifiers = List(
                  // These two operators are a good combination for a vivid yet accurate style
                  new GramMatrixEnhancer(),
                  new MomentMatcher()
                ),
                styleUrl = List(styleUrl),
                magnification = magnification,
                viewLayer = tilingLayer
              ), new BasicOptimizer {
                override val trainingMinutes: Int = 60
                override val trainingIterations: Int = 15
                override val maxRate = 1e9
              }, new GeometricSequence {
                override val min: Double = minResolution
                override val max: Double = maxResolution
                override val steps = TiledTexture.this.steps
              }.toStream.map(_.round.toDouble): _*)(sub)
              null
            })
          }(log)
        }
        null
      } finally {
        registration.foreach(_.stop()(s3client, ec2client))
      }
    }

Returns:

    <function0>

Input Style

Subreport: Painting