Expand 3D captcha into three subtypes: 3d_text, 3d_rotate, 3d_slider

Split the single "3d" captcha type into three independent expert models:
- 3d_text: 3D perspective text OCR (renamed from old "3d", CTC-based ThreeDCNN)
- 3d_rotate: rotation angle regression (new RegressionCNN, circular loss)
- 3d_slider: slider offset regression (new RegressionCNN, SmoothL1 loss)

CAPTCHA_TYPES expanded from 3 to 5 classes. Classifier samples updated
to 50000 (10000 per class). New generators, model, dataset, training
utilities, and full pipeline/export/CLI support for all subtypes.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

models/__init__.py

@@ -1,18 +1,21 @@
 """
 模型定义包
 
-提供三种模型：
+提供四种模型：
 - CaptchaClassifier: 调度分类器 (轻量 CNN, < 500KB)
 - LiteCRNN: 轻量 CRNN (普通字符 + 算式, < 2MB)
-- ThreeDCNN: 3D 验证码专用模型 (ResNet-lite + BiLSTM, < 5MB)
+- ThreeDCNN: 3D 文字验证码专用模型 (ResNet-lite + BiLSTM, < 5MB)
+- RegressionCNN: 回归 CNN (3D 旋转 + 滑块, ~1MB)
 """
 
 from models.classifier import CaptchaClassifier
 from models.lite_crnn import LiteCRNN
 from models.threed_cnn import ThreeDCNN
+from models.regression_cnn import RegressionCNN
 
 __all__ = [
     "CaptchaClassifier",
     "LiteCRNN",
     "ThreeDCNN",
+    "RegressionCNN",
 ]