pix2seq-pytorch

Unofficial implementation of the Pix2Seq paper

Different from the paper

  • image input size 1280
  • bin size 1280
  • LambdaLR scheduler used instead of LinearLR
  • resnet50 instead of resnet50d or resnet101
  • etc.

Dataset

Download first the coco2017 dataset and put it under the dataset folder.

- dataset
  - annotations
    - instances_train2017.json
    - instances_val2017.json
  - train2017
    - 000000000000.jpg
    - ...
  - val2017

Train

python train.py --config configs/pix2seq.yaml

GitHub

View Github