Nope.... FastAI 1.0.52 + doesn't work either.

Glitches are introduced to image rendering.  Doh!
This commit is contained in:
Jason Antic
2019-08-28 17:32:10 -07:00
committed by GitHub
parent e631313223
commit 1fd417fb67
+1 -1
View File
@@ -275,7 +275,7 @@ The images in this folder have been removed because they were using Git LFS and
#### Installation Details
This project is built around the wonderful Fast.AI library. Prereqs, in summary:
* **Fast.AI 1.0.52** (and its dependencies)
* **Fast.AI 1.0.51** (and its dependencies)
* **Jupyter Lab** `conda install -c conda-forge jupyterlab`
* **Tensorboard** (i.e. install Tensorflow) and **TensorboardX** (https://github.com/lanpa/tensorboardX). I guess you don't *have* to but man, life is so much better with it. FastAI now comes with built in support for this- you just need to install the prereqs: `conda install -c anaconda tensorflow-gpu` and `pip install tensorboardX`
* **ImageNet** Only if you're training, of course. It has proven to be a great dataset for my purposes. http://www.image-net.org/download-images