### Keras on TensorFlow in GCP

#### by allenlu2007

先說結論：如何在 GCP 上 install keras 同時可以 visualize 結果。

Method I: Anaconda + tensorflow + keras (on VNC): tf 是 virtue machine

(a) 最簡單的方式是 install anaconda -> tensorflow (見前文）

(b) 在來只要 > conda install keras 就搞定。

另外如果需要 display, 建議用 VNC 搭配。同樣見前文。

VNC client display 結果如下。python code 見下文。

(Server: run > vncserver) if need restart vncserver kill :1 then rerun vncserver)

Method II:

(a) Google cloud shell + 8081 web preview + tensorflow (default) + Jupyter notebook (default). (見前文)

(b) 唯一的問題是如何 install keras in Jupyter notebook => 在 jupyter notebook 用

! pip install keras (Bingo!)

=> 後台好像變成 theano.

=> 不過執行好像自動切回 tensorflow!

**Keras_autoencoder.ipynb**

```
!pip install keras
```

```
from keras.layers import Input, Dense
from keras.models import Model
# this is the size of our encoded representations
encoding_dim = 32 # 32 floats -> compression of factor 24.5, assuming the input is 784 floats
# this is our input placeholder
input_img = Input(shape=(784,))
# "encoded" is the encoded representation of the input
encoded = Dense(encoding_dim, activation='relu')(input_img)
# "decoded" is the lossy reconstruction of the input
decoded = Dense(784, activation='sigmoid')(encoded)
# this model maps an input to its reconstruction
autoencoder = Model(input_img, decoded)
```

```
# this model maps an input to its encoded representation
encoder = Model(input_img, encoded)
```

```
# create a placeholder for an encoded (32-dimensional) input
encoded_input = Input(shape=(encoding_dim,))
# retrieve the last layer of the autoencoder model
decoder_layer = autoencoder.layers[-1]
# create the decoder model
decoder = Model(encoded_input, decoder_layer(encoded_input))
```

```
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
```

```
from keras.datasets import mnist
import numpy as np
(x_train, _), (x_test, _) = mnist.load_data()
```

```
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:])))
x_test = x_test.reshape((len(x_test), np.prod(x_test.shape[1:])))
print(x_train.shape)
print(x_test.shape)
```

```
autoencoder.fit(x_train, x_train,
epochs=50,
batch_size=256,
shuffle=True,
validation_data=(x_test, x_test))
```

```
# encode and decode some digits
# note that we take them from the *test* set
encoded_imgs = encoder.predict(x_test)
decoded_imgs = decoder.predict(encoded_imgs)
```

```
# use Matplotlib (don't ask)
import matplotlib.pyplot as plt
n = 10 # how many digits we will display
plt.figure(figsize=(20, 4))
for i in range(n):
# display original
ax = plt.subplot(2, n, i + 1)
plt.imshow(x_test[i].reshape(28, 28))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
# display reconstruction
ax = plt.subplot(2, n, i + 1 + n)
plt.imshow(decoded_imgs[i].reshape(28, 28))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
plt.show()
```

Advertisements