{ "cells": [ { "cell_type": "markdown", "metadata": { "_cell_guid": "ab74bdce-9ca9-6fd3-b24f-185a67100dd5" }, "source": [ "using keras for remote sensing\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ea88b6f7-a32f-6dd0-31da-9969162aa739" }, "outputs": [], "source": [ "from collections import defaultdict\n", "import csv\n", "import sys\n", "\n", "import cv2\n", "from shapely.geometry import MultiPolygon, Polygon\n", "import shapely.wkt\n", "import shapely.affinity\n", "import numpy as np\n", "import tifffile as tiff\n", "\n", "csv.field_size_limit(sys.maxsize);" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "0703109c-c1c1-9ceb-77f4-3ce3dc77c3cc" }, "outputs": [], "source": [ "IM_ID = '6120_2_2'\n", "POLY_TYPE = '1' # buildings\n", "\n", "# Load grid size\n", "x_max = y_min = None\n", "for _im_id, _x, _y in csv.reader(open('../input/grid_sizes.csv')):\n", " if _im_id == IM_ID:\n", " x_max, y_min = float(_x), float(_y)\n", " break\n", "\n", "# Load train poly with shapely\n", "train_polygons = dict()\n", "for _im_id, _poly_type, _poly in csv.reader(open('../input/train_wkt_v4.csv')):\n", " if _im_id == IM_ID:\n", " train_polygons[_poly_type]=shapely.wkt.loads(_poly)\n", " break\n", "\n", "# Read image with tiff\n", "im_rgb = tiff.imread('../input/three_band/{}.tif'.format(IM_ID)).transpose([1, 2, 0])\n", "im_size = im_rgb.shape[:2]\n", "\n", "def get_scalers():\n", " h, w = im_size # they are flipped so that mask_for_polygons works correctly\n", " w_ = w * (w / (w + 1))\n", " h_ = h * (h / (h + 1))\n", " return w_ / x_max, h_ / y_min\n", "\n", "def mask_for_polygons(polygons):\n", " img_mask = np.zeros(im_size, np.uint8)\n", " if not polygons:\n", " return img_mask\n", " int_coords = lambda x: np.array(x).round().astype(np.int32)\n", " exteriors = [int_coords(poly.exterior.coords) for poly in polygons]\n", " interiors = [int_coords(pi.coords) for poly in polygons\n", " for pi in poly.interiors]\n", " cv2.fillPoly(img_mask, exteriors, 1)\n", " cv2.fillPoly(img_mask, interiors, 0)\n", " return img_mask\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a3f92f64-834d-6528-2f89-d2626ef42615" }, "outputs": [], "source": [ "mask_map = list()\n", "for key in train_polygons.keys():\n", " x_scaler, y_scaler = get_scalers()\n", " train_polygons_scaled = shapely.affinity.scale(train_polygons[key], xfact=x_scaler, yfact=y_scaler, origin=(0, 0, 0))\n", " mask_map.append( mask_for_polygons(train_polygons_scaled) )\n", " \n", "mask = np.dstack(mask_map)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "9e4add19-6c27-ce5d-a324-77e296059413" }, "outputs": [], "source": [ "nrow, ncol = im_size\n", "x = np.arange(0, nrow, 16)\n", "y = np.arange(0, ncol, 16)\n", "\n", "patch_list = list()\n", "lbl_list = list()\n", "for xstart, xend in zip(x[:-1], x[1:]):\n", " for ystart, yend in zip(y[:-1], y[1:]):\n", " patch_list.append(im_rgb[xstart:xend, ystart:yend,:])\n", " lbl_list.append(mask[xstart:xend, ystart:yend].mean())\n", "patches = np.array(patch_list)\n", "lbls = np.array(lbl_list)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "da9f4604-fa4c-6dfe-a117-6fcc823470b9" }, "outputs": [], "source": [ "from sklearn.cross_validation import train_test_split\n", "\n", "xtrain, xtest, ytrain, ytest = train_test_split(patches, lbls,\n", " train_size=0.8,\n", " test_size=0.2)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b1463997-274e-eb86-7c8c-eb7f752a860d" }, "outputs": [], "source": [ "from keras.layers import Convolution2D, MaxPooling2D, Flatten, Dense\n", "from keras.layers.normalization import BatchNormalization\n", "from keras.layers import Activation\n", "from keras.models import Sequential\n", "\n", "model = Sequential()\n", "model.add(Convolution2D(64, 1, 1, border_mode='same', input_shape=(16, 16, 3), dim_ordering=\"tf\"))\n", "model.add(BatchNormalization(mode=0))\n", "model.add(Activation(\"relu\"))\n", "model.add(MaxPooling2D((2,2), dim_ordering=\"tf\"))\n", "model.add(Convolution2D(64, 1, 1, border_mode='same', dim_ordering=\"tf\"))\n", "model.add(BatchNormalization(mode=0))\n", "model.add(Activation(\"relu\"))\n", "model.add(Convolution2D(128, 3, 3, border_mode='same', dim_ordering=\"tf\"))\n", "model.add(BatchNormalization(mode=0))\n", "model.add(Activation(\"relu\"))\n", "model.add(MaxPooling2D((2,2), dim_ordering=\"tf\"))\n", "model.add(Flatten())\n", "model.add(Dense(1))\n", "\n", "model.compile(loss='mean_squared_error', optimizer='adam')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "37f93611-0793-ad61-2079-8552a199e509" }, "outputs": [], "source": [ "%time model.fit(xtrain.values, ytrain.values, batch_size=32, nb_epoch=10, verbose=False)\n", "\n", "model.evaluate(xtrain.values, ytrain.values, batch_size=32, verbose=False), model.evaluate(X_test.values, Y_test.values, batch_size=32, verbose=False)" ] } ], "metadata": { "_change_revision": 0, "_is_fork": false, "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": "3.5.2" } }, "nbformat": 4, "nbformat_minor": 0 }