File size: 8,476 Bytes
1a881d8 55ece2a 1a881d8 55ece2a 1a881d8 55ece2a 1a881d8 55ece2a 1a881d8 55ece2a 1a881d8 55ece2a 1a881d8 55ece2a 1a881d8 55ece2a |
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 |
import gradio as gr
from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
import pandas as pd
from apscheduler.schedulers.background import BackgroundScheduler
from huggingface_hub import snapshot_download
from src.about import (
CITATION_BUTTON_LABEL,
CITATION_BUTTON_TEXT,
EVALUATION_QUEUE_TEXT,
INTRODUCTION_TEXT,
ABOUT_TEXT,
TITLE,
Training_Dataset,
Testing_Type
)
from src.display.css_html_js import custom_css
from src.display.utils import (
BENCHMARK_COLS,
COLS,
EVAL_COLS,
EVAL_TYPES,
AutoEvalColumn,
ModelType,
fields,
Precision
)
from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
from src.populate import get_evaluation_queue_df, get_leaderboard_df
from src.submission.submit import add_new_eval
def restart_space():
API.restart_space(repo_id=REPO_ID)
### Space initialisation
try:
snapshot_download(
repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
)
except Exception:
restart_space()
try:
snapshot_download(
repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
)
except Exception:
restart_space()
LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
(
finished_eval_queue_df,
pending_eval_queue_df,
) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
def init_leaderboard(dataframe):
if dataframe is None or dataframe.empty:
raise ValueError("Leaderboard DataFrame is empty or None.")
with gr.Tabs(elem_classes="leaderboard-tabs") as leaderboard_tabs:
for testing_type in Testing_Type:
with gr.TabItem("Average Scores" if testing_type.value == "avg" else testing_type.name, elem_id=f"{testing_type.value}_Leaderboard"):
if testing_type.value == "avg":
gr.Markdown("The scores presented in this tab are averaged scores across all datasets.")
try:
leaderboard = Leaderboard(
value=dataframe[dataframe["Testing Type"] == testing_type.name],
datatype=[c.type for c in fields(AutoEvalColumn)],
select_columns=SelectColumns(
default_selection=[c.name for c in fields(AutoEvalColumn) if c.displayed_by_default],
cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
label="Select Columns to Display:",
),
search_columns=[AutoEvalColumn.model_name.name],
hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
filter_columns=[
ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
ColumnFilter(AutoEvalColumn.training_dataset_type.name, type="checkboxgroup", label="Training Dataset"),
ColumnFilter(
AutoEvalColumn.model_parameters.name,
type="slider",
min=0,
max=10000,
default=["0", "100"],
label="Select the number of parameters (M)",
),
],
bool_checkboxgroup_label="Hide Models",
interactive=False,
)
except:
gr.Markdown("There are no submissions for this testing type yet.")
def init_submissions():
with gr.Column():
with gr.Row():
gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
with gr.Column():
with gr.Accordion(
f"β
Finished Evaluations ({len(finished_eval_queue_df)})",
open=False,
):
with gr.Row():
finished_eval_table = gr.components.Dataframe(
value=finished_eval_queue_df,
headers=EVAL_COLS,
datatype=EVAL_TYPES,
row_count=5,
)
with gr.Accordion(
f"β³ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
open=False,
):
with gr.Row():
pending_eval_table = gr.components.Dataframe(
value=pending_eval_queue_df,
headers=EVAL_COLS,
datatype=EVAL_TYPES,
row_count=5,
)
with gr.Row():
gr.Markdown("# βοΈβ¨ Submit your model here!", elem_classes="markdown-text")
with gr.Row():
with gr.Column():
model_name_textbox = gr.Textbox(label="Model name")
model_link_textbox = gr.Textbox(label="Link to Model")
model_backbone_textbox = gr.Dropdown(
choices=["Original"],
label="Model Backbone",
value="Original",
allow_custom_value=True,
)
model_parameter_number = gr.Number(label="Model Parameter Count (M)", precision=1, minimum=0)
precision = gr.Dropdown(
choices=[i.name for i in Precision],
label="Precision",
multiselect=False,
value="float32",
interactive=True,
)
paper_name_textbox = gr.Textbox(label="Paper Name")
paper_link_textbox = gr.Textbox(label="Link To Paper")
with gr.Column():
training_dataset = gr.Dropdown(
choices=[i.value for i in Training_Dataset if i.value != Training_Dataset.Other.value],
label="Training Dataset",
multiselect=False,
value=Training_Dataset.XCL.value,
interactive=True,
allow_custom_value=True,
)
testing_type = gr.Dropdown(
choices=[i.name for i in Testing_Type],
label="Tested on",
multiselect=False,
value=Testing_Type.AVG.name,
interactive=True,
)
cmap_value = gr.Number(label="cmAP Performance", precision=2, minimum=0.00, maximum=1.00, step=0.01)
auroc_value = gr.Number(label="AUROC Performance", precision=2, minimum=0.00, maximum=1.00, step=0.01)
t1acc_value = gr.Number(label="T1-Acc Performance", precision=2, minimum=0.00, maximum=1.00, step=0.01)
submit_button = gr.Button("Submit Eval")
submission_result = gr.Markdown()
submit_button.click(
fn=add_new_eval,
inputs=[
model_name_textbox,
model_link_textbox,
model_backbone_textbox,
precision,
model_parameter_number,
paper_name_textbox,
paper_link_textbox,
training_dataset,
testing_type,
cmap_value,
auroc_value,
t1acc_value,
],
outputs=submission_result,
)
demo = gr.Blocks(css=custom_css)
with demo:
gr.HTML(TITLE)
gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
with gr.Tabs(elem_classes="tab-buttons") as tabs:
with gr.TabItem("π
Leaderboard", elem_id="leaderboard-tab-table", id=0):
init_leaderboard(LEADERBOARD_DF)
with gr.TabItem("π About", elem_id="leaderboard-tab-table", id=2):
gr.Markdown(ABOUT_TEXT, elem_classes="markdown-text")
with gr.TabItem("π Submit here! ", elem_id="leaderboard-tab-table", id=3):
init_submissions()
with gr.Row():
with gr.Accordion("π Citation", open=False):
citation_button = gr.Textbox(
value=CITATION_BUTTON_TEXT,
label=CITATION_BUTTON_LABEL,
lines=20,
elem_id="citation-button",
show_copy_button=True,
)
scheduler = BackgroundScheduler()
scheduler.add_job(restart_space, "interval", seconds=1800)
scheduler.start()
demo.launch()
|