gluon
Here are 183 public repositories matching this topic...
resuming training
How do i resume training for text classification?
-
Updated
Aug 13, 2019 - Jupyter Notebook
Description
We should use the official mxnet batchify functions to implement our own batchify functions. However, since we'd like to later support other frameworks, we should still keep our own batchify.py. We can change it to call MXNet implementations.
MXNet batchify: https://github.com/apache/incubator-mxnet/blob/master/python/mxnet/gluon/data/batchify.py
GluonNLP batchify: https://gi
-
Updated
Nov 15, 2020 - Rust
-
Updated
Nov 21, 2020 - Python
-
Updated
Dec 2, 2020 - Python
-
Updated
Oct 22, 2020 - Jupyter Notebook
-
Updated
Oct 27, 2020 - Jupyter Notebook
-
Updated
Nov 25, 2020 - Python
-
Updated
Aug 24, 2020 - Jupyter Notebook
-
Updated
Dec 1, 2020 - C
-
Updated
Apr 14, 2020 - Python
The generator currently outputs TypeScript projects only. It should have an option to output JavaScript projects.
This could be accomplished without duplicating code by the following steps
- If the TypeScript option is selected, continue as normal
- If the JavaScript option is selected, run all the same steps as the TypeScript generator, but add the following steps afterwards:
- Run
-
Updated
Oct 23, 2020 - Jupyter Notebook
-
Updated
Mar 27, 2020 - Python
-
Updated
Oct 26, 2020 - C#
-
Updated
Nov 20, 2017 - Jupyter Notebook
-
Updated
Dec 2, 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.