CODEWITHSUNDEEP
tensorflowkerasdeep-learning
user466534
user466534

Reputation:

Strange error while creating a convolution neural network

i want to create convolutional neural network model in keras, first of all i have imported all necessary library like this

from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import MaxPooling2D

than i have tried following model

model =Sequential()
model.add(Conv2D(filters=32,kernel_size=(5,5),padding='valid',input_shape=(1,28,28),activation='relu',data_format='channels_first'))
model.add(MaxPooling2D(2,2, dim_ordering='tf'))
moodel.add(Dropout(0.2))
model.add(Flattenn())
model.add(Dense(128,activation='relu'))
model.add(Dense(num_classes,activation='softmax'))
model.compile(loss='categorical_crossentropy' , optimizer='adam' , metrics=['accuracy' ])

but i have got following error :

TypeError: The added layer must be an instance of class Layer. Found: <tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7faaefc57438>

could you help me please to fix this error

Upvotes: 0

Views: 43

Answers (1)

Matus Dubrava
Matus Dubrava

Reputation: 14462

moodel.add(Dropout(0.2))

Typo - moodel -> model

model.add(Flattenn())

Typo - Flattenn -> Flatten

And you should use Convolution2D instead of Conv2D import.

from tensorflow.keras.layers import Convolution2D

model = Sequential()
model.add(Convolution2D(filters=32,...

Upvotes: 2

Related Questions