I am currently looking for a way i can combine the output of multiple model into one model, I need to create a CNN network that does classification.
The image is separated into sections (as seen by the colors), each section is given as input to a certain model (1,2,3,4) the structure of each model is the same, but each section is given to a separate model to ensure that the the same weight is not applied on whole image - My attempt to avoid full weight sharing, and keeping the weight sharing local. Each model then perform convolution and max pooling, and generate some sort of output that has to fed into a dense layer that takes the outputs from the prior models (model 1,2,3,4,) and performs classifications.
My question here is it possible to create model 1,2,3,4 and connect it to the fully connected layer and train all the models given the input sections and and the output class - without having to define the outputs of the convolution and pooling layer in keras?
Yes, you can create such models using Multi-input and multi-output models, refer keras documentation for more details. Here I am sharing code sample, hope this helps
import numpy as np
import keras
from keras.optimizers import SGD
from keras.models import Sequential, Model
from keras.layers import Activation, Dense, Dropout, Flatten, Input, Merge, Convolution2D, MaxPooling2D
# Generate dummy data
train1 = np.random.random((100, 100, 100, 3))
train2 = np.random.random((100, 100, 100, 3))
train3 = np.random.random((100, 100, 100, 3))
train4 = np.random.random((100, 100, 100, 3))
y_train = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
#parallel ip for different sections of image
inp1 = Input(shape=train1.shape[1:])
inp2 = Input(shape=train2.shape[1:])
inp3 = Input(shape=train3.shape[1:])
inp4 = Input(shape=train4.shape[1:])
# paralle conv and pool layer which process each section of input independently
conv1 = Conv2D(64, (3, 3), activation='relu')(inp1)
conv2 = Conv2D(64, (3, 3), activation='relu')(inp2)
conv3 = Conv2D(64, (3, 3), activation='relu')(inp3)
conv4 = Conv2D(64, (3, 3), activation='relu')(inp4)
maxp1 = MaxPooling2D((3, 3))(conv1)
maxp2 =MaxPooling2D((3, 3))(conv2)
maxp3 =MaxPooling2D((3, 3))(conv3)
maxp4 =MaxPooling2D((3, 3))(conv4)
# can add multiple parallel conv, pool layes to reduce size
flt1 = Flatten()(maxp1)
flt2 = Flatten()(maxp2)
flt3 = Flatten()(maxp3)
flt4 = Flatten()(maxp4)
mrg = Merge(mode='concat')([flt1,flt2,flt3,flt4])
dense = Dense(256, activation='relu')(mrg)
op = Dense(10, activation='softmax')(dense)
model = Model(input=[inp1, inp2, inp3, inp4], output=op)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit([train1,train2,train3,train4], y_train,
nb_epoch=10, batch_size=28)
Related
I'm making my first steps on keras and I'm trying to do binary classification on the cancer dataset available in scikit-learn
# load dataset
from sklearn import datasets
cancer = datasets.load_breast_cancer()
cancer.data
# dataset into pd.dataframe
import pandas as pd
donnee = pd.concat([pd.DataFrame(data = cancer.data, columns = cancer.feature_names),
pd.DataFrame(data = cancer.target, columns = ["target"])
], axis = 1)
# train/test split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(donnee.loc[:, donnee.columns != "target"], donnee.target, test_size = 0.25, random_state = 1)
I'm trying to follow keras' tutorial here : https://keras.io/#getting-started-30-seconds-to-keras
The thing is, I always get the same loss value (6.1316862406430541), and the same accuracy (0.61538461830232527), because the predictions are always 1.
I'm not sure if it's because of a code error :
I don't know, maybe the shape of X_train is wrong ?
Or maybe I'm doing something wrong with epochs and/or batch_size.
Or if it's because of the network itself :
if I'm not mistaken, all 1 predictions is possible if there's no biases to the layers, and I don't know yet how they're initialized
But maybe it's something else, maybe 1 layer only is too few ? (if so, I wonder why keras' tutorial is 1 layer only...)
Here is my code, if you have any idea :
import keras
from keras.models import Sequential
model = Sequential()
from keras.layers import Dense
model.add(Dense(units=64, activation='relu', input_dim=30))
model.add(Dense(units=1, activation='sigmoid'))
model.summary()
model.compile(loss = keras.losses.binary_crossentropy,
optimizer = 'rmsprop',
metrics=['accuracy']
)
model.fit(X_train.as_matrix(), y_train.as_matrix().reshape(426, -1), epochs=5, batch_size=32)
loss_and_metrics = model.evaluate(X_test.as_matrix(), y_test.as_matrix(), batch_size=128)
loss_and_metrics
classes = model.predict(X_test.as_matrix(), batch_size=128)
classes
This is a very usual case. If you check the histogram of your data you will see that there are data points in your dataset which coordinates spans from 0 to 100. When you feed such data to neural network input to sigmoid might be so big that it will suffer from underflow. In order to scale data, you could use either MinMaxScaler or StandardScaler thanks to what you'll make your data to have a span suitable for neural network computations.
Here is a simple neural network that contains 3 input values and 3 output values.
The error :
ValueError: Error when checking model target: expected dense_78 to have shape (None, 3) but got array with shape (3, 1)
Is thrown when I execute this network. I've the set the final layer to have 3 possible outputs which match the number of labels :
model.add(Dense(3, activation='softmax'))
I've not architected this network correctly, where is my mistake ?
data = ([[ 0.29365378],
[ 0.27958957],
[ 0.27946938]])
labels = [[1], [2], [3]]
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.optimizers import SGD
model.add(Dense(64, activation='relu', input_dim=1))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(3, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
model.fit(data, labels,
epochs=20,
batch_size=32)
A Dense(3...) will give you three outputs per sample.
The output of a Dense(3...) has shape (BatchSize,3), or (None,3) as Keras says it.
If you want one among 3 possible classes for each sample, then you must have labels with shape (BatchSize,3). Where in your case the batch size also seems to be 3.
You must format your labels in one-hot vectors:
class 1 = [1,0,0]
class 2 = [0,1,0]
class 3 = [0,0,1]
The to_categorical in keras.utils can help you with transforming numerical classes into one-hot vector classes.
If you have three samples, you must have labels as:
labels = [[1,0,0],[0,1,0],[0,0,1]]
Three samples, each sample with three possible classes, being the first sample class 1, the second sample class 2 and the third sample class 3.
This has shape (3,3) which will match the (None,3) demanded by Dense(3...).
I'm building a neural network to classify images that have an email address written on them. The positive folder contains images with email addresses written on top of the picture, in different fonts, colors, sizes and positions.
The negative folder contains images without text on top and also images with text on top that doesn't have the format of an email address (no # sign).
The pictures are 300 x 225 x 3 (rgb).
It should be a simple a simple classification task (the NN should be able to pick up that when there's an #, the image has an email) but my model isn't performing well. It's stuck at 83% test accuracy after 25 epochs. Also, it's taking 10 hours to train, which sounds excessive to me.
Can you help me to analyse the structure of my CNN and suggest improvements (or help me avoid pitfalls)?
The model I wrote is this:
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.preprocessing.image import ImageDataGenerator
input_size = (64, 48)
# Initialising the CNN
classifier = Sequential()
# Step 1 - Convolution
classifier.add(Conv2D(32, (3, 3), input_shape = (*input_size, 3), activation = 'relu'))
# Step 2 - Pooling
classifier.add(MaxPooling2D(pool_size = (2, 2)))
# Adding a second convolutional layer
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2, 2)))
# Step 3 - Flattening
classifier.add(Flatten())
# Step 4 - Full connection
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))
# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
# Part 2 - Fitting the CNN to the images
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True)
test_datagen = ImageDataGenerator(rescale = 1./255)
training_set = train_datagen.flow_from_directory('./training_Set',
target_size = input_size,
batch_size = 32,
class_mode = 'binary')
test_set = test_datagen.flow_from_directory('./test_set',
target_size = input_size,
batch_size = 32,
class_mode = 'binary')
classifier.fit_generator(training_set,
steps_per_epoch = 8000,
epochs = 25,
validation_data = test_set,
validation_steps = 2000)
I am a little new to neural networks and keras. I have some images with size 6*7 and the size of the filter is 15. I want to have several filters and train a convolutional layer separately on each and then combine them. I have looked at one example here:
model = Sequential()
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
border_mode='valid',
input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten(input_shape=input_shape))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('tanh'))
This model works with one filter. Can anybody give me some hints on how to modify the model to work with parallel convolutional layers.
Thanks
Here is an example of designing a network of parallel convolution and sub sampling layers in keras version 2. I hope this resolves your problem.
rows, cols = 100, 15
def create_convnet(img_path='network_image.png'):
input_shape = Input(shape=(rows, cols, 1))
tower_1 = Conv2D(20, (100, 5), padding='same', activation='relu')(input_shape)
tower_1 = MaxPooling2D((1, 11), strides=(1, 1), padding='same')(tower_1)
tower_2 = Conv2D(20, (100, 7), padding='same', activation='relu')(input_shape)
tower_2 = MaxPooling2D((1, 9), strides=(1, 1), padding='same')(tower_2)
tower_3 = Conv2D(20, (100, 10), padding='same', activation='relu')(input_shape)
tower_3 = MaxPooling2D((1, 6), strides=(1, 1), padding='same')(tower_3)
merged = keras.layers.concatenate([tower_1, tower_2, tower_3], axis=1)
merged = Flatten()(merged)
out = Dense(200, activation='relu')(merged)
out = Dense(num_classes, activation='softmax')(out)
model = Model(input_shape, out)
plot_model(model, to_file=img_path)
return model
The image of this network will look like
My approach is to create other model that defines all parallel convolution and pulling operations and concat all parallel result tensors to single output tensor. Now you can add this parallel model graph in your sequential model just like layer. Here is my solution, hope it solves your problem.
# variable initialization
from keras import Input, Model, Sequential
from keras.layers import Conv2D, MaxPooling2D, Concatenate, Activation, Dropout, Flatten, Dense
nb_filters =100
kernel_size= {}
kernel_size[0]= [3,3]
kernel_size[1]= [4,4]
kernel_size[2]= [5,5]
input_shape=(32, 32, 3)
pool_size = (2,2)
nb_classes =2
no_parallel_filters = 3
# create seperate model graph for parallel processing with different filter sizes
# apply 'same' padding so that ll produce o/p tensor of same size for concatination
# cancat all paralle output
inp = Input(shape=input_shape)
convs = []
for k_no in range(len(kernel_size)):
conv = Conv2D(nb_filters, kernel_size[k_no][0], kernel_size[k_no][1],
border_mode='same',
activation='relu',
input_shape=input_shape)(inp)
pool = MaxPooling2D(pool_size=pool_size)(conv)
convs.append(pool)
if len(kernel_size) > 1:
out = Concatenate()(convs)
else:
out = convs[0]
conv_model = Model(input=inp, output=out)
# add created model grapg in sequential model
model = Sequential()
model.add(conv_model) # add model just like layer
model.add(Conv2D(nb_filters, kernel_size[1][0], kernel_size[1][0]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten(input_shape=input_shape))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('tanh'))
For more information refer similar question: Combining the outputs of multiple models into one model
I am new to keras and I am trying to built my own neural network.
A task:
I need to write a system that can make decisions for the character, which may meet one or more enemies. The system can be known:
Percentage Health character
Presence of the pistol;
The number of enemies.
The answer must be in the form of one of the following:
Attack
Run
Hide (for a surprise attack)
To do nothing
To train up I made a table of "lessons":
https://i.stack.imgur.com/lD0WX.png
So here is my code:
# Create first network with Keras
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD
import numpy
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# split into input (X) and output (Y) variables
X = numpy.array([[0.5,1,1], [0.9,1,2], [0.8,0,1], [0.3,1,1], [0.6,1,2], [0.4,0,1], [0.9,1,7], [0.5,1,4], [0.1,0,1], [0.6,1,0], [1,0,0]])
Y = numpy.array([[1],[1],[1],[2],[2],[2],[3],[3],[3],[4],[4]])
# create model
model = Sequential()
model.add(Dense(3, input_dim=3, init='uniform', activation='relu'))
model.add(Dense(1, init='uniform', activation='sigmoid'))
# Compile model
sgd = SGD(lr=0.001)
model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy'])
# Fit the model
model.fit(X, Y, nb_epoch=150)
# calculate predictions
predictions = model.predict(X)
# round predictions
rounded = [round(x) for x in predictions]
print(rounded)
Here the predictions I get.
[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
The accuracy on each epoch is 0.2727 and the loss is decrease.
It's not right.
I was trying to devide learning rate by 10, changing activations and optimizers. Even data I input manually.
Can anyone tell me how to solve my simple problem. thx.
There are several problems in your code.
Number of data entries are very small compared to the NN model.
Y is represented as classes number and not as class vector. A regression model can be learnt on this but its a poor design choice.
output of softmax function is always between 0-1 .. as this is used your model only knows to spew out values between 0-1.
Here below is a bit better modified code:
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD
import numpy
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# split into input (X) and output (Y) variables
X = numpy.array([[0.5,1,1], [0.9,1,2], [0.8,0,1], [0.3,1,1], [0.6,1,2], [0.4,0,1], [0.9,1,7], [0.5,1,4], [0.1,0,1], [0.6,1,0], [1,0,0]])
y = numpy.array([[1],[1],[1],[2],[2],[2],[3],[3],[3],[0],[0]])
from keras.utils import np_utils
Y = np_utils.to_categorical(y, 4)
# print Y
# create model
model = Sequential()
model.add(Dense(3, input_dim=3, activation='relu'))
model.add(Dense(4, activation='softmax'))
# Compile model
# sgd = SGD(lr=0.1)
# model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
# Fit the model
model.fit(X, Y, nb_epoch=700)
# calculate predictions
predictions = model.predict(X)
predictions_class = predictions.argmax(axis=-1)
print(predictions_class)
Note I have used the softmax activation as the classes are mutually exclusive