Datasets
Models
Downloads: 1
Diff of
/MultiscaleNet.ipynb
[000000]
..
[a8e9b4]
Switch to side-by-side view
--- a +++ b/MultiscaleNet.ipynb @@ -0,0 +1,809 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "%matplotlib inline\n", + "import pandas as pd\n", + "import numpy as np\n", + "from cdtw import pydtw\n", + "import seaborn as sns\n", + "from tqdm import tqdm\n", + "import os\n", + "import json\n", + "import h5py" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Using TensorFlow backend.\n" + ] + } + ], + "source": [ + "from keras import backend as K\n", + "from keras.regularizers import l2, activity_l2\n", + "\n", + "from keras import backend as K\n", + "from keras.engine.topology import Layer\n", + "from keras.optimizers import RMSprop, SGD, Adam\n", + "from keras.layers.core import Dense, Dropout, Activation, Flatten, Lambda, Merge\n", + "from keras.layers.recurrent import LSTM, GRU\n", + "from keras.models import Sequential, Model, load_model\n", + "from keras.layers import Input, Bidirectional, merge\n", + "from keras.layers.convolutional import Convolution1D, AtrousConvolution1D\n", + "from keras.layers.pooling import MaxPooling1D, AveragePooling1D, GlobalMaxPooling1D" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def read_train(fname):\n", + " subjects = {}\n", + " with h5py.File(fname, \"r\") as data_file:\n", + " for subject, subject_data in data_file.items():\n", + " print(subject)\n", + " X = subject_data[\"data\"][:]\n", + " y = subject_data[\"labels\"][:]\n", + " subjects[subject] = (X, y)\n", + " return subjects\n", + "\n", + "def read_test(fname):\n", + " subjects = {}\n", + " with h5py.File(fname, \"r\") as data_file:\n", + " X = {}\n", + " for subject, subject_data in data_file.items():\n", + " X[subject] = {}\n", + " for chunk_id, chunk in data_file[subject].items():\n", + " X[subject][chunk_id] = chunk[:]\n", + "\n", + " return X\n", + "\n", + "def batch(ts, y, n=1):\n", + " l = len(ts)\n", + " for ndx in range(0, l-n, 1):\n", + " yield (ts[ndx:min(ndx + n, l)], y[ndx:min(ndx + n, l)])\n", + "\n", + "def label_batch(batch):\n", + " if all([i == 1 for i in batch[1]]):\n", + " return 1\n", + " elif all([i == 0 for i in batch[1]]):\n", + " return 0\n", + " elif all([i == 2 for i in batch[1]]):\n", + " return 2\n", + " return -1\n", + " \n", + "def get_data():\n", + " train = read_train(\"train.h5\")\n", + " test = read_test(\"test.h5\")\n", + " \n", + "\n", + " subject_datas = {}\n", + " for subject, data in tqdm(train.items()):\n", + " subject_ts = data[0].T\n", + " subject_y = data[1][0]\n", + " batches = [i for i in batch(subject_ts, subject_y, n=1125)]\n", + " batches = [(i[0], label_batch(i)) for i in batches]\n", + " batches = [i for i in batches if i[1] != -1]\n", + " batches = [i for i in batches if len(i[0]) == 1125]\n", + " subject_datas[subject] = batches\n", + " \n", + " X = []\n", + " y = []\n", + " for subj, subj_data in tqdm(subject_datas.items()):\n", + " X.extend([i[0] for i in subj_data])\n", + " y.extend([i[1] for i in subj_data])\n", + " return X, y, test" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "subject_0\n", + "subject_1\n", + "subject_2\n", + "subject_3\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 4/4 [01:14<00:00, 19.86s/it]\n", + "100%|██████████| 4/4 [00:00<00:00, 145.58it/s]\n" + ] + } + ], + "source": [ + "X, y, test = get_data()" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "X = np.array(X)\n", + "y = np.array(y)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def shuffle_in_unison_scary(a, b):\n", + " rng_state = np.random.get_state()\n", + " np.random.shuffle(a)\n", + " np.random.set_state(rng_state)\n", + " np.random.shuffle(b)" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "shuffle_in_unison_scary(X, y)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "validation_start = len(X) - 30\n", + "X_train = X[:validation_start]\n", + "y_train = y[:validation_start]\n", + "X_val = X[validation_start:]\n", + "y_val = y[validation_start:]" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "from scipy.signal import resample\n", + "\n", + "\n", + "def toarr(label):\n", + " arr = np.zeros(3)\n", + " arr[label] = 1\n", + " return arr\n", + "\n", + "def data_generator(X, Y, batch_size):\n", + " while True:\n", + " inds = np.random.choice(len(X), batch_size)\n", + " x = X[inds]\n", + " y = Y[inds]\n", + " y = np.vstack([toarr(i) for i in y])\n", + " x_256 = np.array([resample(i, 256) for i in x])\n", + " x_500 = np.array([resample(i, 500) for i in x])\n", + " x = np.array([i for i in x])\n", + " yield ([x_256, x_500, x], y)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def multiscale(chunk):\n", + " resampled_256 = resample(chunk, 256)\n", + " resampled_500 = resample(chunk, 500)\n", + " return [resampled_256, resampled_500, chunk]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def get_base_model(input_len, fsize):\n", + " '''Base network to be shared (eq. to feature extraction).\n", + " '''\n", + " with K.tf.device('/gpu:1'):\n", + " input_seq = Input(shape=(input_len, 24))\n", + " nb_filters = 150\n", + " convolved = Convolution1D(nb_filters, fsize, border_mode=\"same\", activation=\"tanh\")(input_seq)\n", + " processed = GlobalMaxPooling1D()(convolved)\n", + " compressed = Dense(150, activation=\"tanh\")(processed)\n", + " compressed = Dropout(0.3)(compressed)\n", + " compressed = Dense(150, activation=\"tanh\")(compressed)\n", + " model = Model(input=input_seq, output=compressed) \n", + " return model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "with K.tf.device('/gpu:1'):\n", + " \n", + " input256_seq = Input(shape=(256, 24))\n", + " input500_seq = Input(shape=(500, 24))\n", + " input1125_seq = Input(shape=(1125, 24))\n", + " \n", + " base_network256 = get_base_model(256, 4)\n", + " base_network500 = get_base_model(500, 7)\n", + " base_network1125 = get_base_model(1125, 10)\n", + " \n", + " embedding_256 = base_network256(input256_seq)\n", + " embedding_500 = base_network500(input500_seq)\n", + " embedding_1125 = base_network256(input1125_seq)\n", + " \n", + " merged = merge([embedding_256, embedding_500, embedding_1125], mode=\"concat\")\n", + " out = Dense(3, activation='softmax')(merged)\n", + " \n", + " model = Model(input=[input256_seq, input500_seq, input1125_seq], output=out)\n", + " \n", + " #opt = SGD(lr=0.001, momentum=0.9, nesterov=True, clipvalue=0.0001)\n", + " opt = RMSprop(lr=0.005, clipvalue=10**6)\n", + " #opt = Adam(lr=0.001)\n", + " model.compile(loss=\"categorical_crossentropy\", optimizer=opt)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "with K.tf.device('/gpu:2'):\n", + " model = load_model(\"convnet-multiscale-true-022unk\")" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/100000\n", + "100000/100000 [==============================] - 135s - loss: 0.1939 \n", + "Epoch 2/100000\n", + " 99500/100000 [============================>.] - ETA: 0s - loss: 0.1922" + ] + }, + { + "ename": "KeyboardInterrupt", + "evalue": "", + "output_type": "error", + "traceback": [ + "\u001b[0;31m\u001b[0m", + "\u001b[0;31mKeyboardInterrupt\u001b[0mTraceback (most recent call last)", + "\u001b[0;32m<ipython-input-21-09ad3c297605>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mK\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'/gpu:2'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 7\u001b[0m model.fit_generator(data_generator(X_train, y_train, batch_size=50), samples_per_epoch, nb_epoch, \n\u001b[0;32m----> 8\u001b[0;31m callbacks=[earlyStopping], verbose=1)#, nb_val_samples=20000,\n\u001b[0m\u001b[1;32m 9\u001b[0m \u001b[0;31m#validation_data=data_generator(X_val, y_val, batch_size=40))\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python2.7/dist-packages/keras/engine/training.pyc\u001b[0m in \u001b[0;36mfit_generator\u001b[0;34m(self, generator, samples_per_epoch, nb_epoch, verbose, callbacks, validation_data, nb_val_samples, class_weight, max_q_size, nb_worker, pickle_safe)\u001b[0m\n\u001b[1;32m 1451\u001b[0m \u001b[0mbatch_logs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0ml\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mo\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1452\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1453\u001b[0;31m \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_batch_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch_index\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_logs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1454\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1455\u001b[0m \u001b[0;31m# construct epoch logs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python2.7/dist-packages/keras/callbacks.pyc\u001b[0m in \u001b[0;36mon_batch_end\u001b[0;34m(self, batch, logs)\u001b[0m\n\u001b[1;32m 59\u001b[0m \u001b[0mt_before_callbacks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 60\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mcallback\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 61\u001b[0;31m \u001b[0mcallback\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_batch_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 62\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_delta_ts_batch_end\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mt_before_callbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 63\u001b[0m \u001b[0mdelta_t_median\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmedian\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_delta_ts_batch_end\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python2.7/dist-packages/keras/callbacks.pyc\u001b[0m in \u001b[0;36mon_batch_end\u001b[0;34m(self, batch, logs)\u001b[0m\n\u001b[1;32m 187\u001b[0m \u001b[0;31m# will be handled by on_epoch_end\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 188\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mverbose\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mseen\u001b[0m \u001b[0;34m<\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparams\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'nb_sample'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 189\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprogbar\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mseen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlog_values\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 190\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 191\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mon_epoch_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepoch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m}\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/python2.7/dist-packages/keras/utils/generic_utils.pyc\u001b[0m in \u001b[0;36mupdate\u001b[0;34m(self, current, values, force)\u001b[0m\n\u001b[1;32m 157\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 158\u001b[0m \u001b[0msys\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstdout\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minfo\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 159\u001b[0;31m \u001b[0msys\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstdout\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mflush\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 160\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 161\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mcurrent\u001b[0m \u001b[0;34m>=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtarget\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python2.7/dist-packages/ipykernel/iostream.pyc\u001b[0m in \u001b[0;36mflush\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 267\u001b[0m \u001b[0mevt\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mthreading\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mEvent\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 268\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_io_loop\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd_callback\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mevt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 269\u001b[0;31m \u001b[0mevt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\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 270\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 271\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_flush\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/lib/python2.7/threading.pyc\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 618\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 619\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__flag\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 620\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__cond\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 621\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__flag\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 622\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/lib/python2.7/threading.pyc\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 337\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# restore state no matter what (e.g., KeyboardInterrupt)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 338\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtimeout\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 339\u001b[0;31m \u001b[0mwaiter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0macquire\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 340\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0m__debug__\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 341\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_note\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"%s.wait(): got it\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mKeyboardInterrupt\u001b[0m: " + ] + } + ], + "source": [ + "from keras.callbacks import EarlyStopping\n", + "nb_epoch = 100000\n", + "earlyStopping = EarlyStopping(monitor='val_loss', patience=10, verbose=0, mode='auto')\n", + "samples_per_epoch = 100000\n", + "\n", + "with K.tf.device('/gpu:2'):\n", + " model.fit_generator(data_generator(X_train, y_train, batch_size=50), samples_per_epoch, nb_epoch, \n", + " callbacks=[earlyStopping], verbose=1)#, nb_val_samples=20000,\n", + " #validation_data=data_generator(X_val, y_val, batch_size=40))" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 70s - loss: 0.1640 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + " 24%|██▍ | 12/49 [00:00<00:00, 119.99it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 135.88it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 215.36it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 248.00it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 219.17it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 67s - loss: 0.1592 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\r", + " 0%| | 0/49 [00:00<?, ?it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 126.00it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 190.92it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 161.84it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 190.56it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 60s - loss: 0.1557 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\r", + " 0%| | 0/49 [00:00<?, ?it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 175.59it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 188.29it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 170.44it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 202.76it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 73s - loss: 0.1545 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + " 29%|██▊ | 14/49 [00:00<00:00, 139.19it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 190.23it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 235.47it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 221.90it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 171.74it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 72s - loss: 0.1556 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\r", + " 0%| | 0/49 [00:00<?, ?it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 119.83it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 195.06it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 187.22it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 201.47it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 68s - loss: 0.1563 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + " 27%|██▋ | 13/49 [00:00<00:00, 119.17it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 142.53it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 203.55it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 192.02it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 193.69it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 72s - loss: 0.1588 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + " 31%|███ | 15/49 [00:00<00:00, 145.08it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 181.02it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 199.11it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 229.50it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 204.20it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 67s - loss: 0.1598 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + " 37%|███▋ | 18/49 [00:00<00:00, 174.26it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 130.09it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 208.28it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 189.43it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 181.52it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 53s - loss: 0.1634 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + " 41%|████ | 20/49 [00:00<00:00, 191.91it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 202.34it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 216.69it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 212.14it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 212.55it/s]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/1\n", + "30000/30000 [==============================] - 70s - loss: 0.1491 " + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + " 29%|██▊ | 14/49 [00:00<00:00, 135.21it/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 188.83it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 169.04it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 178.81it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 182.79it/s]\n" + ] + } + ], + "source": [ + "# BLEND NNS\n", + "for blend_id in range(25, 35):\n", + " with K.tf.device('/gpu:2'):\n", + " model.fit_generator(data_generator(X_train, y_train, batch_size=100), samples_per_epoch=30000, nb_epoch=1, \n", + " callbacks=[earlyStopping], verbose=1)\n", + " \n", + " df = []\n", + " for subj in test:\n", + " for chunk in tqdm(test[subj]):\n", + " data = {}\n", + " data[\"subject_id\"] = int(subj.split(\"_\")[-1])\n", + " data[\"chunk_id\"] = int(chunk.split(\"_\")[-1])\n", + " arr = test[subj][chunk].T\n", + " preds = model.predict([np.array([i]) for i in multiscale(arr)])[0]\n", + " data[\"class_0_score\"] = preds[0]\n", + " data[\"class_1_score\"] = preds[1]\n", + " data[\"class_2_score\"] = preds[2]\n", + " for i in range(0, 1125):\n", + " data[\"tick\"] = i\n", + " df.append(data.copy())\n", + " df = pd.DataFrame(df)\n", + " df = df[[\"subject_id\", \"chunk_id\", \"tick\", \"class_0_score\",\n", + " \"class_1_score\",\"class_2_score\"]]\n", + " \n", + " df.to_csv('submit_blended_' + str(blend_id) + '.csv', index=False)" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "model.save(\"convnet-multiscale-deep-021unk\")" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 49/49 [00:00<00:00, 165.60it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 185.89it/s]\n", + "100%|██████████| 49/49 [00:00<00:00, 189.62it/s]\n", + "100%|██████████| 89/89 [00:00<00:00, 175.60it/s]\n" + ] + } + ], + "source": [ + "df = []\n", + "for subj in test:\n", + " for chunk in tqdm(test[subj]):\n", + " data = {}\n", + " data[\"subject_id\"] = int(subj.split(\"_\")[-1])\n", + " data[\"chunk_id\"] = int(chunk.split(\"_\")[-1])\n", + " arr = test[subj][chunk].T\n", + " preds = model.predict([np.array([i]) for i in multiscale(arr)])[0]\n", + " data[\"class_0_score\"] = preds[0]\n", + " data[\"class_1_score\"] = preds[1]\n", + " data[\"class_2_score\"] = preds[2]\n", + " for i in range(0, 1125):\n", + " data[\"tick\"] = i\n", + " df.append(data.copy())\n", + "df = pd.DataFrame(df)\n", + "df = df[[\"subject_id\", \"chunk_id\", \"tick\", \"class_0_score\",\n", + " \"class_1_score\",\"class_2_score\"]]" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "df.to_csv('submit_true_multiscale_016_large_batch.csv', index=False)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.6" + } + }, + "nbformat": 4, + "nbformat_minor": 1 +}