Align task API and add FunCaptcha support

This commit is contained in:
Hua
2026-03-12 19:32:59 +08:00
parent ef9518deeb
commit bc6776979e
33 changed files with 3446 additions and 672 deletions

68
cli.py
View File

@@ -18,6 +18,8 @@ CaptchaBreaker 命令行入口
python cli.py train-solver rotate
python cli.py solve slide --bg bg.png [--tpl tpl.png]
python cli.py solve rotate --image img.png
python cli.py train-funcaptcha --question 4_3d_rollball_animals
python cli.py predict-funcaptcha image.jpg --question 4_3d_rollball_animals
"""
import argparse
@@ -125,6 +127,7 @@ def cmd_export(args):
"3d_text": "threed_text",
"3d_rotate": "threed_rotate",
"3d_slider": "threed_slider",
"4_3d_rollball_animals": "funcaptcha_rollball_animals",
}
name = alias.get(args.model, args.model)
_load_and_export(name)
@@ -284,6 +287,52 @@ def cmd_solve(args):
sys.exit(1)
def cmd_train_funcaptcha(args):
"""训练 FunCaptcha 专项模型。"""
from config import FUN_CAPTCHA_TASKS
from training.train_funcaptcha_rollball import main as train_rollball
question = args.question
if question not in FUN_CAPTCHA_TASKS:
print(f"未知 FunCaptcha question: {question} 可选: {', '.join(FUN_CAPTCHA_TASKS)}")
sys.exit(1)
if question == "4_3d_rollball_animals":
train_rollball(question=question)
return
print(f"暂未实现该 FunCaptcha 训练入口: {question}")
sys.exit(1)
def cmd_predict_funcaptcha(args):
"""专项 FunCaptcha 预测。"""
from config import FUN_CAPTCHA_TASKS
from inference.fun_captcha import FunCaptchaRollballPipeline
image_path = args.image
question = args.question
if not Path(image_path).exists():
print(f"文件不存在: {image_path}")
sys.exit(1)
if question not in FUN_CAPTCHA_TASKS:
print(f"未知 FunCaptcha question: {question} 可选: {', '.join(FUN_CAPTCHA_TASKS)}")
sys.exit(1)
if question == "4_3d_rollball_animals":
pipeline = FunCaptchaRollballPipeline(question=question)
else:
print(f"暂未实现该 FunCaptcha 预测入口: {question}")
sys.exit(1)
result = pipeline.solve(image_path)
print(f"文件: {image_path}")
print(f"question: {result['question']}")
print(f"objects: {result['objects']}")
print(f"result: {result['result']}")
print(f"耗时: {result['time_ms']:.1f} ms")
def main():
parser = argparse.ArgumentParser(
prog="captcha-breaker",
@@ -352,6 +401,23 @@ def main():
p_solve.add_argument("--tpl", default=None, help="模板图路径 (slide 可选)")
p_solve.add_argument("--image", help="图片路径 (rotate 必需)")
# ---- train-funcaptcha ----
p_train_fun = subparsers.add_parser("train-funcaptcha", help="训练 FunCaptcha 专项模型")
p_train_fun.add_argument(
"--question",
required=True,
help="专项 question如: 4_3d_rollball_animals",
)
# ---- predict-funcaptcha ----
p_pred_fun = subparsers.add_parser("predict-funcaptcha", help="识别单张 FunCaptcha challenge")
p_pred_fun.add_argument("image", help="图片路径")
p_pred_fun.add_argument(
"--question",
required=True,
help="专项 question如: 4_3d_rollball_animals",
)
args = parser.parse_args()
if args.command is None:
@@ -368,6 +434,8 @@ def main():
"generate-solver": cmd_generate_solver,
"train-solver": cmd_train_solver,
"solve": cmd_solve,
"train-funcaptcha": cmd_train_funcaptcha,
"predict-funcaptcha": cmd_predict_funcaptcha,
}
cmd_map[args.command](args)