CODEWITHSUNDEEP
tensorflowkeras
johan bender
johan bender

Reputation: 53

Flatten function in Keras

Problem defining the NN architecture

I'm trying to create a CNN with Keras for the CIFAR-10 image dataset (https://keras.io/datasets/), but I can't get the Flatten function to work even though it appears in the Keras library: https://keras.io/layers/core/#flatten

Here is the error message: 

NameError                                 Traceback (most recent call last)
<ipython-input-9-aabd6bce9082> in <module>()
     12 nn.add(Conv2D(64, 3, 3, activation='relu'))
     13 nn.add(MaxPooling2D(pool_size=(2, 2)))
---> 14 nn.add(Flatten())
     15 nn.add(Dense(128, activation='relu'))
     16 nn.add(Dense(10, activation='softmax'))

NameError: name 'Flatten' is not defined

I'm using Jupyter running Python 2.7 and Keras 1.1.1. Below is the code for the NN:

from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.models import Sequential
from keras.layers import Dense, Activation

nn = Sequential()
nn.add(Conv2D(32, 3, 3, activation='relu', input_shape=(32, 32, 3)))

# Max-pool reduces the size of inputs, by taking the largest pixel-value from a grid
nn.add(MaxPooling2D(pool_size=(2, 2)))
nn.add(Conv2D(64, 3, 3, activation='relu'))
nn.add(MaxPooling2D(pool_size=(2, 2)))
nn.add(Flatten())
nn.add(Dense(128, activation='relu'))
nn.add(Dense(10, activation='softmax'))

Thanks in advance,

-Johan B.

Upvotes: 4

Views: 21907

Answers (1)

Vadim
Vadim

Reputation: 4519

try to import the layer first:

from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten

nn = Sequential()
nn.add(Conv2D(32, 3, 3, activation='relu', input_shape=(32, 32, 3)))

# Max-pool reduces the size of inputs, by taking the largest pixel-value from a grid
nn.add(MaxPooling2D(pool_size=(2, 2)))
nn.add(Conv2D(64, 3, 3, activation='relu'))
nn.add(MaxPooling2D(pool_size=(2, 2)))
nn.add(Flatten())
nn.add(Dense(128, activation='relu'))
nn.add(Dense(10, activation='softmax'))

Upvotes: 5

Related Questions