Quantcast
Channel: Incompatible shapes: [128,1] vs. [128,3,3] - Stack Overflow
Browsing latest articles
Browse All 3 View Live

Answer by Gi Yeon Shin for Incompatible shapes: [128,1] vs. [128,3,3]

I think there are two problems in your code.At first, please check the shape of train_labels.Incompatible shapes error would appear if the shapes of tensor are wrong. I think that shape of [128, 1]...

View Article


Answer by Abhishek Verma for Incompatible shapes: [128,1] vs. [128,3,3]

Put a Flatten layer before the last Dense layer. Because you are not doing that, that is why the tensor is not reduced to a single dimension tensor before the layer that gives you the class.It is a...

View Article


Incompatible shapes: [128,1] vs. [128,3,3]

I am trying to create a CNN to classify the SVHN dataset but run into an incompatible shape error when creating my model: Incompatible shapes: [128,3,3,10] vs. [128,1]. How do I fix it? model =...

View Article
Browsing latest articles
Browse All 3 View Live


<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>