File size: 12,950 Bytes
3c75092 a6e43e6 3c75092 0bb476f a6e43e6 3c75092 0bb476f 6734e22 0bb476f 3c75092 0bb476f 80c5be6 0bb476f 80c5be6 0bb476f 3c75092 0bb476f 80c5be6 0bb476f 80c5be6 0bb476f a6e43e6 3c75092 a6e43e6 0bb476f 3c75092 0bb476f 63ffee3 a6e43e6 0bb476f a6e43e6 0bb476f a6e43e6 0bb476f 3c75092 0bb476f 3c75092 a6e43e6 3c75092 a6e43e6 3c75092 f1fda01 6734e22 f1fda01 3c75092 0bb476f 3c75092 0bb476f 80c5be6 0bb476f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 |
import abc
import gradio as gr
from loguru import logger
import pandas as pd
from collections import defaultdict
from judgerbench.preprocess.gen_table import (
format_timestamp,
generate_table,
build_l1_df,
# build_l2_df,
)
from judgerbench.meta_data import (
LEADERBORAD_INTRODUCTION,
LEADERBOARD_MD,
LEADERBOARD_FILE_MAPPING,
MAIN_FIELDS,
DEFAULT_BENCH,
STYLE_CLASS_MAPPING,
CITATION_BUTTON_TEXT,
CITATION_BUTTON_LABEL,
)
def refresh_dataframe(required_fields):
df = generate_table(MAIN_FIELDS)
comp = gr.DataFrame(
value=df,
type='pandas',
interactive=False,
visible=True
)
return comp
with gr.Blocks() as demo:
# struct = load_results()
# timestamp = struct['time']
# EVAL_TIME = format_timestamp(timestamp)
EVAL_TIME = '20241022'
# results = struct['results']
# N_MODEL = len(results)
# N_DATA = len(results['LLaVA-v1.5-7B']) - 1
N_MODEL = 10
N_DATA = 100
# DATASETS = list(results['LLaVA-v1.5-7B'])
# DATASETS.remove('META')
# print(DATASETS)
gr.Markdown(LEADERBORAD_INTRODUCTION.format(
# N_MODEL,
# N_DATA,
EVAL_TIME
))
# structs = [abc.abstractproperty() for _ in range(N_DATA)]
with gr.Tabs(elem_classes='tab-buttons') as tabs:
for cur_id, (filename, filepath) in enumerate(LEADERBOARD_FILE_MAPPING.items()):
tab_name = filename
# if filename == "overall":
# tab_name = '🏅 JudgerBench Main Leaderboard'
with gr.Tab(tab_name.upper(), elem_id=f'tab_{cur_id}', id=cur_id):
# gr.Markdown(LEADERBOARD_MD['MAIN'])
# _, check_box = build_l1_df(MAIN_FIELDS)
table = generate_table(filename=filename)
# type_map = check_box['type_map']
type_map = defaultdict(lambda: 'number')
type_map['Model'] = 'str'
type_map['Class'] = 'str'
type_map['Rank'] = 'number'
# required_fields = gr.State(
# check_box['essential']
# # + ["Average"]
# )
# checkbox_group = gr.CheckboxGroup(
# choices=[item for item in check_box['all'] if item not in required_fields.value],
# value=[item for item in check_box['default'] if item not in required_fields.value],
# label='Evaluation Metrics',
# interactive=True,
# )
# headers = (
# ['Rank'] +
# required_fields.value +
# [item for item in check_box['all'] if item not in required_fields.value]
# # checkbox_group.value
# )
table['Rank'] = list(range(1, len(table) + 1))
# Rearrange columns
if "Class" in table.columns:
starting_columns = ["Rank", "Models", "Class"]
else:
starting_columns = ["Rank", "Models"]
table = table[starting_columns + [ col for col in table.columns if col not in starting_columns ]]
headers = (
# ['Rank'] +
list(table.columns)
)
if "Class" in table.columns:
def cell_styler(v):
df = v.copy()
class_var = df[['Class']].copy()
df.loc[:, :] = ''
df[['Class']] = class_var.map(lambda x: f"background-color: {STYLE_CLASS_MAPPING[x]}")
logger.info(df['Class'])
return df
table_styler = (
table.style.apply(cell_styler, axis=None)
.format(precision=1)
)
else:
table_styler = table.style.format(precision=1)
# 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.DataFrame(
value=table_styler,
type='pandas',
datatype=[type_map[x] for x in headers],
interactive=False,
visible=True
)
def filter_df(
required_fields,
fields,
# model_size,
# model_type
):
# filter_list = ['Avg Score', 'Avg Rank', 'OpenSource', 'Verified']
headers = ['Rank'] + required_fields + fields
# new_fields = [field for field in fields if field not in filter_list]
df = generate_table(fields)
logger.info(f"{df.columns=}")
# 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.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=refresh_dataframe,
# inputs=[required_fields],
# outputs=data_component
# ).then(
# fn=filter_df,
# inputs=[
# required_fields,
# checkbox_group,
# # model_size,
# # model_type
# ],
# outputs=data_component
# )
# with gr.Tab('🔍 About', elem_id='about', id=1):
# gr.Markdown(urlopen(VLMEVALKIT_README).read().decode())
# for i, dataset in enumerate(DATASETS):
# with gr.Tab(f'📊 {dataset} Leaderboard', elem_id=dataset, id=i + 2):
# if dataset in LEADERBOARD_MD:
# gr.Markdown(LEADERBOARD_MD[dataset])
# 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',
lines=7,
)
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--host", type=str, default="0.0.0.0")
parser.add_argument("--port", type=int, default="7860")
parser.add_argument(
"--share",
action="store_true",
help="Whether to generate a public, shareable link",
)
parser.add_argument(
"--concurrency-count",
type=int,
default=10,
help="The concurrency count of the gradio queue",
)
parser.add_argument(
"--max-threads",
type=int,
default=200,
help="The maximum number of threads available to process non-async functions.",
)
# parser.add_argument(
# "--gradio-auth-path",
# type=str,
# help='Set the gradio authentication file path. The file should contain one or more user:password pairs in this format: "u1:p1,u2:p2,u3:p3"',
# default=None,
# )
parser.add_argument(
"--gradio-root-path",
type=str,
help="Sets the gradio root path, eg /abc/def. Useful when running behind a reverse-proxy or at a custom URL path prefix",
)
parser.add_argument(
"--ga-id",
type=str,
help="the Google Analytics ID",
default=None,
)
parser.add_argument(
"--use-remote-storage",
action="store_true",
default=False,
help="Uploads image files to google cloud storage if set to true",
)
args = parser.parse_args()
logger.info(f"args: {args}")
# Set authorization credentials
# auth = None
# if args.gradio_auth_path is not None:
# auth = parse_gradio_auth_creds(args.gradio_auth_path)
demo.queue(
default_concurrency_limit=args.concurrency_count,
status_update_rate=10,
api_open=False,
).launch(
server_name=args.host,
server_port=args.port,
share=args.share,
max_threads=args.max_threads,
# auth=auth,
root_path=args.gradio_root_path,
# debug=True,
show_error=True,
allowed_paths=["../.."]
)
|