fchollet

from keras import backend
from keras.backend import numpy_backend
import numpy as np
import tensorflow as tf


class NPTF(object):

  def __getattr__(self, name):
    if name in dir(numpy_backend) and name in dir(backend):

fchollet

############################################################################
# Case 1: inserting non-layer ops into a graph of layers
############################################################################

input_1 = tf.keras.Input(shape=(3,))
x = tf.keras.layers.Dense(4)(input_1)
output = tf.exp(x)  # !!
model = tf.keras.Model(input_1, output)

############################################################################

fchollet

import keras
import numpy as np

timesteps = 60
input_dim = 64
samples = 10000
batch_size = 128
output_dim = 64

# Test data.

fchollet

"""Downsized version of Xception, without residual connections.
"""
from __future__ import print_function
from __future__ import absolute_import

from keras.models import Model
from keras.layers import Dense
from keras.layers import Input
from keras.layers import BatchNormalization
from keras.layers import Activation

fchollet

from keras.models import Sequential
from keras.layers import Dense

x, y = ...
x_val, y_val = ...

# 1-dimensional MSE linear regression in Keras
model = Sequential()
model.add(Dense(1, input_dim=x.shape[1]))
model.compile(optimizer='rmsprop', loss='mse')

fchollet

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats

fchollet

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats

fchollet

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats

fchollet

'''Functional Keras is a more functional replacement for the Graph API.
'''

###################
# 2 LSTM branches #
###################
a = Input(input_shape=(10, 32))  # output is a TF/TH placeholder, augmented with Keras attributes
b = Input(input_shape=(10, 32))
encoded_a = LSTM(32)(a)  # output is a TF/TH tensor
encoded_b = LSTM(32)(b)

fchollet

import theano
from keras.models import Sequential
from keras.layers.core import Dense, Activation

X_train, y_train = ... # load some training data
X_batch = ... # a batch of test data

# this is your initial model
model = Sequential()
model.add(Dense(20, 64))