ValueError in input to CNN

Question

making a model for image segmentation using keras in python but getting error at first layer which is Conv2D. In code this line is as:

model.add(Conv2D(32,kernel_size=(3, 3),padding='same',input_shape=(1,500,366,3)))

but getting following error:

ValueError: Input 0 is incompatible with layer conv2d_1: expected ndim=4, found ndim=5

I am making this model initially for one image.

PS: input_shape(samples=1,width=500,height=366,channels=3)

Manpreet kaur
– Manpreet kaur

2018-03-14 10:55:54 +00:00
Commented Mar 14, 2018 at 10:55 — Manpreet kaur
– Manpreet kaur, Commented Mar 14, 2018 at 10:55

Ioannis Nasios · Accepted Answer · 2018-03-14 10:59:01Z

1

try removing your first dimension like this:

model.add(Conv2D(32,kernel_size=(3, 3),padding='same',input_shape=(500,366,3)))

answered Mar 14, 2018 at 10:59

Ioannis Nasios

8,5474 gold badges41 silver badges59 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Ioannis Nasios Over a year ago

try model.add(Conv2D(32,kernel_size=(3, 3),padding='same',input_shape=(366,500,3)))

Manpreet kaur Over a year ago

But when I am adding the line model.fit(data,output,batch_size,epochs) it gives error: ValueError: Error when checking target: expected max_pooling2d_1 to have shape (None, 183, 250, 32) but got array with shape (1, 366, 500, 3).....that is it's giving error on last layer ... ......Maybe error is somewhere else

Collectives™ on Stack Overflow

ValueError in input to CNN

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related