Skip to content

Instantly share code, notes, and snippets.

@ljcucc

ljcucc/isr-machine.ipynb

Last active March 21, 2022 12:15
Show Gist options
  • Save ljcucc/8a338ccf7f2d48147aacb1b176144ca9 to your computer and use it in GitHub Desktop.
Save ljcucc/8a338ccf7f2d48147aacb1b176144ca9 to your computer and use it in GitHub Desktop.
Download ZIP
ISR Machine.ipynb
Display the source blob
Display the rendered blob
Raw
isr-machine.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"accelerator": "TPU",
"colab": {
"name": "ISR Machine.ipynb",
"provenance": [],
"collapsed_sections": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/ljcucc/8a338ccf7f2d48147aacb1b176144ca9/isr-machine.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "QJ4sSTzDWAao"
},
"source": [
"# ISR Machine - A image upscaling notebook with no code.\n",
"\n",
"This noteobook will help you to upscaling your image by using the magic from ISR team which was a german ML team ( https://github.com/idealo/image-super-resolution ).\n",
"\n",
"ITWolf ([Twitter](https://twitter.com/the_itwolf), [Github](https://github.com/ljcucc) ) is the authro of this noteobook, If you like it, consider to share this notebook.\n",
"\n",
"## How to use it?\n",
"\n",
"1. Enter your Image URL under [Configuration] section \n",
"2. After that, click [Connect] to connect to remote VM at Google Compute Engine.\n",
"3. Click option from top menu bar：`[Runtime] > [Run all]` .\n",
" * If you want to batch process image, try using \"How to use (batch)\"\n",
"4. Click auto download to dowanload after finished or click [Download] button to download your image.\n",
"\n",
"## How to use it? (batch)\n",
"\n",
"1. After that, click [Connect] to connect to remote VM at Google Compute Engine.\n",
"2. Click \"Init program\" to init environment.\n",
"3. Click \"GPU, TPU settings\"\n",
"4. Enter your Image URL under [Configuration] section. (The config will auto apply)\n",
"\n",
"Total takes 2min (Init environment, run once) + (8s~2min)，depends waht model and how much size of your image."
]
},
{
"cell_type": "code",
"metadata": {
"id": "KCd2ZuS4V6Z0"
},
"source": [
"%%capture\n",
"#@title Init program\n",
"#@markdown (Ignore me, but I'm taking a while, about <2min )\n",
"!pip install ISR\n",
"!pip install 'h5py<3.0.0'\n",
"!pip install tensorflow==2.4.1\n",
"!pip install keras==2.4.3"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "TPDLdnKedj6R",
"cellView": "form"
},
"source": [
"%%capture\n",
"#@title Configuration { run: \"auto\" }\n",
"\n",
"#@markdown Step by step to get started\n",
"#@markdown \n",
"#@markdown ---\n",
"\n",
"#@markdown #### 1. Your image URL\n",
"image_url = \"https://d.furaffinity.net/art/ludo/1455487019/1455487019.ludo_zeba_ghost.png\" #@param {type:\"string\"}\n",
"\n",
"#@markdown #### 2. Type of your image\n",
"#@markdown png or jpg. If you choose jpg, program will auto noise-cancel.\n",
"image_type = \"jpg\" #@param [\"png\",\"jpg\"]\n",
"\n",
"#@markdown #### 3. Choose want kind of model you want to use\n",
"#@markdown * **gans**: Max upscaling model, but noise or image will looks sharper.\n",
"#@markdown * **psnr-smal** For small images, fastest model, try it to check it's fit or not.\n",
"#@markdown * **psnr-large** For larger images, execution time will slower, try it to check it's fit or not.\n",
"#@markdown * **noise-cancel**： just, noise canceling.\n",
"\n",
"upscaling_model = \"psnr-small\" #@param [\"gans\", \"psnr-small\", \"psnr-large\", \"noise-cancel\"]\n",
"\n",
"#@markdown Do you need to auto downlaod after finished? (check that checkbox to ensure)\n",
"\n",
"download_after_finishing = False #@param {type:\"boolean\"}\n",
"\n",
"#@markdown #### 4. Then click **Runtime** > **Run all** to Start\n",
"\n",
"#@markdown ---\n",
"\n",
"#@markdown #### Optional\n",
"#@markdown Noise cancel after upscaling (this may take a while to do it):\n",
"\n",
"noise_canceling_after_predict = False #@param {type: \"boolean\"}\n",
"\n",
"#@markdown Show image after finished: \n",
"show_on_finished = True #@param {type: \"boolean\"}\n",
"\n",
"\n",
"#@markdown Choose the runtime you use (TPU is default option)\n",
"#@markdown e.g. CPU may takes >15min，GPU takes 5～6min，TPU only takes 1min～1min and half.\n",
"\n",
"runtime_type = \"TPU\" #@param [\"CPU\",\"GPU\",\"TPU\"]"
],
"execution_count": 6,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "VAaFLLiKXJST",
"cellView": "form"
},
"source": [
"#@title GPU、TPU Settings\n",
"#@markdown Ignore this, unless you want to config GPU or TPU.\n",
"%%capture\n",
"%tensorflow_version 2.x\n",
"import tensorflow as tf\n",
"print(\"Tensorflow version \" + tf.__version__)\n",
"\n",
"# tf.config.optimizer.set_jit(True)\n",
"\n",
"if runtime_type == \"TPU\":\n",
" try:\n",
" tpu = tf.distribute.cluster_resolver.TPUClusterResolver() # TPU detection\n",
" print('Running on TPU ', tpu.cluster_spec().as_dict()['worker'])\n",
" except ValueError:\n",
" raise BaseException('ERROR: Not connected to a TPU runtime; please see the previous cell in this notebook for instructions!')\n",
"\n",
" tf.config.experimental_connect_to_cluster(tpu)\n",
" tf.tpu.experimental.initialize_tpu_system(tpu)\n",
" tpu_strategy = tf.distribute.experimental.TPUStrategy(tpu)\n",
"elif runtime_type == \"GPU\" : \n",
" device_name = tf.test.gpu_device_name()\n",
" if device_name != '/device:GPU:0':\n",
" raise SystemError('GPU device not found')\n",
" print('Found GPU at: {}'.format(device_name))\n",
" # tf.debugging.set_log_device_placement(True)"
],
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "hCZfkvojYwbY",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 443
},
"cellView": "form",
"outputId": "27b5dcd3-3ee7-479c-8a0e-6657ab236487"
},
"source": [
"# %%capture\n",
"#@title Main Progra\n",
"#@markdown Dont open this, unless you understand what inside.\n",
"\n",
"# !wget {image_url}\n",
"!mv *.{image_type} test.png\n",
"!mkdir -p data/input/test_images\n",
"!mv test.png data/input/test_images\n",
"\n",
"import numpy as np\n",
"from PIL import Image\n",
"\n",
"img = Image.open(f'data/input/test_images/test.png')\n",
"\n",
"from ISR.models import RDN, RRDN\n",
"import tensorflow\n",
"\n",
"\n",
"img = img.convert(\"RGB\")\n",
"lr_img = np.array(img)\n",
"\n",
"print(f\"feeding {lr_img.shape} image into noise canceling\")\n",
"\n",
"if image_type == \"jpg\":\n",
" noise_cancel__model = RDN(weights='noise-cancel')\n",
" lr_img = noise_cancel__model.predict(lr_img)\n",
" del noise_cancel__model\n",
"\n",
"print(f\"feeding {lr_img.shape} image into predict mode\")\n",
"\n",
"model = None\n",
"if upscaling_model == \"gans\":\n",
" model = RRDN(weights=upscaling_model)\n",
"else:\n",
" model = RDN(weights=upscaling_model)\n",
"\n",
"sr_img = model.predict(lr_img)\n",
"del model\n",
"\n",
"print(f\"feeding {sr_img.shape} image into noise canceling\")\n",
"\n",
"if noise_canceling_after_predict:\n",
" noise_cancel__model = RDN(weights='noise-cancel')\n",
" sr_img = noise_cancel__model.predict(sr_img)\n",
" del noise_cancel__model\n",
"\n",
"image = Image.fromarray(sr_img)\n",
"image.save(f\"./result.png\")"
],
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"mv: cannot stat '*.jpg': No such file or directory\n",
"mv: cannot stat 'test.png': No such file or directory\n"
]
},
{
"output_type": "error",
"ename": "SymbolAlreadyExposedError",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mSymbolAlreadyExposedError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-10-ba76a0fb511b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mImage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf'data/input/test_images/test.png'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mISR\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodels\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mRDN\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mRRDN\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 16\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 17\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/ISR/models/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0mcut_vgg19\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mCut_VGG19\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0mdiscriminator\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mDiscriminator\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0mrdn\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mRDN\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0mrrdn\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mRRDN\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/ISR/models/cut_vgg19.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodels\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mModel\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapplications\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvgg19\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mVGG19\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mISR\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlogger\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mget_logger\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/keras/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 17\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 18\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mconstraints\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 19\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mdatasets\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 20\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mestimator\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 21\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mexperimental\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/keras/datasets/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mcifar100\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mfashion_mnist\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mimdb\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 15\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmnist\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 16\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mreuters\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/keras/datasets/imdb/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msys\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0m_sys\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 11\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdatasets\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimdb\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mget_word_index\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 12\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdatasets\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimdb\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mload_data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/datasets/imdb.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 23\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 25\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpreprocessing\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msequence\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0m_remove_long_seq\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 26\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata_utils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mget_file\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplatform\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtf_logging\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mlogging\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/preprocessing/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 25\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mbackend\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 26\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpreprocessing\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mimage\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 27\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpreprocessing\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msequence\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 28\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpreprocessing\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/preprocessing/image.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1101\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1102\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1103\u001b[0;31m \u001b[0mkeras_export\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'keras.preprocessing.image.random_rotation'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrandom_rotation\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1104\u001b[0m \u001b[0mkeras_export\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'keras.preprocessing.image.random_shift'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrandom_shift\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1105\u001b[0m \u001b[0mkeras_export\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'keras.preprocessing.image.random_shear'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrandom_shear\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/tf_export.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, func)\u001b[0m\n\u001b[1;32m 334\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mf\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_overrides\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 335\u001b[0m \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mundecorated_f\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_decorator\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munwrap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 336\u001b[0;31m \u001b[0mdelattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mundecorated_f\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mapi_names_attr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 337\u001b[0m \u001b[0mdelattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mundecorated_f\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mapi_names_attr_v1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 338\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/tf_export.py\u001b[0m in \u001b[0;36mset_attr\u001b[0;34m(self, func, api_names_attr, names)\u001b[0m\n\u001b[1;32m 351\u001b[0m \u001b[0;31m# __dict__ instead of using hasattr to verify that subclasses have\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 352\u001b[0m \u001b[0;31m# their own _tf_api_names as opposed to just inheriting it.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 353\u001b[0;31m \u001b[0;32mif\u001b[0m \u001b[0mapi_names_attr\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__dict__\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 354\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_allow_multiple_exports\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 355\u001b[0m raise SymbolAlreadyExposedError(\n",
"\u001b[0;31mSymbolAlreadyExposedError\u001b[0m: Symbol random_rotation is already exposed as ('keras.preprocessing.image.random_rotation',)."
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "Sv3w2GHRhZLy",
"cellView": "form"
},
"source": [
"#@title Download\n",
"#@markdown Click that [Download] button after [Run all]\n",
"\n",
"from google.colab import files\n",
"import ipywidgets as widgets\n",
"\n",
"def download(_):\n",
" files.download(\"./result.png\")\n",
"\n",
"button = widgets.Button(\n",
" description='Download',\n",
" disabled=False,\n",
" button_style='success', # 'success', 'info', 'warning', 'danger' or ''\n",
" tooltip='Click me',\n",
" icon='check' # (FontAwesome names without the `fa-` prefix)\n",
")\n",
"button.on_click(download)\n",
"\n",
"if download_after_finishing:\n",
" files.download(\"./result.png\")\n",
"\n",
"button"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "twLMFj5l3shG",
"cellView": "form"
},
"source": [
"#@title Display final result { vertical-output: true }\n",
"#@markdown (If you're checked that `show_on_finished` checkbox)\n",
"\n",
"if not show_on_finished:\n",
" exit()\n",
"\n",
"Image.open(\"result.png\")"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "nfCVBuQNdC47"
},
"source": [
"Credit: [![Google Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/idealo/image-super-resolution/blob/master/notebooks/ISR_Prediction_Tutorial.ipynb)"
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment