from keras.preprocessing import sequence
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.layers.embeddings import Embedding
from keras.layers.recurrent import LSTM
from keras.datasets import imdb
from nlp_code.get_data import input_data
max_features = 20000
maxlen = 100 # cut texts after this number of words (among top max_features most common words)
batch_size = 32
print('Loading data...')
# (X_train, y_train), (X_test, y_test) = imdb.load_data(nb_words=max_features,
# test_split=0.2)
X_train, y_train, X_test, y_test = input_data()
print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')
print("Pad sequences (samples x time)")
X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
print('X_train shape:', X_train.shape)
#(samples, dim)
print('X_test shape:', X_test.shape)
#Y 1, 0
print('Build model...')
model = Sequential()
# model.add(Embedding(max_features, 128, input_length=maxlen, dropout=0.5))
model.add(Embedding(max_features, 128, input_length=maxlen))
# model.add(LSTM(128, dropout_W=0.5, dropout_U=0.5)) # try using a GRU instead, for fun
from nlp_code.get_data import input_data_gen_w2v, input_data_w2v, input_data
__author__ = 'bohaohan'
from keras.models import Sequential
from keras.layers import LSTM, Dense, Embedding
import numpy as np
print('Loading data...')
x_train, y_train, x_val, y_val = input_data()
print "end load"
data_dim = 300
timesteps = len(x_train[0])
nb_classes = 1
nb_epoch = 2000
print "build model"
# expected input data shape: (batch_size, timesteps, data_dim)
model = Sequential()
model.add(Embedding(1, 128, input_length=timesteps))
model.add(LSTM(200, return_sequences=True))
# ,input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 32
model.add(LSTM(
100,
return_sequences=True)) # returns a sequence of vectors of dimension 32
model.add(LSTM(32)) # return a single vector of dimension 32
model.add(Dense(nb_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
print "finish model"
# generate dummy training data
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.layers.embeddings import Embedding
from keras.layers.recurrent import LSTM
from keras.datasets import imdb
from nlp_code.get_data import input_data
max_features = 20000
maxlen = 100 # cut texts after this number of words (among top max_features most common words)
batch_size = 32
print('Loading data...')
# (X_train, y_train), (X_test, y_test) = imdb.load_data(nb_words=max_features,
# test_split=0.2)
X_train, y_train, X_test, y_test = input_data()
print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')
print("Pad sequences (samples x time)")
X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
print('X_train shape:', X_train.shape)
#(samples, dim)
print('X_test shape:', X_test.shape)
#Y 1, 0
print('Build model...')
model = Sequential()
# model.add(Embedding(max_features, 128, input_length=maxlen, dropout=0.5))
model.add(Embedding(max_features, 128, input_length=maxlen))
# model.add(LSTM(128, dropout_W=0.5, dropout_U=0.5)) # try using a GRU instead, for fun
''' from keras.models import Sequential from keras.layers.core import Dense, Dropout, Activation, Flatten from keras.layers.convolutional import Convolution2D, MaxPooling2D from keras.optimizers import SGD from keras.utils import np_utils import random, cPickle from nlp_code.get_data import input_data # load data data, label = input_data() # shuffle data index = [i for i in range(len(data))] random.shuffle(index) data = data[index] data = data/255 label = label[index] print(data.shape[0], ' samples') # 20 classes, transform labels into the format requirement of keras is binary class matrices label = np_utils.to_categorical(label, 20) # print (data) ############### # start to build CNN model ###############
from nlp_code.get_data import input_data_gen_w2v, input_data_w2v, input_data
__author__ = 'bohaohan'
from keras.models import Sequential
from keras.layers import LSTM, Dense, Embedding
import numpy as np
print('Loading data...')
x_train, y_train, x_val, y_val = input_data()
print "end load"
data_dim = 300
timesteps = len(x_train[0])
nb_classes = 1
nb_epoch = 2000
print "build model"
# expected input data shape: (batch_size, timesteps, data_dim)
model = Sequential()
model.add(Embedding(1, 128, input_length=timesteps))
model.add(LSTM(200, return_sequences=True))
# ,input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 32
model.add(LSTM(100, return_sequences=True)) # returns a sequence of vectors of dimension 32
model.add(LSTM(32)) # return a single vector of dimension 32
model.add(Dense(nb_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
print "finish model"
# generate dummy training data
CPU run command:
python cnn.py
'''
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD
from keras.utils import np_utils
import random, cPickle
from nlp_code.get_data import input_data
# load data
data, label = input_data()
# shuffle data
index = [i for i in range(len(data))]
random.shuffle(index)
data = data[index]
data = data / 255
label = label[index]
print(data.shape[0], ' samples')
# 20 classes, transform labels into the format requirement of keras is binary class matrices
label = np_utils.to_categorical(label, 20)
# print (data)
###############
# start to build CNN model
###############