{ "cells": [ { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(11022, 200, 200, 1)\n" ] } ], "source": [ "# author: stefan.kowarik@uni-graz.at\n", "# The following example loads the KMC dataset, potentially augments it with noise and rotations / shifts and plots the data\n", "\n", "import numpy as np\n", "import pickle\n", "from matplotlib import pyplot as plt\n", "\n", "# image dimensions\n", "L = 200 # pixels\n", "\n", "# load data from drive x_train: images, y_train: labels EB and ED\n", "with open(\"./train_dat.txt\",\"rb\") as f:\n", " x_train, y_train = pickle.load(f)\n", " \n", "#similarly valid_dat.txt can be loaded and processed\n", " \n", "# Data preprocessing:\n", "# Adding Salt and Pepper noise:\n", "#probability of noise level for salt and pepper pixel replacement; 0 = no noise; 1 = only noise;\n", "prob = 0.04\n", "\n", "#gb: should be one-channel image with pixels in [0, 1] range\n", "def add_salt_and_pepper(gb, prob):\n", " rnd = np.random.rand(gb.shape[0], gb.shape[1])\n", " noisy = gb.copy()\n", " noisy[rnd < prob] = 0\n", " noisy[rnd > 1 - prob] = 1\n", " return noisy\n", "\n", "\n", "config_x_train = []\n", "config_y_train = []\n", "\n", "# Adding image rotations and shifts for data augmentation\n", "for i, y in enumerate(y_train):\n", " for j in range(1): #range(4) for four 90 degree rotations for data augmentation\n", " lattice_rot = np.rot90(x_train[i],j)\n", " for k in range(1): ##e.g. range(10) for ten image shifts for data augmentation - as simulations have periodic boundary conditions shifting / rolling images up down or left-right is possible\n", " config_rot_shift = add_salt_and_pepper(np.roll(lattice_rot,k*27),prob)\n", " config_x_train.append(config_rot_shift)\n", " config_x_train.append(np.fliplr(config_rot_shift))\n", " config_x_train.append(np.flipud(config_rot_shift))\n", " config_y_train.extend([y,y,y])\n", " \n", "\n", "# training data\n", "y_train = np.asarray(config_y_train, dtype=np.float16)\n", "x_train = np.asarray(config_x_train)\n", "x_train = x_train.reshape(x_train.shape[0], L, L, 1)\n", "\n", "# printing dimesions: 11022 images with 200x200 pixels on one grayscale channel\n", "print(x_train.shape)\n", "\n", " " ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "energy values in eV for image number 1 :\n", "[E_Diffusion, E_Binding]\n", "[0.5127 0.3313]\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "###Plotting example image 1\n", "number = 1\n", "\n", "print(\"energy values in eV for image number\",number,\":\")\n", "print(\"[E_Diffusion, E_Binding]\")\n", "print(y_train[number])\n", "plt.imshow(np.array((x_train[number]))[:,:,0])\n" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "energy values in eV for image number 200 :\n", "[E_Diffusion, E_Binding]\n", "[0.425 0.175]\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "###Plotting example image 200\n", "number = 200\n", "\n", "print(\"energy values in eV for image number\",number,\":\")\n", "print(\"[E_Diffusion, E_Binding]\")\n", "print(y_train[number])\n", "plt.imshow(np.array((x_train[number]))[:,:,0])" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "accelerator": "GPU", "colab": { "collapsed_sections": [], "machine_shape": "hm", "name": "Untitled (1).ipynb", "provenance": [] }, "kernelspec": { "display_name": "Python 3", "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": "3.7.6" } }, "nbformat": 4, "nbformat_minor": 1 }