import streamlit as st from apps.utils import read_markdown from .streamlit_tensorboard import st_tensorboard, kill_tensorboard from .utils import Toc def app(state=None): #kill_tensorboard() toc = Toc() st.info("Welcome to our Multilingual-VQA demo. Please use the navigation sidebar to move to our demo, or scroll below to read all about our project. 🤗 In case the sidebar isn't properly rendered, please change to a smaller window size and back to full screen.") st.header("Table of Contents") toc.placeholder() toc.header("Introduction and Motivation") st.info("**News**: Two days back, a paper using CLIP-Vision and BERT has been posted on arXiv! The paper uses LXMERT objectives and achieves 80% on the English VQAv2 dataset. It would be interesting to see how it performs on our multilingual dataset. Check it out here: https://arxiv.org/pdf/2107.06383.pdf") st.write(read_markdown("intro/intro_part_1.md")) with st.beta_expander("FasterRCNN Approach"): st.write(read_markdown("intro/faster_rcnn_approach.md")) st.write(read_markdown("intro/intro_part_2.md")) toc.subheader("Novel Contributions") st.write(read_markdown("intro/contributions.md")) toc.header("Methodology") toc.subheader("Pre-training") st.write(read_markdown("pretraining/intro.md")) # col1, col2 = st.beta_columns([5,5]) st.image( "./misc/article/Multilingual-VQA.png", caption="Masked LM model for Image-text Pre-training.", ) toc.subsubheader("MLM Dataset") st.write(read_markdown("pretraining/data.md")) toc.subsubheader("MLM Model") st.write(read_markdown("pretraining/model.md")) toc.subsubheader("MLM Training Logs") st.write("Click on the expandable region to see the TensorBoard logs.") st.info("In case the TensorBoard logs are not displayed, please visit this link: https://huggingface.co/flax-community/multilingual-vqa-pt-ckpts/tensorboard") with st.beta_expander("MLM TensorBoard Logs"): st_tensorboard(logdir='./logs/pretrain_logs', port=6006) toc.subheader("Finetuning") toc.subsubheader("VQA Dataset") st.write(read_markdown("finetuning/data.md")) toc.subsubheader("VQA Model") st.write(read_markdown("finetuning/model.md")) toc.subsubheader("VQA Training Logs") st.write("Click on the expandable region to see the TensorBoard logs.") st.info("In case the TensorBoard logs are not displayed, please visit this link: https://huggingface.co/flax-community/multilingual-vqa-pt-60k-ft/tensorboard") with st.beta_expander("VQA TensorBoard Logs"): st_tensorboard(logdir='./logs/finetune_logs', port=6007) toc.header("Challenges and Technical Difficulties") st.write(read_markdown("challenges.md")) toc.header("Limitations and Bias") st.write(read_markdown("limitations.md")) toc.header("Conclusion, Future Work, and Social Impact") # toc.subheader("Conclusion") # st.write(read_markdown("conclusion_future_work/conclusion.md")) # toc.subheader("Future Work") # st.write(read_markdown("conclusion_future_work/future_work.md")) # toc.subheader("Social Impact") st.write(read_markdown("conclusion_future_work/social_impact.md")) toc.header("References") toc.subheader("Papers") st.write(read_markdown("references/papers.md")) toc.subheader("Useful Links") st.write(read_markdown("references/useful_links.md")) toc.header("Checkpoints") st.write(read_markdown("checkpoints/checkpoints.md")) toc.subheader("Other Checkpoints") st.write(read_markdown("checkpoints/other_checkpoints.md")) toc.header("Acknowledgements") st.write(read_markdown("acknowledgements.md")) toc.generate()