File tree Expand file tree Collapse file tree
Expand file tree Collapse file tree Original file line number Diff line number Diff line change 218218# ----
219219#
220220# In this tutorial we will use the `Celeb-A Faces
221- # dataset <https ://mmlab.ie.cuhk.edu.hk/projects/CelebA.html>`__ which can
221+ # dataset <http ://mmlab.ie.cuhk.edu.hk/projects/CelebA.html>`__ which can
222222# be downloaded at the linked site, or in `Google
223223# Drive <https://drive.google.com/drive/folders/0B7EVK8r0v71pTUZsaXdaSnZBZzg>`__.
224224# The dataset will download as a file named *img_align_celeba.zip*. Once
283283#
284284# From the DCGAN paper, the authors specify that all model weights shall
285285# be randomly initialized from a Normal distribution with mean=0,
286- # stdev=0.2 . The ``weights_init`` function takes an initialized model as
286+ # stdev=0.02 . The ``weights_init`` function takes an initialized model as
287287# input and reinitializes all convolutional, convolutional-transpose, and
288288# batch normalization layers to meet this criteria. This function is
289289# applied to the models immediately after initialization.
You can’t perform that action at this time.
0 commit comments