have 2 datasets, for the first data set i want to apply convolution and keep the result of flatten layyer then concatenate it with an other data set and a do a simple feed forward it is possible with keras ?
def build_model(x_train,y_train):
np.random.seed(7)
left = Sequential()
left.add(Conv1D(nb_filter= 6, filter_length=3, input_shape= (48,1),activation = 'relu', kernel_initializer='glorot_uniform'))
left.add(Conv1D(nb_filter= 6, filter_length=3, activation= 'relu'))
#model.add(MaxPooling1D())
print model
#model.add(Dropout(0.2))
# flatten layer
#https://www.quora.com/What-is-the-meaning-of-flattening-step-in-a-convolutional-neural-network
left.add(Flatten())
left.add(Reshape((48,1)))
right = Sequential()
#model.add(Reshape((48,1)))
# Compile model
model.add(Merge([left, right], mode='sum'))
model.add(Dense(10, 10))
epochs = 100
lrate = 0.01
decay = lrate/epochs
sgd = SGD(lr=lrate, momentum=0.9, decay=decay, nesterov=False)
#clipvalue=0.5)
model.compile(loss='mean_squared_error', optimizer='Adam')
model.fit(x_train,y_train, nb_epoch =epochs, batch_size=10, verbose=1)
#model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'] , )
return model
You need to look at the functional API. The sequential model you are using is not designed to take multiple network inputs.
Follow the "Multi-input and multi-output models" example and you will have it working in no time!
Related
sequence_input = Input(shape=(MAX_LENGTH_SEQUENCE,), dtype='int32')
embedded_sequences = embedding_layer(sequence_input)
l_lstm = Bidirectional(LSTM(10))(embedded_sequences)
preds = Dense(len(macronum), activation='softmax')(l_lstm)
model = Model(sequence_input, preds)
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['acc'])
I need to add additional hidden layer and an attention layer to the above LSTM model , usually i construct the model in this way:
model = tensorflow.keras.Sequential()
model.add(tensorflow.keras.layers.LSTM(128, dropout=0.3,
recurrent_dropout=0.2,input_shape=(N, K), return_sequences=True))
#model.add(tensorflow.keras.layers.LSTM(128, dropout=0.3,
recurrent_dropout=0.2,input_shape=(N, K), return_sequences=True))
model.add(Attention(name='attention_weight'))
model.add(tensorflow.keras.layers.Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
print(model.summary())
print(_x_train.shape)
model.fit(_x_train, _y_train, epochs=10, batch_size=1)
scores = model.evaluate(_x_test, _y_test, verbose=0)
print("Accuracy: %.2f%%" % (scores[1]*100))
as shown in the second code i normaly stack and add as many layer as i need using
model.add
but for the first code i'm not familiar with this approach,
if i want to add extra LSTM layer and Attention layer to the first code, where should i include them inside the code? what is the right syntax ?
I am trying to use keras to train a simple feedforward network. I tried two different methods of what I think is the same network, but one is performing significantly better. The first one and the better performing one is the following:
inputs = keras.Input(shape=(384,))
dense = layers.Dense(64, activation="relu")
x = dense(inputs)
x = layers.Dense(64, activation="relu")(x)
outputs = layers.Dense(384)(x)
model = keras.Model(inputs=inputs, outputs=outputs, name="simple_model")
model.compile(loss='mse',optimizer='Adam')
history = model.fit(X_train,
y_train_tf,
epochs=20,
validation_data=(X_test, y_test),
steps_per_epoch=100,
validation_steps=50)
and it settles on a validation loss of about 0.2. The second model performs much worse:
model = keras.models.Sequential()
model.add(Dense(64, input_shape=(384,), activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(384, activation='relu'))
optimizer = tf.keras.optimizers.Adam()
model.compile(loss='mse', optimizer=optimizer)
history = model.fit(X_train,
y_train_tf,
epochs=20,
validation_data=(X_test, y_test),
steps_per_epoch=100,
validation_steps=50)
and this has validation loss of around 5. But when I do model.summary, they look virtually the same. Is there something wrong with the second model?
I am not sure that they are the same since second model has relu activation after last layer (384 units) and first doesn't. This might be the issue since default activation of the Keras dense layer is None.
I am trying to implement a system by encoding inputs using CNN. After CNN, I need to get a vector and use it in another deep learning method.
def get_input_representation(self):
# get word vectors from embedding
inputs = tf.nn.embedding_lookup(self.embeddings, self.input_placeholder)
sequence_length = inputs.shape[1] # 56
vocabulary_size = 160 # 18765
embedding_dim = 256
filter_sizes = [3,4,5]
num_filters = 3
drop = 0.5
epochs = 10
batch_size = 30
# this returns a tensor
print("Creating Model...")
inputs = Input(shape=(sequence_length,), dtype='int32')
embedding = Embedding(input_dim=vocabulary_size, output_dim=embedding_dim, input_length=sequence_length)(inputs)
reshape = Reshape((sequence_length,embedding_dim,1))(embedding)
conv_0 = Conv2D(num_filters, kernel_size=(filter_sizes[0], embedding_dim), padding='valid', kernel_initializer='normal', activation='relu')(reshape)
conv_1 = Conv2D(num_filters, kernel_size=(filter_sizes[1], embedding_dim), padding='valid', kernel_initializer='normal', activation='relu')(reshape)
conv_2 = Conv2D(num_filters, kernel_size=(filter_sizes[2], embedding_dim), padding='valid', kernel_initializer='normal', activation='relu')(reshape)
maxpool_0 = MaxPool2D(pool_size=(sequence_length - filter_sizes[0] + 1, 1), strides=(1,1), padding='valid')(conv_0)
maxpool_1 = MaxPool2D(pool_size=(sequence_length - filter_sizes[1] + 1, 1), strides=(1,1), padding='valid')(conv_1)
maxpool_2 = MaxPool2D(pool_size=(sequence_length - filter_sizes[2] + 1, 1), strides=(1,1), padding='valid')(conv_2)
concatenated_tensor = Concatenate(axis=1)([maxpool_0, maxpool_1, maxpool_2])
flatten = Flatten()(concatenated_tensor)
dropout = Dropout(drop)(flatten)
output = Dense(units=2, activation='softmax')(dropout)
model = Model(inputs=inputs, outputs=output)
adam = Adam(lr=1e-4, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
model.compile(optimizer=adam, loss='binary_crossentropy', metrics=['accuracy'])
adam = Adam(lr=1e-4, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
model.compile(optimizer=adam, loss='binary_crossentropy', metrics=['accuracy'])
print("Traning Model...")
model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, callbacks=[checkpoint], validation_data=(X_test, y_test)) # starts training
return ??
The above code, trains the model using X_train and Y_train and then tests it. However in my system I do not have Y_train or Y_test, I only need the vector in the last hidden layer before softmax layer. How can I obtain it?
For that you can define a backend function to get the output of arbitrary layer(s):
from keras import backend as K
func = K.function([model.input], [model.layers[index_of_layer].output])
You can find the index of your desired layer using model.summary() where the layers are listed starting from index zero. If you need the layer before the last layer you can use -2 as the index (i.e. .layers attribute is actually a list so you can index it like a list in python). Then you can use the function you have defined by passing a list of input array(s):
outputs = func(inputs)
Alternatively, you can also define a model for this purpose. This has been covered in Keras documentation more thoroughly so I advise you to read that.
How to tune the network automatically instead of adjusting the number of hidden layers and epochs everytime manually? (Using Keras)
from keras.models import Sequential
from keras.layers import Dense
import numpy
seed = 9
numpy.random.seed(seed)
from pandas import read_csv
filename = 'BBCN.csv'
dataframe = read_csv(filename)
array = dataframe.values
x = array[:,0 : 11]
y = array[:, 11]
model = Sequential()
model.add(Dense(11, input_dim=11, kernel_initializer = 'uniform', z = 'relu'))
model.add(Dense(8, kernel_initializer = 'uniform', activation = 'relu'))
model.add(Dense(8, kernel_initializer = 'uniform', activation = 'relu'))
model.add(Dense(1, kernel_initializer = 'uniform', activation = 'sigmoid'))
model.compile(loss='binary_crossentropy', optimizer ='adam', metrics = ['accuracy'])
model.fit(x, y,nb_epoch = 50, batch_size = 10 )
scores = model.evaluate(x,y)
print("%s, %.2f%%" % (model.metrics_names[1], scores[1]*100))
The result I need is to show the process and the percentage of the accuracy.
Thanks a lot!
You could start with a simple loop over some hyperparameters and train with these for some epochs and then compare the results.
You can also look into grid search which is a more systematic approach. Basically you setup a function that creates a model and use it with a set of hyperparameters that you want to try out and an array of values. For more details and boilerplate code I recommend this tutorial.
How do I train 1 model multiple times and combine them at the output layer?
For example:
model_one = Sequential() #model 1
model_one.add(Convolution2D(32, 3, 3, activation='relu', input_shape=(1,28,28)))
model_one.add(Flatten())
model_one.add(Dense(128, activation='relu'))
model_two = Sequential() #model 2
model_two.add(Dense(128, activation='relu', input_shape=(784)))
model_two.add(Dense(128, activation='relu'))
model_???.add(Dense(10, activation='softmax')) #combine them here
model.compile(loss='categorical_crossentropy', #continu together
optimizer='adam',
metrics=['accuracy'])
model.fit(X_train, Y_train, #continu together somehow, even though this would never work because X_train and Y_train have wrong formats
batch_size=32, nb_epoch=10, verbose=1)
I've heard I can do this through a graph model but I can't find any documentation on it.
EDIT: in reply to the suggestion below:
A1 = Conv2D(20,kernel_size=(5,5),activation='relu',input_shape=( 28, 28, 1))
---> B1 = MaxPooling2D(pool_size=(2,2))(A1)
throws this error:
AttributeError: 'Conv2D' object has no attribute 'get_shape'
Graph notation would do it for you. Essentially you give every layer a unique handle then link back to the previous layer using the handle in brackets at the end:
layer_handle = Layer(params)(prev_layer_handle)
Note that the first layer must be an Input(shape=(x,y)) with no prior connection.
Then when you make your model you need to tell it that it expects multiple inputs with a list:
model = Model(inputs=[in_layer1, in_layer2, ..], outputs=[out_layer1, out_layer2, ..])
Finally when you train it you also need to provide a list of input and output data that corresponds with your definition:
model.fit([x_train1, x_train2, ..], [y_train1, y_train2, ..])
Meanwhile everything else is the same so you just need to combine together the above to give you the network layout that you want:
from keras.models import Model
from keras.layers import Input, Convolution2D, Flatten, Dense, Concatenate
# Note Keras 2.02, channel last dimension ordering
# Model 1
in1 = Input(shape=(28,28,1))
model_one_conv_1 = Convolution2D(32, (3, 3), activation='relu')(in1)
model_one_flat_1 = Flatten()(model_one_conv_1)
model_one_dense_1 = Dense(128, activation='relu')(model_one_flat_1)
# Model 2
in2 = Input(shape=(784, ))
model_two_dense_1 = Dense(128, activation='relu')(in2)
model_two_dense_2 = Dense(128, activation='relu')(model_two_dense_1)
# Model Final
model_final_concat = Concatenate(axis=-1)([model_one_dense_1, model_two_dense_2])
model_final_dense_1 = Dense(10, activation='softmax')(model_final_concat)
model = Model(inputs=[in1, in2], outputs=model_final_dense_1)
model.compile(loss='categorical_crossentropy', #continu together
optimizer='adam',
metrics=['accuracy'])
model.fit([X_train_one, X_train_two], Y_train,
batch_size=32, nb_epoch=10, verbose=1)
Documentation can be found in the Functional Model API. I'd recommend reading around other questions or checking out Keras' repo as well since the documentation currently doesn't have many examples.