why use "batch_squash = tf.divide(batch_x, 255.)" rather than just batch_x

www0wwwjs1 / Matrix-Capsules-EM-Tensorflow

A Tensorflow implementation of CapsNet based on paper Matrix Capsules with EM Routing

Apache License 2.0

218 stars 83 forks source link

Open 898582324 opened 5 years ago

898582324 commented 5 years ago

I try to replace the batch_squash with batch_x, and the reconstruct loss going to very large. Why we can not training with original MNIST data?