跑lmdb_lstm.py 因为需要用lstm,所以就先跑 lstm例子,
1、官网下载后,直接运行lmdb_lstm.py。总是提示无法下载,打开程序有看到, 通过load_data来下载数据,但是这个数据没法在线下载,导致跑不通。
print("Loading data...")
(X_train, y_train), (X_test, y_test) = imdb.load_data(nb_words=max_features, test_split=0.2)
解决:在lmdb.py 中路径更改一下。 如下边所示,直接给路径。
# path = get_file(path, origin="https://s3.amazonaws.com/text-datasets/imdb.pkl")
path = "E:\\project\\deep learning\\RNN\\eeg rnn\\theano code\\keras-master\\imdb.pkl"
再次运行,即可跑通
二、下边是官网 例子说明,讲的很清楚, 看完这个才真正发现,这个库确实 很好用,很简单啊。 就是速度有点慢。
官网地址:http://keras.io/examples/
Here are a few examples to get you started!
from keras.models import Sequentialfrom keras.layers.core import Dense, Dropout, Activationfrom keras.optimizers import SGDmodel = Sequential()# Dense(64) is a fully-connected layer with 64 hidden units.# in the first layer, you must specify the expected input data shape:# here, 20-dimensional vectors.model.add(Dense(64, input_dim=20, init='uniform')) // 全连接层, 64个神经元model.add(Activation('tanh'))model.add(Dropout(0.5))model.add(Dense(64, init='uniform'))model.add(Activation('tanh'))model.add(Dropout(0.5))model.add(Dense(2, init='uniform'))model.add(Activation('softmax')) // 最后一个全连接层用 softmax当激活函数sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True) // 用随机梯度下降优化,nesterov?????model.compile(loss='mean_squared_error', optimizer=sgd)model.fit(X_train, y_train, nb_epoch=20, batch_size=16)score = model.evaluate(X_test, y_test, batch_size=16)
model = Sequential()model.add(Dense(64, input_dim=20, init='uniform', activation='tanh'))model.add(Dropout(0.5))model.add(Dense(64, init='uniform', activation='tanh'))model.add(Dropout(0.5))model.add(Dense(2, init='uniform', activation='softmax'))sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True) model.compile(loss='mean_squared_error', optimizer=sgd)
from keras.models import Sequentialfrom keras.layers.core import Dense, Dropout, Activation, Flattenfrom keras.layers.convolutional import Convolution2D, MaxPooling2Dfrom keras.optimizers import SGDmodel = Sequential()# input: 100x100 images with 3 channels -> (3, 100, 100) tensors.# this applies 32 convolution filters of size 3x3 each.model.add(Convolution2D(32, 3, 3, border_mode='full', input_shape=(3, 100, 100)))model.add(Activation('relu'))model.add(Convolution2D(32, 3, 3))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Convolution2D(64, 3, 3, border_mode='valid'))model.add(Activation('relu'))model.add(Convolution2D(64, 3, 3))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Flatten())# Note: Keras does automatic shape inference.model.add(Dense(256))model.add(Activation('relu'))model.add(Dropout(0.5))model.add(Dense(10))model.add(Activation('softmax'))sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)model.compile(loss='categorical_crossentropy', optimizer=sgd)model.fit(X_train, Y_train, batch_size=32, nb_epoch=1)
from keras.models import Sequentialfrom keras.layers.core import Dense, Dropout, Activationfrom keras.layers.embeddings import Embeddingfrom keras.layers.recurrent import LSTMmodel = Sequential()model.add(Embedding(max_features, 256, input_length=maxlen))model.add(LSTM(output_dim=128, activation='sigmoid', inner_activation='hard_sigmoid'))model.add(Dropout(0.5))model.add(Dense(1))model.add(Activation('sigmoid'))model.compile(loss='binary_crossentropy', optimizer='rmsprop')model.fit(X_train, Y_train, batch_size=16, nb_epoch=10)score = model.evaluate(X_test, Y_test, batch_size=16)
(word-level embedding, caption of maximum length 16 words).
Note that getting this to work well will require using a bigger convnet, initialized with pre-trained weights.
max_caption_len = 16vocab_size = 10000# first, let's define an image model that# will encode pictures into 128-dimensional vectors.# it should be initialized with pre-trained weights.image_model = Sequential()image_model.add(Convolution2D(32, 3, 3, border_mode='full', input_shape=(3, 100, 100)))image_model.add(Activation('relu'))image_model.add(Convolution2D(32, 3, 3))image_model.add(Activation('relu'))image_model.add(MaxPooling2D(pool_size=(2, 2)))image_model.add(Convolution2D(64, 3, 3, border_mode='full'))image_model.add(Activation('relu'))image_model.add(Convolution2D(64, 3, 3))image_model.add(Activation('relu'))image_model.add(MaxPooling2D(pool_size=(2, 2)))image_model.add(Flatten())image_model.add(Dense(128))# let's load the weights from a save file.image_model.load_weights('weight_file.h5')# next, let's define a RNN model that encodes sequences of words# into sequences of 128-dimensional word vectors.language_model = Sequential()language_model.add(Embedding(vocab_size, 256, input_length=max_caption_len))language_model.add(GRU(output_dim=128, return_sequences=True))language_model.add(Dense(128))# let's repeat the image vector to turn it into a sequence.image_model.add(RepeatVector(max_caption_len))# the output of both models will be tensors of shape (samples, max_caption_len, 128).# let's concatenate these 2 vector sequences.model = Sequential()model.add(Merge([image_model, language_model], mode='concat', concat_axis=-1))# let's encode this vector sequence into a single vectormodel.add(GRU(256, 256, return_sequences=False))# which will be used to compute a probability# distribution over what the next word in the caption should be!model.add(Dense(vocab_size))model.add(Activation('softmax'))model.compile(loss='categorical_crossentropy', optimizer='rmsprop')# "images" is a numpy float array of shape (nb_samples, nb_channels=3, width, height).# "captions" is a numpy integer array of shape (nb_samples, max_caption_len)# containing word index sequences representing partial captions.# "next_words" is a numpy float array of shape (nb_samples, vocab_size)# containing a categorical encoding (0s and 1s) of the next word in the corresponding# partial caption.model.fit([images, partial_captions], next_words, batch_size=16, nb_epoch=100)
In the examples folder, you will find example models for real datasets: - CIFAR10 small images classification: Convolutional Neural Network (CNN) with realtime data augmentation - IMDB movie review sentiment classification: LSTM over sequences of words - Reuters newswires topic classification: Multilayer Perceptron (MLP) - MNIST handwritten digits classification: MLP & CNN - Character-level text generation with LSTM
...and more.
三、看到网上一篇博客注释lstm, 这个可能是老版本上注释的, 但是参数还是有可借鉴的地方参考博客地址: http://www.jianshu.com/p/3992fe7bb847
keras.layers.recurrent.GRU(input_dim, output_dim=128, init='glorot_uniform', inner_init='orthogonal', activation='sigmoid', inner_activation='hard_sigmoid', weights=None, truncate_gradient=-1, return_sequences=False)
Gated Recurrent Unit - Cho et al. 2014.
(nb_samples, timesteps, input_dim)
.return_sequences
:3D 张量形如:(nb_samples, timesteps, output_dim)
.(nb_samples, output_dim)
.keras.layers.recurrent.LSTM(input_dim, output_dim=128, init='glorot_uniform', inner_init='orthogonal', forget_bias_init='one', activation='tanh', inner_activation='hard_sigmoid', weights=None, truncate_gradient=-1, return_sequences=False)
Long Short-Term Memory unit - Hochreiter et al. 1997
(nb_samples, timesteps, input_dim)
.return_sequences
:3D 张量形如:(nb_samples, timesteps, output_dim)
.(nb_samples, output_dim)
.keras.layers.recurrent.JZS1(input_dim, output_dim=128, init='glorot_uniform', inner_init='orthogonal', activation='tanh', inner_activation='sigmoid', weights=None, truncate_gradient=-1, return_sequences=False)
全连接的 RNN 其中输出被重回输入。不是特别有用,仅供参考。
(nb_samples, timesteps, input_dim)
.return_sequences
:3D 张量形如:(nb_samples, timesteps, output_dim)
.(nb_samples, output_dim)
.[(input_dim, output_dim), (output_di,, output_dim), (output_dim, )]
keras.layers.recurrent.SimpleDeepRNN(input_dim, output_dim, depth=3, init='glorot_uniform', inner_init='orthogonal', activation='sigmoid', inner_activation='hard_sigmoid', weights=None, truncate_gradient=-1, return_sequences=False)
全连接的 RNN 其中多个时间步的输出重回输入中(使用 depth 参数来控制步数)。
output = activation( W.x_t + b + inner_activation(U_1.h_tm1) + inner_activation(U_2.h_tm2) + ... )
也不是常用的模型,仅供参考。
(nb_samples, timesteps, input_dim)
.return_sequences
:3D 张量形如:(nb_samples, timesteps, output_dim)
.(nb_samples, output_dim)
.[(input_dim, output_dim), (output_di,, output_dim), (output_dim, )]
联系客服