gluon
Here are 181 public repositories matching this topic...
resuming training
How do i resume training for text classification?
-
Updated
Aug 13, 2019 - Jupyter Notebook
Well, Gumbel Distribution is magical. Basically, given a sequence of K logits, i.e., "\log a_1, \log a_2, ..., \log a_K" and K independent gumbel random variables, i.e., "g_1, g_2, ..., g_K". We have
\argmax_i \log a_i + g_i ~ Categorical({a_i / sum(a)})
This gives you a very simple way to sampl
-
Updated
Oct 15, 2020 - Rust
-
Updated
Oct 17, 2020 - Python
-
Updated
Sep 11, 2020 - Python
-
Updated
Sep 5, 2020 - Jupyter Notebook
-
Updated
Oct 16, 2020 - Python
-
Updated
Sep 9, 2020 - Jupyter Notebook
-
Updated
Aug 24, 2020 - Jupyter Notebook
-
Updated
Oct 17, 2020 - C
-
Updated
Apr 14, 2020 - Python
Package
@apollo-elements/create
Description
npm init @apollo-elements -- component should allow for creating components in subdirs with dashes in the name
Steps To Reproduce
- run
-
Updated
Oct 2, 2020 - Jupyter Notebook
-
Updated
Sep 27, 2020 - C#
-
Updated
Mar 27, 2020 - Python
-
Updated
Nov 20, 2017 - Jupyter Notebook
-
Updated
Oct 15, 2020 - Jupyter Notebook
-
Updated
Aug 21, 2018 - Python
-
Updated
Jun 12, 2019 - Python
-
Updated
Apr 16, 2020 - Python
-
Updated
Feb 23, 2020 - Python
-
Updated
Dec 24, 2017 - Jupyter Notebook
-
Updated
Feb 28, 2018 - Jupyter Notebook
-
Updated
Mar 12, 2020 - Jupyter Notebook
Improve this page
Add a description, image, and links to the gluon topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the gluon topic, visit your repo's landing page and select "manage topics."


Hi, thanks for the great code!
I wonder do you have plans to support resuming from checkpoints for classification? As we all know, in terms of training ImageNet, the training process is really long and it can be interrupted somehow, but I haven't notice any code related to "resume" in
scripts/classification/train_imagenet.py.Maybe @hetong007 ? Thanks in advance.