xsl
446d7a9391
T-P0-16/12/10 可行性验证：CPU 基准 + 代理质检指标 + 合成图体型剖面法 原型 + REPORT.md 三问三答（Sprint 1 门槛的决策依据）。 偏差说明：模型齐全未触发降级（rtmpose-s/m + birefnet_lite fp32 全部首选 候选成功，hf-mirror 实测 4~12MB/s）；huggingface_hub 不在 spike extra 且 禁新增依赖，改用 stdlib urllib 直连 resolve 端点（同 HTTP 语义）；PINTO model zoo 无法脚本化定位小模型、dhkim0115 仓不存在，姿态模型改用 bukuroo/RTMPose-ONNX；BiRefNet 官方仓无 ONNX，用 onnx-community 导出； GPU 档未测（CPU 版 ORT 无 CUDA EP，按文档不折腾）；BiRefNet 单张>3s 正式 次数自适应降为 10 并在输出注明；RTMPose 在合成剪影上置信度低（域差异）， 体型断言按文档允许走真值定高路径，关键点路径仅统计参考一致率。
140 lines
5.6 KiB
Python
140 lines
5.6 KiB
Python
"""T9 SPIKE · 合成人形图生成器（纯几何绘制，不使用任何真实人脸/人体数据——合规红线）。
|
|
|
|
rtmpose_benchmark / birefnet_matting 的输入图、body_measure_prototype 的体型变体
|
|
全部由本模块确定性生成（同一参数永远产出同一张图），并把「生成时即已知」的真值
|
|
（三线高度 / 三线宽度 / 期望体型）写入 ground_truth.json——这就是体型分类一致性
|
|
验证的最小真值来源。
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import cv2
|
|
import numpy as np
|
|
|
|
ASSETS_DIR = Path(__file__).resolve().parent / "assets"
|
|
|
|
# ── 画布与几何（像素；画布 384x512，人形居中站立） ────────────────────────────
|
|
CANVAS_W, CANVAS_H = 384, 512
|
|
CX = CANVAS_W // 2
|
|
HEAD_R = 34
|
|
HEAD_TOP = 26
|
|
HEAD_CY = HEAD_TOP + HEAD_R
|
|
NECK_HW = 8
|
|
Y_SHOULDER, Y_WAIST, Y_HIP = 112, 200, 280
|
|
LEG_BOTTOM, LEG_GAP = 486, 8
|
|
ARM_T = 10 # 手臂沿躯干边缘绘制，每侧超出边缘 ARM_T/2 → 三线宽度 ≈ 2×半宽 + ARM_T
|
|
|
|
BODY_COLOR: tuple[int, int, int] = (150, 168, 198) # BGR，米肤色调
|
|
BG_FLAT: tuple[int, int, int] = (242, 242, 242) # 纯色背景
|
|
GRAD_TOP = np.array([250, 250, 250], dtype=np.float32) # 渐变背景（上亮）
|
|
GRAD_BOTTOM = np.array([158, 166, 182], dtype=np.float32) # 渐变背景（下暗）
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class BodyShape:
|
|
"""体型变体：三处剖面半宽（像素）+ 期望分类（生成时即已知，即一致性断言真值）。"""
|
|
|
|
key: str
|
|
expect: str
|
|
shoulder_hw: int
|
|
waist_hw: int
|
|
hip_hw: int
|
|
|
|
|
|
# STD 是 §3.2/§3.3 的标准输入图（中性比例，分类为 H）；其余五种覆盖 H/A/V/O/X 全类别
|
|
VARIANTS: tuple[BodyShape, ...] = (
|
|
BodyShape("STD", "H", 60, 50, 60),
|
|
BodyShape("H", "H", 58, 55, 57),
|
|
BodyShape("A", "A", 44, 46, 68),
|
|
BodyShape("V", "V", 72, 48, 54),
|
|
BodyShape("X", "X", 60, 34, 62),
|
|
BodyShape("O", "O", 52, 66, 56),
|
|
)
|
|
|
|
|
|
def _canvas(background: str) -> np.ndarray:
|
|
if background == "gradient":
|
|
t = np.linspace(0.0, 1.0, CANVAS_H, dtype=np.float32)[:, None]
|
|
rows = GRAD_TOP[None, :] * (1.0 - t) + GRAD_BOTTOM[None, :] * t # (H,3) 逐行插值
|
|
img = np.repeat(rows[:, None, :], CANVAS_W, axis=1).astype(np.uint8)
|
|
return np.ascontiguousarray(img)
|
|
return np.full((CANVAS_H, CANVAS_W, 3), BG_FLAT, dtype=np.uint8)
|
|
|
|
|
|
def draw_figure(shape: BodyShape, background: str = "flat") -> np.ndarray:
|
|
"""按体型参数绘制人形剪影：头圆 + 颈 + 躯干三段梯形 + 贴边手臂 + 双腿。"""
|
|
img = _canvas(background)
|
|
left_edge = [
|
|
(CX - shape.shoulder_hw, Y_SHOULDER),
|
|
(CX - shape.waist_hw, Y_WAIST),
|
|
(CX - shape.hip_hw, Y_HIP),
|
|
]
|
|
right_edge = [
|
|
(CX + shape.shoulder_hw, Y_SHOULDER),
|
|
(CX + shape.waist_hw, Y_WAIST),
|
|
(CX + shape.hip_hw, Y_HIP),
|
|
]
|
|
poly = np.array([*left_edge, right_edge[2], right_edge[1], right_edge[0]], dtype=np.int32)
|
|
cv2.fillPoly(img, [poly], BODY_COLOR)
|
|
# 手臂：沿躯干左右轮廓的粗折线，圆角过渡，对三条剖面线近似均匀加宽 ARM_T/2×2
|
|
for edge in (left_edge, right_edge):
|
|
cv2.polylines(
|
|
img,
|
|
[np.array(edge, dtype=np.int32)],
|
|
isClosed=False,
|
|
color=BODY_COLOR,
|
|
thickness=ARM_T,
|
|
lineType=cv2.LINE_8,
|
|
)
|
|
# 颈 + 头
|
|
cv2.rectangle(img, (CX - NECK_HW, HEAD_CY), (CX + NECK_HW, Y_SHOULDER + 6), BODY_COLOR, -1)
|
|
cv2.circle(img, (CX, HEAD_CY), HEAD_R, BODY_COLOR, -1)
|
|
# 双腿：臀线以下的两个矩形，总宽 = 臀宽，中间留 LEG_GAP
|
|
leg_w = shape.hip_hw - LEG_GAP // 2
|
|
for x0 in (CX - shape.hip_hw, CX + LEG_GAP // 2):
|
|
cv2.rectangle(img, (x0, Y_HIP - 2), (x0 + leg_w, LEG_BOTTOM), BODY_COLOR, -1)
|
|
return img
|
|
|
|
|
|
def _ground_truth(shape: BodyShape) -> dict[str, Any]:
|
|
"""生成时即已知的真值：三线高度、三线宽度（含手臂加宽）、包围盒、期望分类。"""
|
|
half = max(shape.shoulder_hw, shape.hip_hw)
|
|
return {
|
|
"key": shape.key,
|
|
"expect": shape.expect,
|
|
"half_widths": {
|
|
"shoulder": shape.shoulder_hw,
|
|
"waist": shape.waist_hw,
|
|
"hip": shape.hip_hw,
|
|
},
|
|
"gt_widths": {
|
|
"shoulder": 2 * shape.shoulder_hw + ARM_T,
|
|
"waist": 2 * shape.waist_hw + ARM_T,
|
|
"hip": 2 * shape.hip_hw + ARM_T,
|
|
},
|
|
"line_y": {"shoulder": Y_SHOULDER, "waist": Y_WAIST, "hip": Y_HIP},
|
|
"bbox": [CX - half - ARM_T, HEAD_TOP, CX + half + ARM_T, LEG_BOTTOM],
|
|
}
|
|
|
|
|
|
def ensure_assets(assets_dir: Path = ASSETS_DIR) -> dict[str, Any]:
|
|
"""（重新）生成全部合成图与真值 JSON。确定性输出，可反复执行（幂等）。"""
|
|
variants_dir = assets_dir / "variants"
|
|
variants_dir.mkdir(parents=True, exist_ok=True)
|
|
gt: dict[str, Any] = {"canvas": [CANVAS_W, CANVAS_H], "arm_thickness": ARM_T, "variants": {}}
|
|
for shape in VARIANTS:
|
|
cv2.imwrite(str(variants_dir / f"{shape.key}.png"), draw_figure(shape, "flat"))
|
|
gt["variants"][shape.key] = _ground_truth(shape)
|
|
# §3.2/§3.3 的标准输入：纯色背景 + 渐变背景变体（各一张）
|
|
cv2.imwrite(str(assets_dir / "synthetic_person.png"), draw_figure(VARIANTS[0], "flat"))
|
|
cv2.imwrite(str(assets_dir / "synthetic_person_grad.png"), draw_figure(VARIANTS[0], "gradient"))
|
|
(assets_dir / "ground_truth.json").write_text(
|
|
json.dumps(gt, indent=2, ensure_ascii=False), encoding="utf-8"
|
|
)
|
|
return gt
|