import streamlit as st
from streamlit_extras.switch_page_button import switch_page


translations = {
'en': {'title': 'PLLaVA',
    'original_tweet': 
       """
       [Original tweet](https://twitter.com/mervenoyann/status/1786336055425138939) (May 3, 2024)
       """,
    'tweet_1':
        """
        Parameter-free LLaVA for video captioning works like magic! 🤩 Let's take a look!
        """,
    'tweet_2':
        """
        Most of the video captioning models work by downsampling video frames to reduce computational complexity and memory requirements without losing a lot of information in the process.  
        PLLaVA on the other hand, uses pooling! 🤩  
        <br>
        How? 🧐  
        It takes in frames of video, passed to ViT and then projection layer, and then output goes through average pooling where input shape is (# frames, width, height, text decoder input dim) 👇 
        """,
    'tweet_3':
        """
        Pooling operation surprisingly reduces the loss of spatial and temporal information. See below some examples on how it can capture the details 🤗 
        """,
    'tweet_4':
        """
        According to authors' findings, it performs way better than many of the existing models (including proprietary VLMs) and scales very well (on text decoder). 
        """,
    'tweet_5':
        """
        Model repositories 🤗 [7B](https://t.co/AeSdYsz1U7), [13B](https://t.co/GnI1niTxO7), [34B](https://t.co/HWAM0ZzvDc)  
        Spaces🤗 [7B](https://t.co/Oms2OLkf7O), [13B](https://t.co/C2RNVNA4uR)  
        """,
    'ressources':
        """
        Ressources:  
        [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://arxiv.org/abs/2404.16994) 
        by Lin Xu, Yilin Zhao, Daquan Zhou, Zhijie Lin, See Kiong Ng, Jiashi Feng (2024)  
        [GitHub](https://github.com/magic-research/PLLaVA)
        """
      },
'fr': {
    'title': 'PLLaVA',
    'original_tweet': 
       """
       [Tweet de base](https://twitter.com/mervenoyann/status/1786336055425138939) (en anglais) (3 mai 2024)
       """,
    'tweet_1':
        """
        Parameter-free LLaVA (PLLaVA) pour le sous-titrage vidéo fonctionne comme par magie ! 🤩  
        Jetons un coup d'œil !
        """,
    'tweet_2':
        """
        La plupart des modèles de sous-titrage vidéo fonctionnent par sous-échantillonnage des images vidéo afin de réduire la complexité de calcul et les besoins en mémoire sans perdre beaucoup d'informations au cours du processus.  
        PLLaVA, quant à lui, utilise le pooling ! 🤩  
        <br>
        Comment ?  
        Il prend les images de la vidéo, les passe au ViT puis à la couche de projection, et la sortie passe par un average pooling où la forme d'entrée est (# images, largeur, hauteur, dim d'entrée du décodeur de texte) 👇         """,
    'tweet_3':
        """
        L'opération de pooling réduit de manière surprenante la perte d'informations spatiales et temporelles. Voir ci-dessous quelques exemples de la façon dont elle peut capturer les détails 🤗         """,
    'tweet_4':
        """
        Selon les conclusions des auteurs, il est bien plus performant que de nombreux modèles existants (y compris les VLM propriétaires) et passe à l'échelle très bien (sur le décodeur de texte).         """,
    'tweet_5':
        """
        Dépôts des modèles 🤗 [7 Mds](https://t.co/AeSdYsz1U7), [13 Mds](https://t.co/GnI1niTxO7), [34 Mds](https://t.co/HWAM0ZzvDc)  
        Spaces🤗 [7 Mds](https://t.co/Oms2OLkf7O), [13 Mds](https://t.co/C2RNVNA4uR)  
        """,
    'ressources':
        """
        Ressources :  
        [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://arxiv.org/abs/2404.16994) 
        de Lin Xu, Yilin Zhao, Daquan Zhou, Zhijie Lin, See Kiong Ng, Jiashi Feng (2024)  
        [GitHub](https://github.com/magic-research/PLLaVA)
        """
    }
}    


def language_selector():
    languages = {'EN': '🇬🇧', 'FR': '🇫🇷'}
    selected_lang = st.selectbox('', options=list(languages.keys()), format_func=lambda x: languages[x], key='lang_selector')
    return 'en' if selected_lang == 'EN' else 'fr'

left_column, right_column = st.columns([5, 1])

# Add a selector to the right column
with right_column:
    lang = language_selector()

# Add a title to the left column
with left_column:
    st.title(translations[lang]["title"])
    
st.success(translations[lang]["original_tweet"], icon="ℹ️")
st.markdown(""" """)

st.markdown(translations[lang]["tweet_1"], unsafe_allow_html=True)
st.markdown(""" """)

st.image("pages/PLLaVA/image_1.jpg", use_column_width=True)
st.markdown(""" """)

st.markdown(translations[lang]["tweet_2"], unsafe_allow_html=True)
st.markdown(""" """)

st.image("pages/PLLaVA/image_2.jpeg", use_column_width=True)
st.markdown(""" """)

st.markdown(translations[lang]["tweet_3"], unsafe_allow_html=True)
st.markdown(""" """)

st.image("pages/PLLaVA/image_3.jpeg", use_column_width=True)
st.markdown(""" """)

st.markdown(translations[lang]["tweet_4"], unsafe_allow_html=True)
st.markdown(""" """)

st.image("pages/PLLaVA/image_4.jpeg", use_column_width=True)
st.markdown(""" """)

st.markdown(translations[lang]["tweet_5"], unsafe_allow_html=True)
st.markdown(""" """)

st.info(translations[lang]["ressources"], icon="📚")  

st.markdown(""" """)
st.markdown(""" """)
st.markdown(""" """)
col1, col2, col3= st.columns(3)
with col1:
    if lang == "en":
        if st.button('Previous paper', use_container_width=True):
            switch_page("MiniGemini")
    else:
        if st.button('Papier précédent', use_container_width=True):
            switch_page("MiniGemini")
with col2:
    if lang == "en":
        if st.button("Home", use_container_width=True):
            switch_page("Home")
    else:
        if st.button("Accueil", use_container_width=True):
            switch_page("Home")
with col3:
    if lang == "en":
        if st.button("Next paper", use_container_width=True):
            switch_page("CuMo")
    else:
        if st.button("Papier suivant", use_container_width=True):
            switch_page("CuMo")