msdnet
msdnet copied to clipboard
dmpelt
Python implementation of the Mixed-Scale Dense Convolutional Neural Network
Hi, i have a few questions about the normalization in Example 01: train a network for regression. a. Is it correct that only the training data is normalized in this...
https://stats.stackexchange.com/a/336077/293880
PR #14 removed openmp support for windows because of build problems. Hopefully it is possible to re-enable in the future, but I need to figure out what the underlying cause...
Changes proposed in this pull request: * update versions of python, numba and numpy * fix warnings from numpy and scikit Fixes issue #27 (or at least, I cannot reproduce...
**Describe the bug** [Example 01: Train a network for regression](https://dmpelt.github.io/msdnet/auto_examples/train_regr.html#sphx-glr-download-auto-examples-train-regr-py) and [Example 05: Train a network for regression (tomography)](https://dmpelt.github.io/msdnet/auto_examples/train_regr_tomography.html#sphx-glr-auto-examples-train-regr-tomography-py) fail with ```AttributeError: 'NoneType' object has no attribute 'deriv'``` It looks...
Changes proposed in this pull request: * np.int changed to int i * np.Inf changed to np.inf * removed a keyword argument from skimage.transform.rescale * added requirements.txt Fixes issue *...
