Can the Keras deal with input images with different size? For example, in the fully convolutional neural network, the input images can have any size. However, we need to specify the input shape when we create a network by Keras. Therefore, how can we use Keras to deal with different input size without resizing the input images to the same size? Thanks for any help.
3 Answers
Yes. Just change your input shape to shape=(n_channels, None, None). Where n_channels is the number of channels in your input image.
I'm using Theano backend though, so if you are using tensorflow you might have to change it to (None,None,n_channels)
You should use:
input_shape=(1, None, None)
None in a shape denotes a variable dimension. Note that not all layers will work with such variable dimensions, since some layers require shape information (such as Flatten). https://github.com/fchollet/keras/issues/1920
For example, using keras's functional API your input layer would be:
For a RGB dataset
inp = Input(shape=(3,None,None)) For a Gray dataset
inp = Input(shape=(1,None,None)) 6 Comments
user288609
Hi maz, I am having exactly the same problem. According to your suggestions, does it mean I can use images with different sizes for training, and similarly, I can predict segmenations for images with different size.
maz
Never tried training with different image sizes, but ideally it should work. In prediction, though, i have tried it and it works (ymmv of course). Worst case scenario you would have to feed in batches of same size images.
bob
Specifying
input_shape = c(None, None, 3) did not work in keras. It resulted in an error: Error in normalize_shape(input_shape) : object 'None' not found Sarvagya Gupta
I get the following error:
ValueError: The channel dimension of the inputs should be defined. Found `None`. What do you recommend?
Jorge M. Londoño P.
Actually, pay attention to the data_format parameter of your layer. If 'channels_first', then use (n_channels,None,None), or if 'channels_last' then use (None,None,n_channels)
|
Implementing arbitrarily sized input arrays with the same computational kernels can pose many challenges - e.g. on a GPU, you need to know how big buffers to reserve, and more weakly how much to unroll your loops, etc. This is the main reason that Keras requires constant input shapes, variable-sized inputs are too painful to deal with.
This more commonly occurs when processing variable-length sequences like sentences in NLP. The common approach is to establish an upper bound on the size (and crop longer sequences), and then pad the sequences with zeros up to this size.
(You could also include masking on zero values to skip computations on the padded areas, except that the convolutional layers in Keras might still not support masked inputs...)
I'm not sure if for 3D data structures, the overhead of padding is not prohibitive - if you start getting memory errors, the easiest workaround is to reduce the batch size. Let us know about your experience with applying this trick on images!
Just use None while specifying input shape. But I still do not know how to pass different-shaped images into fit function.
2 Comments
aaossa
This is already explained in the top voted answer I think
Усердный бобёр
@aaossa yes it is.