Add slide and rotate interactive captcha solvers

New solver subsystem with independent models:
- GapDetectorCNN (1x128x256 grayscale → sigmoid) for slide gap detection
- RotationRegressor (3x128x128 RGB → sin/cos via tanh) for rotation angle prediction
- SlideSolver with 3-tier strategy: template match → edge detect → CNN fallback
- RotateSolver with ONNX sin/cos → atan2 inference
- Generators, training scripts, CLI commands, and slide track utility

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Hua
2026-03-11 18:07:06 +08:00
parent 90d6423551
commit 9b5f29083e
20 changed files with 1440 additions and 10 deletions

View File

@@ -18,11 +18,14 @@ from config import (
THREED_CHARS,
NUM_CAPTCHA_TYPES,
REGRESSION_RANGE,
SOLVER_CONFIG,
)
from models.classifier import CaptchaClassifier
from models.lite_crnn import LiteCRNN
from models.threed_cnn import ThreeDCNN
from models.regression_cnn import RegressionCNN
from models.gap_detector import GapDetectorCNN
from models.rotation_regressor import RotationRegressor
def export_model(
@@ -52,7 +55,7 @@ def export_model(
dummy = torch.randn(1, *input_shape)
# 分类器和识别器的 dynamic_axes 不同
if model_name == "classifier" or model_name in ("threed_rotate", "threed_slider"):
if model_name == "classifier" or model_name in ("threed_rotate", "threed_slider", "gap_detector", "rotation_regressor"):
dynamic_axes = {"input": {0: "batch"}, "output": {0: "batch"}}
else:
# CTC 模型: output shape = (T, B, C)
@@ -110,6 +113,14 @@ def _load_and_export(model_name: str):
h, w = IMAGE_SIZE["3d_slider"]
model = RegressionCNN(img_h=h, img_w=w)
input_shape = (1, h, w)
elif model_name == "gap_detector":
h, w = SOLVER_CONFIG["slide"]["cnn_input_size"]
model = GapDetectorCNN(img_h=h, img_w=w)
input_shape = (1, h, w)
elif model_name == "rotation_regressor":
h, w = SOLVER_CONFIG["rotate"]["input_size"]
model = RotationRegressor(img_h=h, img_w=w)
input_shape = (3, h, w)
else:
print(f"[错误] 未知模型: {model_name}")
return
@@ -119,11 +130,15 @@ def _load_and_export(model_name: str):
def export_all():
"""依次导出 classifier, normal, math, threed_text, threed_rotate, threed_slider 六个模型。"""
"""依次导出全部模型 (含 solver 模型)"""
print("=" * 50)
print("导出全部 ONNX 模型")
print("=" * 50)
for name in ["classifier", "normal", "math", "threed_text", "threed_rotate", "threed_slider"]:
for name in [
"classifier", "normal", "math", "threed_text",
"threed_rotate", "threed_slider",
"gap_detector", "rotation_regressor",
]:
_load_and_export(name)
print("\n全部导出完成。")