Skip to content

Commit

Permalink
update README
Browse files Browse the repository at this point in the history
Former-commit-id: 54f1f1f7af6d73b804a675777fe92c1dbd9d187e
  • Loading branch information
Javi Ribera committed Feb 13, 2019
1 parent d2ac92b commit ec0a64c
Showing 1 changed file with 11 additions and 12 deletions.
23 changes: 11 additions & 12 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,17 +11,18 @@


## Using Conda (recommended) <a name="conda"></a>

<a name="installation"></a>
### Installation

<ol>
<li>Download and install Anaconda as described in <a href="https://docs.anaconda.com/anaconda/install/">https://docs.anaconda.com/anaconda/install</a></li>
<li>Get the code from this git repository (or download the tool from <a href="https://github.rcac.purdue.edu/jprat/object-locator/archive/v1.3.1.zip">this link</a>, and decompress the zip).
<li>(Optional) Check out a non-development version (such as `git checkout v1.3.1`).
<li>Clone this repository
<li>(Optional) Check out a stable version (such as `git checkout 1.5.0`) shown in CHANGELOG.html
<li>Open the terminal in Linux/MacOS. In Windows, open the Anaconda Prompt.</li>
<li>"cd" into the decompressed directory</li>
<li>Download the trained models from <a href="https://lorenz.ecn.purdue.edu/~jprat/plant_locator/checkpoints">here</a> and put them in
<pre>object-locator-1.3.1/object-locator/checkpoints</pre>
<li>"cd" into the decompressed directory or the cloned repo</li>
<li>Download the trained models from <a href="https://lorenz.ecn.purdue.edu/~jprat/plant_locator/checkpoints">here</a> (or provided by us) and put them in
<pre>object-locator-1.5.0/object-locator/checkpoints</pre>


<li>Install the dependencies:</li>
Expand Down Expand Up @@ -96,10 +97,11 @@ python -m object-locator.locate \
<a name="train"></a>

#### Train (optional)
If you do not want to use one of the provided pretrained models, you can train your own model. Run the following command to get the full help message on how to train, with an explanation of all available training parameters.
You need to have a NVIDIA card and CUDA 8 installed to train your own model. This depends greatly on the specific model of your NVIDIA card and operating system.
You can use one of the provided pretrained models, or you can train your own model.
You need to have a NVIDIA card and CUDA 8 installed to train your own model.
This depends greatly on the specific model of your NVIDIA card and operating system.

Run this to get help (usage instructions):
Run this to show instructions on how to train:
<pre>
python -m object-locator.train -h
</pre>
Expand Down Expand Up @@ -136,10 +138,7 @@ conda env remove --name object-locator
</pre>

<a name="docker"></a>
## Using Docker


(only for expert users)
## Using Docker (experts only)

1. Install docker-ce as described in https://docs.docker.com/install/linux/docker-ce/ubuntu/#set-up-the-repository
2. Install NVIDIA drivers
Expand Down

0 comments on commit ec0a64c

Please sign in to comment.