Spaces:
Sleeping
Sleeping
| """ | |
| Adapted from the SEED-Bench Leaderboard by AILab-CVC | |
| Source: https://huggingface.co/spaces/AILab-CVC/SEED-Bench_Leaderboard | |
| """ | |
| import gradio as gr | |
| import pandas as pd | |
| from constants import * | |
| global data_component, filter_component | |
| def upload_file(files): | |
| file_paths = [file.name for file in files] | |
| return file_paths | |
| def get_baseline_df(): | |
| df = pd.read_csv(CSV_DIR) | |
| df = df.sort_values(by=DEFAULT_SPLIT, ascending=False) | |
| present_columns = MODEL_INFO + [DEFAULT_SPLIT] | |
| df = df[present_columns] | |
| # print(df) | |
| return df | |
| def get_all_df(): | |
| df = pd.read_csv(CSV_DIR) | |
| df = df.sort_values(by=DEFAULT_SPLIT, ascending=False) | |
| # print(df) | |
| return df | |
| block = gr.Blocks() | |
| with block: | |
| gr.Markdown( | |
| LEADERBORAD_INTRODUCTION | |
| ) | |
| with gr.Tabs(elem_classes="tab-buttons") as tabs: | |
| with gr.TabItem("🏅 EgoPlan Benchmark", elem_id="evalcrafter-benchmark-tab-table", id=0): | |
| gr.Markdown( | |
| TABLE_INTRODUCTION | |
| ) | |
| dropdown_value = gr.inputs.Dropdown( | |
| choices=SPLIT_INFO, | |
| default=DEFAULT_SPLIT | |
| ) | |
| # pdb.set_trace() | |
| data_component = gr.components.Dataframe( | |
| value=get_baseline_df, | |
| headers=COLUMN_NAMES, | |
| type="pandas", | |
| datatype=DATA_TITILE_TYPE, | |
| interactive=False, | |
| visible=True, | |
| ) | |
| def on_dropdown_value_change(selected_split): | |
| # pdb.set_trace() | |
| present_columns = MODEL_INFO + [selected_split] | |
| updated_data = get_all_df()[present_columns].dropna() | |
| updated_data = updated_data.sort_values(by=present_columns[-1], ascending=False) | |
| updated_headers = present_columns | |
| update_datatype = [DATA_TITILE_TYPE[COLUMN_NAMES.index(x)] for x in updated_headers] | |
| # pdb.set_trace() | |
| filter_component = gr.components.Dataframe( | |
| value=updated_data, | |
| headers=updated_headers, | |
| type="pandas", | |
| datatype=update_datatype, | |
| interactive=False, | |
| visible=True, | |
| ) | |
| # pdb.set_trace() | |
| return filter_component.value | |
| dropdown_value.change(fn=on_dropdown_value_change, inputs=dropdown_value, outputs=data_component) | |
| # table 2 | |
| with gr.TabItem("📝 About", elem_id="egoplan-benchmark-tab-table", id=2): | |
| gr.Markdown(LEADERBORAD_INFO, elem_classes="markdown-text") | |
| with gr.Row(): | |
| data_run = gr.Button("Refresh") | |
| data_run.click( | |
| get_baseline_df, outputs=data_component | |
| ) | |
| gr.Markdown(r""" | |
| Please cite this paper if you find it useful ♥️: | |
| ```bibtex | |
| @article{chen2023egoplan, | |
| title={EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning}, | |
| author={Chen, Yi and Ge, Yuying and Ge, Yixiao and Ding, Mingyu and Li, Bohao and Wang, Rui and Xu, Ruifeng and Shan, Ying and Liu, Xihui}, | |
| journal={arXiv preprint arXiv:2312.06722}, | |
| year={2023} | |
| } | |
| ``` | |
| """) | |
| # block.load(get_baseline_df, outputs=data_title) | |
| block.launch(share=False) |