Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update to installation procedure #58

Open
wants to merge 5 commits into
base: kinetic-devel
Choose a base branch
from

Conversation

ben-greenberg
Copy link
Contributor

Addition of details to the installation procedure. The most important note is to install the correct versions of Lasagne and Theano.

@jrgnicho
Copy link
Contributor

@ben-greenberg thanks for submitting this. I'll be reviewing it soon.

@@ -15,6 +15,7 @@
2. Verify robot controller
Run the robot execution node and verify that the robot arm and rail joint are moved to the home position
```
pip install kitchen
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't this step be listed under convolutional neural network installation section?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I believe that I only got the error about missing the kitchen package when I tried to run the test_robot_execution.py script, that's why I put the installation of it prior. I think this would probably be more appropriate in the installation section of the main README if its required to run the base application (with or without the CNN)

@@ -3,12 +3,18 @@ For using Correspondence Grouping method in object recognition:

For using convolutional neural network method in object recognition:
1. Make sure your computer has Nvidia GPU;
lspci | grep VGA

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What message should we see if there's a valid GPU?

@@ -36,6 +37,8 @@
- This step will also bring up the individual nodes for tool planning, trajectory planning,
perception and robot execution, each in its own terminal window (don't close the windows).

- Run the CNN script in a new window as follows:
THEANO_FLAGS='floatX=float32' rosrun gilbreth_perception recognition_cnn.py
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The application_run.launch file step above runs the recognition_cnn.py node so it's not necessary to run it a second time. Therefore, the right procedure should probably start with the THEANO_FLAGS environment variable declaration followed by the launch file.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

When I start up using only the application_run.launch file I get the following error: "[recognition_cnn-6] process has finished cleanly"

When I run the recognition_cnn.py node seperately it does not shut down. I'm not sure why this is but it consistently works.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants