DeepLayout
DeepLayout copied to clipboard
PyTorch implementation of "LayoutTransformer: Layout Generation and Completion with Self-attention" to appear in ICCV 2021
Hi, Currently the PubLayNet example generates layouts of size 256x256, a fixed square aspect ratio. How do I modify the representation to make it support different aspect ratios during inference?
Thanks for the excellent work! Do you have plan to provide the training code on RICO datasets and related pre-trained models?
Thanks for releasing your code. And could you please tell me how to generate the 3D shape? I would be grateful!!! :-)
Hello, thank you for sharing this code. I used the code with no changes and when I saw the visualization of the generated boxes are not really good.  ...
Hi~ I've read your paper and the code, and I am little confused about some details. Firstly, the coordinates of bounding boxes are discretized and the vocabulary for layouts contains...
Thanks for your repo. I used the default training code of publayout, and trained for 10 epoches. The final training loss reaches around 1.27. epoch 10 iter 5245: train loss...
Excuse me, where is code of evaluation(overlap,coverage) index of experimental results?
Hi authors (@kampta @abhijeet00 ) , The paper mentions that "We use the official validation split from COCO as test set in our experiments". Can you please clarify if you...