I have an autoencoder that has two output( decoded,pred_w), one output is the reconstructed input image and other one is a reconstructed binary image. I used sigmoid activation function in the last layer but the outputs are float number and I need the network label each pixel as 0 or 1. I attached my code here. could you please guide me what should I do to solve this problem? thanks.
from keras.layers import Input, Concatenate, GaussianNoise,Dropout
from keras.layers import Conv2D
from keras.models import Model
from keras.datasets import mnist
from keras.callbacks import TensorBoard
from keras import backend as K
from keras import layers
import matplotlib.pyplot as plt
import tensorflow as tf
import keras as Kr
import numpy as np
import pylab as pl
import matplotlib.cm as cm
import keract
from tensorflow.python.keras.layers import Lambda;
#-----------------building w train---------------------------------------------
w_main = np.random.randint(2,size=(1,4,4,1))
w_main=w_main.astype(np.float32)
w_expand=np.zeros((1,28,28,1),dtype='float32')
w_expand[:,0:4,0:4]=w_main
w_expand.reshape(1,28,28,1)
w_expand=np.repeat(w_expand,49999,0)
#-----------------building w validation---------------------------------------------
w_valid = np.random.randint(2,size=(1,4,4,1))
w_valid=w_valid.astype(np.float32)
wv_expand=np.zeros((1,28,28,1),dtype='float32')
wv_expand[:,0:4,0:4]=w_valid
wv_expand.reshape(1,28,28,1)
wv_expand=np.repeat(wv_expand,9999,0)
#-----------------building w test---------------------------------------------
w_test = np.random.randint(2,size=(1,4,4,1))
w_test=w_test.astype(np.float32)
wt_expand=np.zeros((1,28,28,1),dtype='float32')
wt_expand[:,0:4,0:4]=w_test
wt_expand.reshape(1,28,28,1)
#wt_expand=np.repeat(wt_expand,10000,0)
#-----------------------encoder------------------------------------------------
#------------------------------------------------------------------------------
wtm=Input((28,28,1))
image = Input((28, 28, 1))
conv1 = Conv2D(16, (3, 3), activation='relu', padding='same', name='convl1e')(image)
conv2 = Conv2D(32, (3, 3), activation='relu', padding='same', name='convl2e')(conv1)
conv3 = Conv2D(8, (3, 3), activation='relu', padding='same', name='convl3e')(conv2)
DrO1=Dropout(0.25)(conv3)
encoded = Conv2D(1, (3, 3), activation='relu', padding='same',name='reconstructed_I')(DrO1)
#-----------------------adding w---------------------------------------
#add_const = Kr.layers.Lambda(lambda x: x + Kr.backend.constant(w_expand))
#encoded_merged=Kr.layers.Add()([encoded,wtm])
add_const = Kr.layers.Lambda(lambda x: x + wtm)
encoded_merged = add_const(encoded)
encoder=Model(inputs=image, outputs= encoded_merged)
encoder.summary()
#-----------------------decoder------------------------------------------------
#------------------------------------------------------------------------------
#encoded_merged = Input((28, 28, 2))
deconv1 = Conv2D(16, (3, 3), activation='relu', padding='same', name='convl1d')(encoded_merged)
deconv2 = Conv2D(32, (3, 3), activation='relu', padding='same', name='convl2d')(deconv1)
deconv3 = Conv2D(8, (3, 3), activation='relu',padding='same', name='convl3d')(deconv2)
DrO2=Dropout(0.25)(deconv3)
decoded = Conv2D(1, (3, 3), activation='relu', padding='same', name='decoder_output')(DrO2)
#decoder=Model(inputs=encoded_merged, outputs=decoded)
#decoder.summary()
model=Model(inputs=image,outputs=decoded)
#----------------------w extraction------------------------------------
convw1 = Conv2D(16, (3,3), activation='relu', padding='same', name='conl1w')(decoded)
convw2 = Conv2D(32, (3, 3), activation='relu', padding='same', name='convl2w')(convw1)
convw3 = Conv2D(8, (3, 3), activation='relu', padding='same', name='conl3w')(convw2)
DrO3=Dropout(0.25)(convw3)
pred_w = Conv2D(1, (1, 1), activation='sigmoid', padding='same', name='reconstructed_W')(DrO3)
# reconsider activation (is W positive?)
# should be filter=1 to match W
w_extraction=Model(inputs=[image,wtm],outputs=[decoded,pred_w])
#----------------------training the model--------------------------------------
#------------------------------------------------------------------------------
#----------------------Data preparesion----------------------------------------
(x_train, _), (x_test, _) = mnist.load_data()
x_validation=x_train[1:10000,:,:]
x_train=x_train[10001:60000,:,:]
#
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_validation = x_validation.astype('float32') / 255.
x_train = np.reshape(x_train, (len(x_train), 28, 28, 1)) # adapt this if using `channels_first` image data format
x_test = np.reshape(x_test, (len(x_test), 28, 28, 1)) # adapt this if using `channels_first` image data format
x_validation = np.reshape(x_validation, (len(x_validation), 28, 28, 1))
#---------------------compile and train the model------------------------------
# is accuracy sensible metric for this model?
w_extraction.compile(optimizer='adadelta', loss={'decoder_output':'mse','reconstructed_W':'mse'}, metrics=['mae'])
w_extraction.fit([x_train,w_expand], [x_train,w_expand],
epochs=100,
batch_size=128,
validation_data=([x_validation,wv_expand], [x_validation,wv_expand]),
callbacks=[TensorBoard(log_dir='E:/tmp/AutewithW200', histogram_freq=0, write_graph=False)])
model.summary()
If you need this inside the model, you can use K.round() from keras.backend. Notice this will not be differentiable and will not be able to be used very well in training.
If you need just the results, you can simple define a threshold (usually 0.5) and:
binary_reslts = results > threshold
You can see the results by adding metrics that round the data.
Standard metrics for this could be "accuracy" or "categorical_accuracy". You you can define your own metrics like:
def diceMetric(yTrue, yPred):
yTrue = K.batch_flatten(yTrue)
yPred = K.batch_flatten(yPred)
#round
yPred = K.greater(yPred, 0.5)
yPred = K.cast(yPred, K.floatx())
intersection = yPred * yTrue
sum = yTrue + yPred
return (2*intersection + K.epsilon())/(sum + K.epsilon())
Metrics are added in compile:
model.compile(optimizer=..., loss=..., metrics = [diceMetric, 'categorical_accuracy'])
Metrics do not affect training, they're just feedback for you to know what's happening.