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

Jupyter notebook eval #12

Closed
wants to merge 39 commits into from
Closed

Jupyter notebook eval #12

wants to merge 39 commits into from

Conversation

thejerrytan
Copy link
Collaborator

Added a jupyter notebook to visualize data, and do sanity check for trained models.

This is not ready to be merged yet.

I am including it first because it may be helpful to some of you who wants to evaluate your trained DL models.

Going to use it to generate images for README later also.

I think i did sth stupid, i commited Vatsal's dataset - TFrecord files into the repo, 266MB, ~ 1000 files. Let me know if this is bloating up your githistory and i can rewrite the githistory.

swwelch and others added 30 commits December 7, 2017 17:32
Adding monkey patching fix suggested on forums
Adding code to do  waypoint visualizations
fix: correcting some typos in creating waypoints objects
Updates and error fixes to pid.py.
…tudents who want to use different networks for each.
…tudents who want to use different networks for each.
* Implemented simple red light classifier and interface to change the classifier

* minor refactoring

* updated the thresholds and modified the message name

* updated review comments

* updated thresholds for stopping and red light size

* Update waypoint_updater.py

Updated the comment in line with the implementation from 2 to 4 for number of stopping ahead wapoints
@thejerrytan thejerrytan requested review from ser94mor, pkorivi and Karthikeya108 and removed request for pkorivi January 23, 2019 12:34
Copy link
Owner

@ser94mor ser94mor left a comment

Choose a reason for hiding this comment

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

Indeed, please, rewrite the commit history. We should not include into this repo any dataset.

@ser94mor
Copy link
Owner

This pull request introduces 1 alert when merging 83de649 into ed7da4b - view on LGTM.com

new alerts:

  • 1 for Unused local variable

Comment posted by LGTM.com

@thejerrytan thejerrytan force-pushed the jupyter-notebook-eval branch from 83de649 to 5111001 Compare January 23, 2019 14:41
@thejerrytan
Copy link
Collaborator Author

Indeed, please, rewrite the commit history. We should not include into this repo any dataset.

this is what i did:
git filter-branch --tree-filter 'rm -rf path/to/your/file' HEAD
git push --force origin jupyter-notebook-eval

in order to remove those files from commit history.

Now to get the validation set on your own:

  1. download from this link: https://github.com/coldKnight/TrafficLight_Detection-TensorFlowAPI#get-the-dataset
  2. copy paste to ./data folder
  3. the downloaded file name is dataset-sdcnd-capstone.zip. unzip.
    root folder is dataset-sdcnd-capstone
  4. assuming you are at projectRoot/data: mv dataset-sdcnd-capstone/data ../validation

@ser94mor
Copy link
Owner

ser94mor commented Jan 23, 2019

Ah, something bad happens with the diff. Could you create a new branch from master and put an eval.ipynb file there and create a new PR? Looks like not only your commit was rewritten.

@thejerrytan thejerrytan deleted the jupyter-notebook-eval branch January 23, 2019 17:52
@thejerrytan
Copy link
Collaborator Author

@Aoool this branch is closed, please refer to #14 for the new one.

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.

9 participants