search

ying09 / TextFuseNet

A PyTorch implementation of "TextFuseNet: Scene Text Detection with Richer Fused Features".
MIT License
475 stars 122 forks source link

question about train synthetic data and funsd data #38

Open kbrajwani opened 3 years ago

kbrajwani commented 3 years ago

  1. I have tried to train the model on synthetic data (keras-ocr https://keras-ocr.readthedocs.io/en/latest/examples/end_to_end_training.html#generating-synthetic-data). I have 10000 background images. Till now i have trained for 25000 iterations with pre-trained weights of synth text model but not able to see any result so can you tell me how many iterations i have to train the model.

  2. I have also try training on https://guillaumejaume.github.io/FUNSD/download/ dataset. which is based on documents where the word is annotated. I have modified your code a little bit to train only on word level. I am training with pretrained ctw model weights. Following is my metrics file can you tell me its looks fine or I have done something wrong? metrics.txt

congjianting commented 3 years ago

@kbrajwani can you share the edited codes for trainning only on word level? i think many people will benefit from it.

kbrajwani commented 3 years ago

Currently my training is not going good and the code is also mess see below notebook if that can help you. https://colab.research.google.com/drive/1E-QdWS5bymwnLZPz8ZcmfsyLECqSS40E?usp=sharing