{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1a138390-e848-401e-b286-ffeef5d8df83",
   "metadata": {},
   "source": [
    "# stackview in combination with Voila\n",
    "If you combine stackview with [voila](https://voila.readthedocs.io/en/stable/), you can build powerful, interactive, browser-based image processing apps and demonstrators. \n",
    "Just build a graphical user interface in a Jupyter notebook and then start it using\n",
    "```\n",
    "voila apoc_gui.ipynb\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f3c290cd-a8db-4f56-938f-28ec81c44c32",
   "metadata": {},
   "outputs": [],
   "source": [
    "from skimage.io import imread\n",
    "import numpy as np\n",
    "import stackview\n",
    "import ipywidgets as widgets\n",
    "from IPython.display import display, clear_output\n",
    "import apoc\n",
    "import pyclesperanto_prototype as cle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ff5f404a-ef5d-44e3-b9e6-eab55b0db872",
   "metadata": {},
   "outputs": [],
   "source": [
    "image = imread('data/blobs.tif')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e13631b7-5608-4c77-b3ef-ef3e36164cfb",
   "metadata": {},
   "outputs": [],
   "source": [
    "annotation = cle.push(np.zeros_like(image, dtype=np.uint32)).astype(np.uint32)\n",
    "labels = cle.push(np.zeros_like(image, dtype=np.uint16)).astype(np.uint32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a46b0d9f-1de1-4df1-aeaf-be1f7f33d97c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "411bcf6bd41c425a87fa1c94ae05b68b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(VBox(children=(VBox(children=(HBox(children=(HBox(children=(VBox(children=(ImageWidget(height=2…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Buttons\n",
    "train_button = widgets.Button(\n",
    "                                    description='Train', \n",
    "                                    button_style='success', \n",
    "                                    tooltip='Start machine learning training')\n",
    "train_button.layout.height = '500'\n",
    "\n",
    "def on_train_click(change):\n",
    "        model_filename = \"object_segmenter.cl\"\n",
    "        apoc.erase_classifier(model_filename)\n",
    "        model = apoc.ObjectSegmenter(model_filename)\n",
    "        model.train(apoc.PredefinedFeatureSet.small_quick.value, image=image, ground_truth=annotation)\n",
    "        new_labels = model.predict(image=image)\n",
    "        cle.copy(new_labels, labels)\n",
    "        slice_placeholder.update()\n",
    "\n",
    "train_button.on_click(on_train_click)\n",
    "\n",
    "reset_button = widgets.Button(\n",
    "                                    description='Reset', \n",
    "                                    button_style='danger', \n",
    "                                    tooltip='Reset annotation')\n",
    "\n",
    "def on_reset_click(change):\n",
    "    cle.set(annotation, 0)\n",
    "    cle.set(labels, 0)        \n",
    "    annotate_placeholder.update()\n",
    "    slice_placeholder.update()\n",
    "        \n",
    "reset_button.on_click(on_reset_click)\n",
    "\n",
    "# Image interaction\n",
    "annotate_placeholder = stackview.annotate(image, annotation)\n",
    "slice_placeholder = stackview.curtain(image, labels, alpha=0.7)\n",
    "\n",
    "# Initially display the annotate field\n",
    "display(widgets.HBox([\n",
    "    widgets.VBox([\n",
    "        annotate_placeholder, \n",
    "        widgets.HBox([\n",
    "            reset_button,\n",
    "            train_button])\n",
    "        ]),\n",
    "    slice_placeholder\n",
    "]))\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a890731e-638c-4c6b-b4f3-df42f055f48d",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}