search

ritwik12 / Celestial-bodies-detection

TensorFlow Image Classifier that can be used to classify whether an image is of a Planet (Earth, Mercury, Mars, etc), Galaxy (Spiral, Elliptical, Irregular), Satellites, Comets, Etc.
https://celestial-bodies-detection.herokuapp.com
GNU General Public License v3.0
84 stars 59 forks source link

Add test cases #56

Open ritwik12 opened 4 years ago

ritwik12 commented 4 years ago

We need more test cases to make our Model better while receiving PRs. Test cases can be then included as part of Travis.

shawngonsalves commented 4 years ago

Hello! I would like to contribute to this project! But I am new to the open-source contribution, can you help me through the process?

ritwik12 commented 4 years ago

@shawngonsalves Hey, thanks for taking an interest. This project is mainly a Deep Learning Model. Part of it is to train and another is to evaluate. It will be good to have test cases for the evaluation part. Please look at the code in hub/examples/image_retraining/label_image.py and write test cases for that.

Shreya-Pathak commented 4 years ago

Hi! Is this issue open? I would like to work on it.

ritwik12 commented 4 years ago

@Shreya-Pathak Yep, this is open. Please go ahead!!

Shreya-Pathak commented 4 years ago

I have increased the test_data for each of the classes and raised a PR. I obtained the images via Google search. Is there anything else to do?

ritwik12 commented 4 years ago

@Shreya-Pathak I have replied on the PR itself. Please take a look.

Rahul-3000 commented 4 years ago

hey, I m new to open source and want to contribute to this project can anyone help me, please.

ritwik12 commented 4 years ago

@Rahul-3000 Hey, Thanks for taking interest in this. Let me know what you need help with.

Rahul-3000 commented 4 years ago

@ritwik12 Hi, can you guide me how can I contribute i know python, cpp and html css

ritwik12 commented 4 years ago

@Rahul-3000 For this you need to have some Tensorflow and Deep Learning knowledge so that we can cover all the cases of test cases for the evaluation part or hub/examples/image_retraining/label_image.py

ritwik12 commented 4 years ago

If you can go through the hub/examples/image_retraining/label_image.py and understand how it is working then we can write better test cases.

AkshatGadhwal commented 3 years ago

Hii @ritwik12, I am new to open source and looking for the issues labeled "good first issue". Can you help me with understanding this issue? exactly where do I have to make the changes?

ritwik12 commented 3 years ago

@AkshatGadhwal As of now, we have limited test cases. For this project to work better. We should cover up the edge cases where it can break and run those as part of the PR using Travis for every new patch of code that comes in.