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
Add Quickdraw Sketch RNN Dataset #361
Conversation
Thanks for dataset. You need to add fake_examples. |
I am also changing the number of shards per split going from 1-1-1 to 20-5-5, I will update the gist accordingly. |
@us How should fake examples work? Are they simply placeholders or should I add 3 complete .npz files? |
You can add |
Updated the dataset_info.json with the correct BibTeX citation. |
- Fix a bug due to rstrip - Add builtin conversion to from stroke-3 and stroke-5 - Update testing
One thing I have seen during testing is that if we want to be able to reproduce the technique of the original paper we should probably invert the notation for the end of the drawing. In the original paper, the authors pad each sketch with |
In following the content of the paper, the padding step aimed at making each label sequences of same length is added as part of the examples generation. - Fixed the python2 syntax error - Format respecting the code-style using yapf --style=chromium
Contrary to what said above I have moved the padding step to the examples generation, the final user will thus just need to use |
I have modified the preprocess step adding the stroke signaling the start of a sketch as they do in here. EDIT: 🤔 apparently the py2-tf2 test is failing. Also updated the dataset info since I have increased the training set shards from 20 to 30. |
Fixed an error in the padding function. The TF 2 Py2.7 Test will fail due to a known Keras issue. |
@mr-ubik still continue? |
I had stopped due to the issue with NumPy and Keras I had referenced earlier while I have been working on making sure the data format and pre-processing were accurately reflecting the one done in the paper. |
Did you open an issue by tagging this pr? |
The issue should be fixed now. I will look at the code next week and start pushing new updates again. ❤️ |
Okay! It'll be awesome :) |
@mr-ubik hey don't forget ! |
@us Just sorting through issues at work, contributions will resume ASAP |
Hi there! This PR looks great, is it still active? |
Hi @ageron! I actually had to stop working on it due to other priorities, but I'd like to resume it. It should probably be updated with the new API of In an internal fork of |
is this PR active |
dataset_info.json
Add the Quickdraw Dataset used to train Sketch RNN.
Close one of the TODOs of #337
Caveats: