{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "bc448dc4-e853-4947-ab90-f7199223260a" }, "outputs": [], "source": [ "# -*- coding: utf-8 -*-\n", "\n", "import numpy as np\n", "\n", "import os\n", "import glob\n", "import cv2\n", "import math\n", "import pickle\n", "import datetime\n", "import pandas as pd\n", "\n", "from sklearn.cross_validation import train_test_split\n", "from sklearn.cross_validation import KFold\n", "from keras.models import Sequential\n", "from keras.layers.core import Dense, Dropout, Flatten\n", "from keras.layers.convolutional import Convolution2D, MaxPooling2D, \\\n", " ZeroPadding2D\n", "\n", "# from keras.layers.normalization import BatchNormalization\n", "# from keras.optimizers import Adam\n", "from keras.optimizers import SGD\n", "from keras.utils import np_utils\n", "from keras.models import model_from_json\n", "# from sklearn.metrics import log_loss\n", "from numpy.random import permutation\n", "\n", "\n", "np.random.seed(2016)\n", "use_cache = 1\n", "# color type: 1 - grey, 3 - rgb\n", "color_type_global = 3\n", "\n", "# color_type = 1 - gray\n", "# color_type = 3 - RGB\n", "\n", "\n", "def get_im(path, img_rows, img_cols, color_type=1):\n", " # Load as grayscale\n", " if color_type == 1:\n", " img = cv2.imread(path, 0)\n", " elif color_type == 3:\n", " img = cv2.imread(path)\n", " # Reduce size\n", " resized = cv2.resize(img, (img_cols, img_rows))\n", " # mean_pixel = [103.939, 116.799, 123.68]\n", " # resized = resized.astype(np.float32, copy=False)\n", "\n", " # for c in range(3):\n", " # resized[:, :, c] = resized[:, :, c] - mean_pixel[c]\n", " # resized = resized.transpose((2, 0, 1))\n", " # resized = np.expand_dims(img, axis=0)\n", " return resized\n", "\n", "\n", "def get_driver_data():\n", " dr = dict()\n", " path = os.path.join('..', 'input', 'driver_imgs_list.csv')\n", " print('Read drivers data')\n", " f = open(path, 'r')\n", " line = f.readline()\n", " while (1):\n", " line = f.readline()\n", " if line == '':\n", " break\n", " arr = line.strip().split(',')\n", " dr[arr[2]] = arr[0]\n", " f.close()\n", " return dr\n", "\n", "\n", "def load_train(img_rows, img_cols, color_type=1):\n", " X_train = []\n", " y_train = []\n", " driver_id = []\n", "\n", " driver_data = get_driver_data()\n", "\n", " print('Read train images')\n", " for j in range(10):\n", " print('Load folder c{}'.format(j))\n", " path = os.path.join('..', 'input', 'imgs', 'train',\n", " 'c' + str(j), '*.jpg')\n", " files = glob.glob(path)\n", " for fl in files:\n", " flbase = os.path.basename(fl)\n", " img = get_im(fl, img_rows, img_cols, color_type)\n", " X_train.append(img)\n", " y_train.append(j)\n", " driver_id.append(driver_data[flbase])\n", "\n", " unique_drivers = sorted(list(set(driver_id)))\n", " print('Unique drivers: {}'.format(len(unique_drivers)))\n", " print(unique_drivers)\n", " return X_train, y_train, driver_id, unique_drivers\n", "\n", "\n", "def load_test(img_rows, img_cols, color_type=1):\n", " print('Read test images')\n", " path = os.path.join('..', 'input', 'imgs', 'test', '*.jpg')\n", " files = glob.glob(path)\n", " X_test = []\n", " X_test_id = []\n", " total = 0\n", " thr = math.floor(len(files)/10)\n", " for fl in files:\n", " flbase = os.path.basename(fl)\n", " img = get_im(fl, img_rows, img_cols, color_type)\n", " X_test.append(img)\n", " X_test_id.append(flbase)\n", " total += 1\n", " if total % thr == 0:\n", " print('Read {} images from {}'.format(total, len(files)))\n", "\n", " return X_test, X_test_id\n", "\n", "\n", "def cache_data(data, path):\n", " if not os.path.isdir('cache'):\n", " os.mkdir('cache')\n", " if os.path.isdir(os.path.dirname(path)):\n", " file = open(path, 'wb')\n", " pickle.dump(data, file)\n", " file.close()\n", " else:\n", " print('Directory doesnt exists')\n", "\n", "\n", "def restore_data(path):\n", " data = dict()\n", " if os.path.isfile(path):\n", " print('Restore data from pickle........')\n", " file = open(path, 'rb')\n", " data = pickle.load(file)\n", " return data\n", "\n", "\n", "def save_model(model, index, cross=''):\n", " json_string = model.to_json()\n", " if not os.path.isdir('cache'):\n", " os.mkdir('cache')\n", " json_name = 'architecture' + str(index) + cross + '.json'\n", " weight_name = 'model_weights' + str(index) + cross + '.h5'\n", " open(os.path.join('cache', json_name), 'w').write(json_string)\n", " model.save_weights(os.path.join('cache', weight_name), overwrite=True)\n", "\n", "\n", "def read_model(index, cross=''):\n", " json_name = 'architecture' + str(index) + cross + '.json'\n", " weight_name = 'model_weights' + str(index) + cross + '.h5'\n", " model = model_from_json(open(os.path.join('cache', json_name)).read())\n", " model.load_weights(os.path.join('cache', weight_name))\n", " return model\n", "\n", "\n", "def split_validation_set(train, target, test_size):\n", " random_state = 51\n", " X_train, X_test, y_train, y_test = \\\n", " train_test_split(train, target,\n", " test_size=test_size,\n", " random_state=random_state)\n", " return X_train, X_test, y_train, y_test\n", "\n", "\n", "def create_submission(predictions, test_id, info):\n", " result1 = pd.DataFrame(predictions, columns=['c0', 'c1', 'c2', 'c3',\n", " 'c4', 'c5', 'c6', 'c7',\n", " 'c8', 'c9'])\n", " result1.loc[:, 'img'] = pd.Series(test_id, index=result1.index)\n", " now = datetime.datetime.now()\n", " if not os.path.isdir('subm'):\n", " os.mkdir('subm')\n", " suffix = info + '_' + str(now.strftime(\"%Y-%m-%d-%H-%M\"))\n", " sub_file = os.path.join('subm', 'submission_' + suffix + '.csv')\n", " result1.to_csv(sub_file, index=False)\n", "\n", "\n", "def read_and_normalize_and_shuffle_train_data(img_rows, img_cols,\n", " color_type=1):\n", "\n", " cache_path = os.path.join('cache', 'train_r_' + str(img_rows) +\n", " '_c_' + str(img_cols) + '_t_' +\n", " str(color_type) + '.dat')\n", "\n", " if not os.path.isfile(cache_path) or use_cache == 0:\n", " train_data, train_target, driver_id, unique_drivers = \\\n", " load_train(img_rows, img_cols, color_type)\n", " cache_data((train_data, train_target, driver_id, unique_drivers),\n", " cache_path)\n", " else:\n", " print('Restore train from cache!')\n", " (train_data, train_target, driver_id, unique_drivers) = \\\n", " restore_data(cache_path)\n", "\n", " train_data = np.array(train_data, dtype=np.uint8)\n", " train_target = np.array(train_target, dtype=np.uint8)\n", "\n", " if color_type == 1:\n", " train_data = train_data.reshape(train_data.shape[0], color_type,\n", " img_rows, img_cols)\n", " else:\n", " train_data = train_data.transpose((0, 3, 1, 2))\n", "\n", " train_target = np_utils.to_categorical(train_target, 10)\n", " train_data = train_data.astype('float32')\n", " mean_pixel = [103.939, 116.779, 123.68]\n", " for c in range(3):\n", " train_data[:, c, :, :] = train_data[:, c, :, :] - mean_pixel[c]\n", " # train_data /= 255\n", " perm = permutation(len(train_target))\n", " train_data = train_data[perm]\n", " train_target = train_target[perm]\n", " print('Train shape:', train_data.shape)\n", " print(train_data.shape[0], 'train samples')\n", " return train_data, train_target, driver_id, unique_drivers\n", "\n", "\n", "def read_and_normalize_test_data(img_rows=224, img_cols=224, color_type=1):\n", " cache_path = os.path.join('cache', 'test_r_' + str(img_rows) +\n", " '_c_' + str(img_cols) + '_t_' +\n", " str(color_type) + '.dat')\n", " if not os.path.isfile(cache_path) or use_cache == 0:\n", " test_data, test_id = load_test(img_rows, img_cols, color_type)\n", " cache_data((test_data, test_id), cache_path)\n", " else:\n", " print('Restore test from cache!')\n", " (test_data, test_id) = restore_data(cache_path)\n", "\n", " test_data = np.array(test_data, dtype=np.uint8)\n", "\n", " if color_type == 1:\n", " test_data = test_data.reshape(test_data.shape[0], color_type,\n", " img_rows, img_cols)\n", " else:\n", " test_data = test_data.transpose((0, 3, 1, 2))\n", "\n", " test_data = test_data.astype('float32')\n", " mean_pixel = [103.939, 116.779, 123.68]\n", " for c in range(3):\n", " test_data[:, c, :, :] = test_data[:, c, :, :] - mean_pixel[c]\n", " # test_data /= 255\n", " print('Test shape:', test_data.shape)\n", " print(test_data.shape[0], 'test samples')\n", " return test_data, test_id\n", "\n", "\n", "def dict_to_list(d):\n", " ret = []\n", " for i in d.items():\n", " ret.append(i[1])\n", " return ret\n", "\n", "\n", "def merge_several_folds_mean(data, nfolds):\n", " a = np.array(data[0])\n", " for i in range(1, nfolds):\n", " a += np.array(data[i])\n", " a /= nfolds\n", " return a.tolist()\n", "\n", "\n", "def merge_several_folds_geom(data, nfolds):\n", " a = np.array(data[0])\n", " for i in range(1, nfolds):\n", " a *= np.array(data[i])\n", " a = np.power(a, 1/nfolds)\n", " return a.tolist()\n", "\n", "\n", "def copy_selected_drivers(train_data, train_target, driver_id, driver_list):\n", " data = []\n", " target = []\n", " index = []\n", " for i in range(len(driver_id)):\n", " if driver_id[i] in driver_list:\n", " data.append(train_data[i])\n", " target.append(train_target[i])\n", " index.append(i)\n", " data = np.array(data, dtype=np.float32)\n", " target = np.array(target, dtype=np.float32)\n", " index = np.array(index, dtype=np.uint32)\n", " return data, target, index\n", "\n", "\n", "def vgg_std16_model(img_rows, img_cols, color_type=1):\n", " model = Sequential()\n", " model.add(ZeroPadding2D((1, 1), input_shape=(color_type,\n", " img_rows, img_cols)))\n", " model.add(Convolution2D(64, 3, 3, activation='relu'))\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(64, 3, 3, activation='relu'))\n", " model.add(MaxPooling2D((2, 2), strides=(2, 2)))\n", "\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(128, 3, 3, activation='relu'))\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(128, 3, 3, activation='relu'))\n", " model.add(MaxPooling2D((2, 2), strides=(2, 2)))\n", "\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(256, 3, 3, activation='relu'))\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(256, 3, 3, activation='relu'))\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(256, 3, 3, activation='relu'))\n", " model.add(MaxPooling2D((2, 2), strides=(2, 2)))\n", "\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(512, 3, 3, activation='relu'))\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(512, 3, 3, activation='relu'))\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(512, 3, 3, activation='relu'))\n", " model.add(MaxPooling2D((2, 2), strides=(2, 2)))\n", "\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(512, 3, 3, activation='relu'))\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(512, 3, 3, activation='relu'))\n", " model.add(ZeroPadding2D((1, 1)))\n", " model.add(Convolution2D(512, 3, 3, activation='relu'))\n", " model.add(MaxPooling2D((2, 2), strides=(2, 2)))\n", "\n", " model.add(Flatten())\n", " model.add(Dense(4096, activation='relu'))\n", " model.add(Dropout(0.5))\n", " model.add(Dense(4096, activation='relu'))\n", " model.add(Dropout(0.5))\n", " model.add(Dense(1000, activation='softmax'))\n", "\n", " model.load_weights('../input/vgg16_weights.h5')\n", "\n", " # Code above loads pre-trained data and\n", " model.layers.pop()\n", " model.add(Dense(10, activation='softmax'))\n", " # Learning rate is changed to 0.001\n", " sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.9, nesterov=True)\n", " model.compile(optimizer=sgd, loss='categorical_crossentropy',metrics=['accuracy'])\n", " return model\n", "\n", "\n", "def run_cross_validation(nfolds=10, nb_epoch=10, split=0.2, modelStr=''):\n", "\n", " # Now it loads color image\n", " # input image dimensions\n", " img_rows, img_cols = 224, 224\n", " batch_size = 64\n", " random_state = 20\n", "\n", " train_data, train_target, driver_id, unique_drivers = \\\n", " read_and_normalize_and_shuffle_train_data(img_rows, img_cols,\n", " color_type_global)\n", "\n", " # ishuf_train_data = []\n", " # shuf_train_target = []\n", " # index_shuf = range(len(train_target))\n", " # shuffle(index_shuf)\n", " # for i in index_shuf:\n", " # shuf_train_data.append(train_data[i])\n", " # shuf_train_target.append(train_target[i])\n", "\n", " # yfull_train = dict()\n", " # yfull_test = []\n", " num_fold = 0\n", " kf = KFold(len(unique_drivers), n_folds=nfolds,\n", " shuffle=True, random_state=random_state)\n", " for train_drivers, test_drivers in kf:\n", " num_fold += 1\n", " print('Start KFold number {} from {}'.format(num_fold, nfolds))\n", " # print('Split train: ', len(X_train), len(Y_train))\n", " # print('Split valid: ', len(X_valid), len(Y_valid))\n", " # print('Train drivers: ', unique_list_train)\n", " # print('Test drivers: ', unique_list_valid)\n", " # model = create_model_v1(img_rows, img_cols, color_type_global)\n", " # model = vgg_bn_model(img_rows, img_cols, color_type_global)\n", " model = vgg_std16_model(img_rows, img_cols, color_type_global)\n", "\n", " model.fit(train_data, train_target, batch_size=batch_size,\n", " nb_epoch=nb_epoch,\n", " show_accuracy=True, verbose=1,\n", " validation_data=(X_valid, Y_valid), shuffle=True)\n", "\n", " # print('losses: ' + hist.history.losses[-1])\n", "\n", " # print('Score log_loss: ', score[0])\n", "\n", " save_model(model, num_fold, modelStr)\n", "\n", " # predictions_valid = model.predict(X_valid, batch_size=128, verbose=1)\n", " # score = log_loss(Y_valid, predictions_valid)\n", " # print('Score log_loss: ', score)\n", " # Store valid predictions\n", " # for i in range(len(test_index)):\n", " # yfull_train[test_index[i]] = predictions_valid[i]\n", "\n", " print('Start testing............')\n", " test_data, test_id = read_and_normalize_test_data(img_rows, img_cols,\n", " color_type_global)\n", " yfull_test = []\n", "\n", " for index in range(1, num_fold + 1):\n", " # 1,2,3,4,5\n", " # Store test predictions\n", " model = read_model(index, modelStr)\n", " test_prediction = model.predict(test_data, batch_size=128, verbose=1)\n", " yfull_test.append(test_prediction)\n", "\n", " info_string = 'loss_' + modelStr \\\n", " + '_r_' + str(img_rows) \\\n", " + '_c_' + str(img_cols) \\\n", " + '_folds_' + str(nfolds) \\\n", " + '_ep_' + str(nb_epoch)\n", "\n", " test_res = merge_several_folds_mean(yfull_test, nfolds)\n", " create_submission(test_res, test_id, info_string)\n", "\n", "\n", "def test_model_and_submit(start=1, end=1, modelStr=''):\n", " img_rows, img_cols = 224, 224\n", " # batch_size = 64\n", " # random_state = 51\n", " nb_epoch = 15\n", "\n", " print('Start testing............')\n", " test_data, test_id = read_and_normalize_test_data(img_rows, img_cols,\n", " color_type_global)\n", " yfull_test = []\n", "\n", " for index in range(start, end + 1):\n", " # Store test predictions\n", " model = read_model(index, modelStr)\n", " test_prediction = model.predict(test_data, batch_size=128, verbose=1)\n", " yfull_test.append(test_prediction)\n", "\n", " info_string = 'loss_' + modelStr \\\n", " + '_r_' + str(img_rows) \\\n", " + '_c_' + str(img_cols) \\\n", " + '_folds_' + str(end - start + 1) \\\n", " + '_ep_' + str(nb_epoch)\n", "\n", " test_res = merge_several_folds_mean(yfull_test, end - start + 1)\n", " create_submission(test_res, test_id, info_string)\n", "\n", "# nfolds, nb_epoch, split\n", "run_cross_validation(2, 20, 0.15, '_vgg_16_2x20')\n", "\n", "# nb_epoch, split\n", "# run_one_fold_cross_validation(10, 0.1)\n", "\n", "# test_model_and_submit(1, 10, 'high_epoch')\n" ] } ], "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 }