0
$\begingroup$

The shapes of

  • x_train=(514, 256), y_train=(514,)
  • x_test=(254, 256), y_test=(254,)

I have 256 features and 770 samples of which 514 is training and 254 is testing.

I just want to fit a basic sequential model but having difficulty in defining the input shape.

Any help on this please

model1=Sequential()
### first layer
model1.add(Dense(100,input_shape=(256,)))
model1.add(Activation('relu'))
model1.add(Dropout(0.5))
### second layer
model1.add(Dense(200))
model1.add(Activation('relu'))
model1.add(Dropout(0.5))
### third layer
model1.add(Dense(100))
model1.add(Activation('relu'))
model1.add(Dropout(0.5))

### final layer
model1.add(Dense(4))
model1.add(Activation('softmax'))
```
Improve this question
$\endgroup$
1
  • 1
    $\begingroup$ Hi Srikanth, welcome to datascience stackexchange. Can you be more specific as to what error you're seeing, and when, as well as what problem you're trying to solve? Your code is syntactically correct, but it's not clear what you think it should do. Also, your title mentions CNN, but your model code is strictly using dense fully connected layers. $\endgroup$
    – brewmaster321
    Aug 3 at 15:04

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.