CODEWITHSUNDEEP
tensorflowkeras
kiseliu
kiseliu

Reputation: 83

I write my program with following the steps of Building Autoencoders in Keras in Keras blog, but it errors as follows:

    callbacks=[TensorBoard(log_dir='/Users/lyj/Programs/KiseliuGit/DeepLearning/tmp/autoencoder')])
  File "/Library/Python/2.7/site-packages/keras/callbacks.py", line 457, in __init__
raise Exception('TensorBoard callback only works '
Exception: TensorBoard callback only works with the TensorFlow backend.

Why? I absolutely followed the steps, here's my program:

#coding:utf-8
from keras.layers import Input, Dense, Convolution2D, MaxPooling2D, UpSampling2D
from keras.models import Model
from keras.datasets import mnist
import numpy as np
from keras.callbacks import TensorBoard

input_img = Input(shape=(1, 28, 28))
x = Convolution2D(16, 3, 3, activation='relu', border_mode='same')(input_img)
x = MaxPooling2D((2, 2), border_mode='same')(x)
x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(x)
x = MaxPooling2D((2, 2), border_mode='same')(x)
x = Convolution2D(8 ,3, 3, activation='relu', border_mode='same')(x)
encoded = MaxPooling2D((2,2), border_mode='same')(x)

x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(encoded)
x = UpSampling2D((2,2))(x)
x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(x)
x = UpSampling2D((2,2))(x)
x = Convolution2D(16, 3, 3, activation='relu')(x)
x = UpSampling2D((2,2))(x)
decoded = Convolution2D(1, 3, 3, activation='sigmoid', border_mode='same')(x)

autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')

(x_train, _), (x_test, _) = mnist.load_data()

x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_train = np.reshape(x_train, (len(x_train), 1, 28, 28))
x_test = np.reshape(x_test, (len(x_test), 1, 28, 28))

autoencoder.fit(x_train, x_test, nb_epoch=50, batch_size=128, shuffle=True,validation_data=(x_test, x_test),
            callbacks=[TensorBoard(log_dir='/Users/kiseliu/DeepLearning/tmp/autoencoder')])

And I inputed the command "tensorboard --logdir=/Users/kiseliu/DeepLearning/tmp/autoencoder"in cmd tools before I run this program.

Upvotes: 1

Views: 383

Answers (1)

jozi
jozi

Reputation: 2851

Change your backend keras from theano to tnesorflow from .keras.json file

Upvotes: 2

Related Questions