File size: 1,781 Bytes
b635719 bc03b37 b635719 bc03b37 b635719 bc03b37 b635719 | 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 | """
MVM² Benchmark Runner
Unified script to run evaluations on integrated research benchmarks.
"""
import os
import sys
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
import argparse
import subprocess
def run_mathverse(limit=None):
"""Run MathVerse evaluation"""
print("\n" + "="*50)
print("[START] MathVerse Benchmark (ECCV 2024)")
print("="*50)
script_path = os.path.join(os.path.dirname(__file__), "evaluate_mathverse.py")
cmd = [sys.executable, script_path]
if limit:
cmd.extend(["--limit", str(limit)])
subprocess.run(cmd)
def run_mathv(limit=None):
"""Run MATH-V evaluation"""
print("\n" + "="*50)
print("[START] MATH-V Benchmark (NeurIPS 2024)")
print("="*50)
script_path = os.path.join(os.path.dirname(__file__), "evaluate_mathv.py")
cmd = [sys.executable, script_path]
if limit:
cmd.extend(["--limit", str(limit)])
subprocess.run(cmd)
def main():
parser = argparse.ArgumentParser(description="Run MVM2 Research Benchmarks")
parser.add_argument('benchmark', choices=['mathverse', 'mathv', 'all'],
help="Benchmark to run")
parser.add_argument('--limit', type=int, default=None,
help="Limit number of samples (for testing)")
args = parser.parse_args()
# Check dependencies
try:
import datasets
except ImportError:
print("[ERROR] Missing dependency: 'datasets'")
print("Please run: pip install datasets")
return
if args.benchmark in ['mathverse', 'all']:
run_mathverse(args.limit)
if args.benchmark in ['mathv', 'all']:
run_mathv(args.limit)
if __name__ == "__main__":
main()
|