Commit 013dca68 authored by Toby Boyd's avatar Toby Boyd Committed by GitHub
Browse files

Merge pull request #1967 from s-gupta/patch-1

Update README.md.
parents 7dde2e2f a12bc1cd
...@@ -22,7 +22,7 @@ citing the following paper: ...@@ -22,7 +22,7 @@ citing the following paper:
### Contents ### Contents
1. [Requirements: software](#requirements-software) 1. [Requirements: software](#requirements-software)
2. [Requirements: data](#requirements-data) 2. [Requirements: data](#requirements-data)
3. [Test Pre-trained Models](#test-pre_trained-models) 3. [Test Pre-trained Models](#test-pre-trained-models)
4. [Train your Own Models](#train-your-own-models) 4. [Train your Own Models](#train-your-own-models)
### Requirements: software ### Requirements: software
...@@ -46,7 +46,8 @@ citing the following paper: ...@@ -46,7 +46,8 @@ citing the following paper:
``` ```
2. Install [Tensorflow](https://www.tensorflow.org/) inside this virtual 2. Install [Tensorflow](https://www.tensorflow.org/) inside this virtual
environment. Typically done with `pip install --upgrade tensorflow-gpu`. environment. You will need to use one of the latest nightly builds
(see instructions [here](https://github.com/tensorflow/tensorflow#installation)).
3. Swiftshader: We use 3. Swiftshader: We use
[Swiftshader](https://github.com/google/swiftshader.git), a CPU based [Swiftshader](https://github.com/google/swiftshader.git), a CPU based
...@@ -99,8 +100,7 @@ citing the following paper: ...@@ -99,8 +100,7 @@ citing the following paper:
`data/README.md` `data/README.md`
### Test Pre-trained Models ### Test Pre-trained Models
1. Download pre-trained models using 1. Download pre-trained models. See `output/README.md`.
`scripts/scripts_download_pretrained_models.sh`
2. Test models using `scripts/script_test_pretrained_models.sh`. 2. Test models using `scripts/script_test_pretrained_models.sh`.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment