MMBench / app.py
kennymckormick
update
d92bd4e
import abc
import gradio as gr
from gen_table import *
from meta_data import *
with gr.Blocks() as demo:
results = load_results()
for k in results:
val = results[k]
val.pop('key')
N_DATA = 5
structs = [abc.abstractproperty() for _ in range(N_DATA)]
gr.Markdown(LEADERBORAD_INTRODUCTION)
with gr.Tabs(elem_classes='tab-buttons') as tabs:
with gr.TabItem('πŸ… MMBench Leaderboard', elem_id='main', id=0):
_, check_box = BUILD_L1_DF(results)
table = generate_table(results)
table['Rank'] = list(range(1, len(table) + 1))
type_map = check_box['type_map']
type_map['Rank'] = 'number'
checkbox_group = gr.CheckboxGroup(
choices=check_box['all'],
value=check_box['required'],
label='Evaluation Dimension',
interactive=True,
)
headers = ['Rank'] + check_box['essential'] + checkbox_group.value
with gr.Row():
model_size = gr.CheckboxGroup(
choices=MODEL_SIZE,
value=MODEL_SIZE,
label='Model Size',
interactive=True
)
model_type = gr.CheckboxGroup(
choices=MODEL_TYPE,
value=MODEL_TYPE,
label='Model Type',
interactive=True
)
data_component = gr.components.DataFrame(
value=table[headers],
type='pandas',
datatype=[type_map[x] for x in headers],
interactive=False,
visible=True)
def filter_df(fields, model_size, model_type):
headers = ['Rank'] + check_box['essential'] + fields
df = generate_table(results)
df['flag'] = [model_size_flag(x, model_size) for x in df['Param (B)']]
df = df[df['flag']]
df.pop('flag')
if len(df):
df['flag'] = [model_type_flag(df.iloc[i], model_type) for i in range(len(df))]
df = df[df['flag']]
df.pop('flag')
df['Rank'] = list(range(1, len(df) + 1))
comp = gr.components.DataFrame(
value=df[headers],
type='pandas',
datatype=[type_map[x] for x in headers],
interactive=False,
visible=True)
return comp
for cbox in [checkbox_group, model_size, model_type]:
cbox.change(fn=filter_df, inputs=[checkbox_group, model_size, model_type], outputs=data_component)
with gr.TabItem('πŸ” About', elem_id='about', id=1):
gr.Markdown(urlopen(MMBench_README).read().decode())
DATASETS = ['MMBench_TEST_EN_V11', 'MMBench_TEST_CN_V11', 'CCBench', 'MMBench_TEST_EN', 'MMBench_TEST_CN']
for i, dataset in enumerate(DATASETS):
with gr.TabItem(f'πŸ“Š {dataset}', elem_id=dataset, id=i + 2):
s = structs[i]
s.table, s.check_box = BUILD_L2_DF(results, dataset)
s.type_map = s.check_box['type_map']
s.type_map['Rank'] = 'number'
s.checkbox_group = gr.CheckboxGroup(
choices=s.check_box['all'],
value=s.check_box['required'],
label=f'{dataset} CheckBoxes',
interactive=True,
)
s.headers = ['Rank'] + s.check_box['essential'] + s.checkbox_group.value
s.table['Rank'] = list(range(1, len(s.table) + 1))
with gr.Row():
s.model_size = gr.CheckboxGroup(
choices=MODEL_SIZE,
value=MODEL_SIZE,
label='Model Size',
interactive=True
)
s.model_type = gr.CheckboxGroup(
choices=MODEL_TYPE,
value=MODEL_TYPE,
label='Model Type',
interactive=True
)
s.data_component = gr.components.DataFrame(
value=s.table[s.headers],
type='pandas',
datatype=[s.type_map[x] for x in s.headers],
interactive=False,
visible=True)
s.dataset = gr.Textbox(value=dataset, label=dataset, visible=False)
def filter_df_l2(dataset_name, fields, model_size, model_type):
s = structs[DATASETS.index(dataset_name)]
headers = ['Rank'] + s.check_box['essential'] + fields
df = cp.deepcopy(s.table)
df['flag'] = [model_size_flag(x, model_size) for x in df['Param (B)']]
df = df[df['flag']]
df.pop('flag')
if len(df):
df['flag'] = [model_type_flag(df.iloc[i], model_type) for i in range(len(df))]
df = df[df['flag']]
df.pop('flag')
df['Rank'] = list(range(1, len(df) + 1))
comp = gr.components.DataFrame(
value=df[headers],
type='pandas',
datatype=[s.type_map[x] for x in headers],
interactive=False,
visible=True)
return comp
for cbox in [s.checkbox_group, s.model_size, s.model_type]:
cbox.change(
fn=filter_df_l2,
inputs=[s.dataset, s.checkbox_group, s.model_size, s.model_type],
outputs=s.data_component)
with gr.Row():
with gr.Accordion('Citation', open=False):
citation_button = gr.Textbox(
value=CITATION_BUTTON_TEXT,
label=CITATION_BUTTON_LABEL,
elem_id='citation-button')
if __name__ == '__main__':
demo.launch(server_name='0.0.0.0')