333 lines
14 KiB
Python
333 lines
14 KiB
Python
|
"""CAD 实测标定 VLM 读图下限（临时加字 + 平行线，测完自动清理、不保存图纸）。
|
|||
|
|
|
|||
|
|
与 `verify_vlm_resolution_offline.py` 配套：离线预扫给**区间**，本脚本在**真实 CAD
|
|||
|
|
渲染**下确认最终 `R_text` / `R_line`（离线合成图偏干净，结论偏乐观）。
|
|||
|
|
|
|||
|
|
流程：
|
|||
|
|
1. 在空白区临时插入标定物（图层 `AI_CALIB`）：
|
|||
|
|
- 3 个单行文字，字高 T（默认 200 图形单位；1:100 时 = 纸面 2mm），内容为易错随机串；
|
|||
|
|
- 若干「1 条 / 2 条」平行线对（世界间距按目标像素间距换算）。
|
|||
|
|
2. 量出绘图区**原生像素** → 有效像素 eff（长边 ≤ `IMAGE_MAX_EDGE`）+ 视口宽高比。
|
|||
|
|
3. 目标像素字高 target：窗口宽 = `T*eff_w/target`、高 = 宽/视口宽高比 → zoom(margin=0)
|
|||
|
|
→ 截图 → 下采样 → 问 VLM 读字。
|
|||
|
|
4. 线对同理：世界间距 `L = g*W_REF/eff_w`，问「1 条还是 2 条」。
|
|||
|
|
5. 汇总 R_text / R_line；无论成败都在 finally 里 `delete_entities` 清理。
|
|||
|
|
|
|||
|
|
用法：
|
|||
|
|
python verify_text_resolution.py # 自动选空白锚点
|
|||
|
|
python verify_text_resolution.py --anchor 500000,0
|
|||
|
|
python verify_text_resolution.py --targets 6,8,10,12,16 --gaps 2,3,4,6,8
|
|||
|
|
python verify_text_resolution.py --keep # 保留标定物（调试）
|
|||
|
|
|
|||
|
|
前置：CAD 在线（127.0.0.1:8080）+ `DEEPSEEK_API_KEY`。需要 Pillow。
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import argparse
|
|||
|
|
import json
|
|||
|
|
import random
|
|||
|
|
import time
|
|||
|
|
from pathlib import Path
|
|||
|
|
|
|||
|
|
from dwg_review import config, tiling
|
|||
|
|
from dwg_review.context import ReviewContext
|
|||
|
|
from dwg_review.llm_client import LlmClient, downsample_image_b64, image_size_b64
|
|||
|
|
from dwg_review.mcp_client import result_images, result_json
|
|||
|
|
from dwg_review.phases import planning
|
|||
|
|
|
|||
|
|
# 复用离线脚本的随机串与解析工具（避免重复实现）
|
|||
|
|
from verify_vlm_resolution_offline import _ALPHABET, _extract_json, _lenient, _norm_token
|
|||
|
|
|
|||
|
|
CALIB_LAYER = "AI_CALIB"
|
|||
|
|
_TEXT_GAP = 2000.0 # 文字之间的水平间距（世界单位）
|
|||
|
|
_LINE_LEN_FRAC = 0.6 # 线长占测线窗口宽的比例
|
|||
|
|
_W_REF = 20000.0 # 测线用的固定窗口宽（世界单位）
|
|||
|
|
_SINGLE_DX = 30000.0 # 「单条线」相对线对的水平偏移（避免同框）
|
|||
|
|
_ROW_DY = 6000.0 # 各档线对的行距
|
|||
|
|
_FIRST_ROW_DY = 10000.0 # 第一行线对相对文字的下移量
|
|||
|
|
|
|||
|
|
_SYS_TEXT = "你是图像文字识别器。只输出一个 JSON 对象，不要任何解释、不要 markdown 代码块。"
|
|||
|
|
_SYS_LINE = "你是工程图纸线型识别器。只输出一个 JSON 对象，不要任何解释、不要 markdown 代码块。"
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------------------------------------------------------------------------
|
|||
|
|
# 基础交互
|
|||
|
|
# ---------------------------------------------------------------------------
|
|||
|
|
def _shot(ctx):
|
|||
|
|
imgs = result_images(ctx.tools.call("get_viewport_screenshot", {}))
|
|||
|
|
return imgs[0] if imgs else None
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _zoom_and_shot(ctx, win):
|
|||
|
|
ctx.tools.call("zoom_to_window", dict(win, margin=0.0))
|
|||
|
|
time.sleep(config.RENDER_WAIT)
|
|||
|
|
return _shot(ctx)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _ask(ctx, shot, system, prompt, out_png=None):
|
|||
|
|
"""截图（先下采样）→ 问 VLM → 返回解析后的 dict（失败 None）。"""
|
|||
|
|
b64, mime = downsample_image_b64(shot[0], shot[1])
|
|||
|
|
if out_png is not None:
|
|||
|
|
import base64
|
|||
|
|
|
|||
|
|
out_png.write_bytes(base64.b64decode(b64))
|
|||
|
|
resp = ctx.llm.chat([
|
|||
|
|
{"role": "system", "content": system},
|
|||
|
|
{"role": "user", "content": [
|
|||
|
|
{"type": "text", "text": prompt},
|
|||
|
|
LlmClient.image_content(b64, mime),
|
|||
|
|
]},
|
|||
|
|
])
|
|||
|
|
return _extract_json(resp.choices[0].message.content)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _center(win):
|
|||
|
|
return ((win["min_x"] + win["max_x"]) / 2.0, (win["min_y"] + win["max_y"]) / 2.0)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _window(cx, cy, w, h):
|
|||
|
|
return {"min_x": cx - w / 2.0, "min_y": cy - h / 2.0,
|
|||
|
|
"max_x": cx + w / 2.0, "max_y": cy + h / 2.0}
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------------------------------------------------------------------------
|
|||
|
|
# 标定物
|
|||
|
|
# ---------------------------------------------------------------------------
|
|||
|
|
def _auto_anchor(ctx):
|
|||
|
|
"""把锚点放在所有图框的右侧远处（空白区）。"""
|
|||
|
|
plan = planning.plan(ctx)
|
|||
|
|
boxes = [f.get("bbox") for f in (plan.get("frames") or [])
|
|||
|
|
if isinstance(f.get("bbox"), list) and len(f["bbox"]) == 4]
|
|||
|
|
if not boxes:
|
|||
|
|
return (0.0, 0.0)
|
|||
|
|
return (max(b[2] for b in boxes) + 50000.0, min(b[1] for b in boxes))
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _calib_window(ax, ay, n_gaps):
|
|||
|
|
"""覆盖全部标定物的查询窗口。"""
|
|||
|
|
return {
|
|||
|
|
"min_x": ax - 2 * _TEXT_GAP,
|
|||
|
|
"min_y": ay - _FIRST_ROW_DY - n_gaps * _ROW_DY - 2 * _W_REF,
|
|||
|
|
"max_x": ax + _SINGLE_DX + 2 * _W_REF,
|
|||
|
|
"max_y": ay + 2 * _TEXT_GAP,
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _add_calibration(ctx, ax, ay, gaps, text_h, eff_w, rng, color=7):
|
|||
|
|
"""插入标定物，返回 (文字 token 列表, 各档线对中心 y 列表)。
|
|||
|
|
|
|||
|
|
`color` 默认 7（白/黑自适应），保证**黑底白字**的高对比——标定的是**分辨率下限**，
|
|||
|
|
不能把「颜色对比度不足」混进来（实测红色 ACI 1 在 12px 时完全读不出）。
|
|||
|
|
"""
|
|||
|
|
tokens = ["".join(rng.choice(_ALPHABET) for _ in range(6)) for _ in range(3)]
|
|||
|
|
for i, tok in enumerate(tokens):
|
|||
|
|
ctx.tools.call("add_text", {
|
|||
|
|
"text": tok, "position": [ax + i * _TEXT_GAP, ay],
|
|||
|
|
"height": text_h, "layer": CALIB_LAYER, "color": color,
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
line_len = _LINE_LEN_FRAC * _W_REF
|
|||
|
|
ys = []
|
|||
|
|
for k, g in enumerate(gaps):
|
|||
|
|
spacing = g * _W_REF / eff_w # 世界间距 ↔ 目标像素间距
|
|||
|
|
yk = ay - _FIRST_ROW_DY - k * _ROW_DY
|
|||
|
|
ys.append(yk)
|
|||
|
|
# 线对（2 条）
|
|||
|
|
for dy in (-spacing / 2.0, spacing / 2.0):
|
|||
|
|
ctx.tools.call("add_line", {
|
|||
|
|
"start": [ax - line_len / 2.0, yk + dy],
|
|||
|
|
"end": [ax + line_len / 2.0, yk + dy],
|
|||
|
|
"layer": CALIB_LAYER, "color": color,
|
|||
|
|
})
|
|||
|
|
# 对照（1 条）
|
|||
|
|
sx = ax + _SINGLE_DX
|
|||
|
|
ctx.tools.call("add_line", {
|
|||
|
|
"start": [sx - line_len / 2.0, yk],
|
|||
|
|
"end": [sx + line_len / 2.0, yk],
|
|||
|
|
"layer": CALIB_LAYER, "color": color,
|
|||
|
|
})
|
|||
|
|
return tokens, ys
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _collect_handles(ctx, window):
|
|||
|
|
env = result_json(
|
|||
|
|
ctx.tools.call("query_entities", {
|
|||
|
|
"window": window, "layer_filter": CALIB_LAYER, "limit": 1000,
|
|||
|
|
}),
|
|||
|
|
{},
|
|||
|
|
)
|
|||
|
|
return [it.get("handle") for it in (env.get("items") or []) if it.get("handle")]
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------------------------------------------------------------------------
|
|||
|
|
# 各子测试
|
|||
|
|
# ---------------------------------------------------------------------------
|
|||
|
|
def _text_center(ctx, window, fallback):
|
|||
|
|
"""取文字类实体的 bbox 中心（拿不到则用 fallback）。
|
|||
|
|
|
|||
|
|
注意：`query_entities` 的 `type_filter` **必须是列表**（传字符串会被静默忽略）。
|
|||
|
|
这里同时按 `tiling.is_text_type` 在 Python 侧再过滤一次，双保险。
|
|||
|
|
"""
|
|||
|
|
env = result_json(
|
|||
|
|
ctx.tools.call("query_entities", {
|
|||
|
|
"window": window, "layer_filter": CALIB_LAYER,
|
|||
|
|
"type_filter": ["TEXT"], "limit": 1000,
|
|||
|
|
}),
|
|||
|
|
{},
|
|||
|
|
)
|
|||
|
|
boxes = []
|
|||
|
|
for it in env.get("items") or []:
|
|||
|
|
if not tiling.is_text_type(it.get("type")):
|
|||
|
|
continue
|
|||
|
|
b = tiling.norm_box(it.get("bbox"))
|
|||
|
|
if b:
|
|||
|
|
boxes.append(b)
|
|||
|
|
if not boxes:
|
|||
|
|
return fallback
|
|||
|
|
return (
|
|||
|
|
(min(b[0] for b in boxes) + max(b[2] for b in boxes)) / 2.0,
|
|||
|
|
(min(b[1] for b in boxes) + max(b[3] for b in boxes)) / 2.0,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def run_text_levels(ctx, tokens, center, targets, text_h, eff_w, aspect, out_dir, repeat):
|
|||
|
|
rows = []
|
|||
|
|
for target in targets:
|
|||
|
|
w = text_h * eff_w / float(target)
|
|||
|
|
win = _window(center[0], center[1], w, w / aspect)
|
|||
|
|
trials = []
|
|||
|
|
for _ in range(max(1, repeat)):
|
|||
|
|
shot = _zoom_and_shot(ctx, win)
|
|||
|
|
if not shot:
|
|||
|
|
trials.append({"got": [], "exact": 0})
|
|||
|
|
continue
|
|||
|
|
data = _ask(
|
|||
|
|
ctx, shot, _SYS_TEXT,
|
|||
|
|
"图中是若干处**白色字符**（黑底）。请把能看清的字符串按从左到右顺序读出，"
|
|||
|
|
'输出 JSON：{"texts":["串1","串2",...]}。看不清的串填空字符串。',
|
|||
|
|
out_png=out_dir / f"text_target{target}.png",
|
|||
|
|
)
|
|||
|
|
got = [str(x) for x in (data or {}).get("texts") or []]
|
|||
|
|
exact = sum(1 for i, t in enumerate(tokens)
|
|||
|
|
if i < len(got) and _norm_token(got[i]) == t)
|
|||
|
|
trials.append({"got": got, "exact": exact})
|
|||
|
|
best = max(t["exact"] for t in trials)
|
|||
|
|
row = {"target_px": target, "tokens": tokens, "trials": trials,
|
|||
|
|
"n": len(tokens), "best_exact": best, "readable": best == len(tokens)}
|
|||
|
|
rows.append(row)
|
|||
|
|
print(f" 目标字高 {target:>3}px 命中 {best}/{len(tokens)} 可读={row['readable']}")
|
|||
|
|
return rows
|
|||
|
|
|
|||
|
|
|
|||
|
|
def run_line_levels(ctx, ax, ys, gaps, aspect, out_dir, repeat):
|
|||
|
|
"""对每档像素间距，分别看「2 条线对」与「1 条对照」是否被正确区分。"""
|
|||
|
|
rows = []
|
|||
|
|
prompt = ('图中是**水平直线**（黑底白线）。只判断线条数量是 1 还是 2，'
|
|||
|
|
'输出 JSON：{"count": 1 或 2}。')
|
|||
|
|
for g, yk in zip(gaps, ys):
|
|||
|
|
res = {}
|
|||
|
|
for kind, cx in (("pair", ax), ("single", ax + _SINGLE_DX)):
|
|||
|
|
got = None
|
|||
|
|
for _ in range(max(1, repeat)):
|
|||
|
|
shot = _zoom_and_shot(ctx, _window(cx, yk, _W_REF, _W_REF / aspect))
|
|||
|
|
if not shot:
|
|||
|
|
continue
|
|||
|
|
data = _ask(ctx, shot, _SYS_LINE, prompt,
|
|||
|
|
out_png=out_dir / f"line_g{g}_{kind}.png")
|
|||
|
|
try:
|
|||
|
|
got = int(data.get("count"))
|
|||
|
|
except (TypeError, ValueError, AttributeError):
|
|||
|
|
got = None
|
|||
|
|
if got == (2 if kind == "pair" else 1):
|
|||
|
|
break
|
|||
|
|
res[kind] = got
|
|||
|
|
ok = res.get("pair") == 2 and res.get("single") == 1
|
|||
|
|
rows.append({"gap_px": g, "pair": res.get("pair"), "single": res.get("single"),
|
|||
|
|
"resolved": ok})
|
|||
|
|
print(f" 目标间距 {g:>3}px 线对={res.get('pair')} 单条={res.get('single')} "
|
|||
|
|
f"可分辨={ok}")
|
|||
|
|
return rows
|
|||
|
|
|
|||
|
|
|
|||
|
|
def _parse_floats(s):
|
|||
|
|
return [float(x) for x in str(s).split(",") if x.strip()]
|
|||
|
|
|
|||
|
|
|
|||
|
|
def main(argv=None):
|
|||
|
|
ap = argparse.ArgumentParser()
|
|||
|
|
ap.add_argument("--anchor", default="auto", help='"auto" 或 "x,y"')
|
|||
|
|
ap.add_argument("--text-height", type=float, default=200.0,
|
|||
|
|
help="标定字高（图形单位；1:100 时 200 = 纸面 2mm）")
|
|||
|
|
ap.add_argument("--targets", default="6,8,10,12,16,20", help="目标像素字高扫描档")
|
|||
|
|
ap.add_argument("--gaps", default="2,3,4,5,6,8,12", help="目标像素线间距扫描档")
|
|||
|
|
ap.add_argument("--repeat", type=int, default=1, help="每档重复次数")
|
|||
|
|
ap.add_argument("--seed", type=int, default=7, help="随机串种子")
|
|||
|
|
ap.add_argument("--keep", action="store_true", help="保留标定物（调试用）")
|
|||
|
|
ap.add_argument("--out", default="reports/_probe/vlm_calib_cad")
|
|||
|
|
args = ap.parse_args(argv)
|
|||
|
|
|
|||
|
|
targets = [int(x) for x in _parse_floats(args.targets)]
|
|||
|
|
gaps = [int(x) for x in _parse_floats(args.gaps)]
|
|||
|
|
|
|||
|
|
ctx = ReviewContext.create(need_llm=True)
|
|||
|
|
out_dir = Path(config.PROJECT_ROOT) / args.out
|
|||
|
|
out_dir.mkdir(parents=True, exist_ok=True)
|
|||
|
|
|
|||
|
|
if args.anchor.strip().lower() == "auto":
|
|||
|
|
ax, ay = _auto_anchor(ctx)
|
|||
|
|
else:
|
|||
|
|
ax, ay = (float(v) for v in args.anchor.split(","))
|
|||
|
|
print(f"锚点：({ax:.0f}, {ay:.0f}) 模型：{ctx.llm.model}")
|
|||
|
|
|
|||
|
|
# 量视口像素（决定世界↔像素换算）
|
|||
|
|
base = _shot(ctx)
|
|||
|
|
if not base:
|
|||
|
|
raise SystemExit("无法截图：get_viewport_screenshot 无返回")
|
|||
|
|
vp = image_size_b64(base[0])
|
|||
|
|
if not vp:
|
|||
|
|
raise SystemExit("无法解析截图尺寸（缺 Pillow 或图片非法）")
|
|||
|
|
eff = tiling.effective_px(vp, config.IMAGE_MAX_EDGE)
|
|||
|
|
aspect = vp[0] / float(vp[1])
|
|||
|
|
print(f"绘图区原生 {vp[0]}x{vp[1]} → 有效 {eff[0]}x{eff[1]} 视口宽高比 {aspect:.3f}")
|
|||
|
|
|
|||
|
|
handles = []
|
|||
|
|
results = {"viewport": list(vp), "effective": list(eff),
|
|||
|
|
"text_height": args.text_height, "anchor": [ax, ay]}
|
|||
|
|
try:
|
|||
|
|
rng = random.Random(args.seed)
|
|||
|
|
tokens, ys = _add_calibration(ctx, ax, ay, gaps, args.text_height, eff[0], rng)
|
|||
|
|
win = _calib_window(ax, ay, len(gaps))
|
|||
|
|
handles = _collect_handles(ctx, win)
|
|||
|
|
print(f"已插入标定物：{len(handles)} 个实体（图层 {CALIB_LAYER}）")
|
|||
|
|
|
|||
|
|
center = _text_center(ctx, win, (ax + _TEXT_GAP, ay))
|
|||
|
|
|
|||
|
|
print("\n-- 文字可读性（真实 CAD 渲染） --")
|
|||
|
|
text_rows = run_text_levels(ctx, tokens, center, targets, args.text_height,
|
|||
|
|
eff[0], aspect, out_dir, args.repeat)
|
|||
|
|
|
|||
|
|
print("\n-- 线间距可分辨性（1 vs 2） --")
|
|||
|
|
line_rows = run_line_levels(ctx, ax, ys, gaps, aspect, out_dir, args.repeat)
|
|||
|
|
|
|||
|
|
r_text = next((r["target_px"] for r in text_rows if r["readable"]), None)
|
|||
|
|
r_line = next((r["gap_px"] for r in line_rows if r["resolved"]), None)
|
|||
|
|
results.update({"text": text_rows, "line": line_rows,
|
|||
|
|
"R_text": r_text, "R_line": r_line})
|
|||
|
|
print(f"\n实测：R_text={r_text}px R_line={r_line}px")
|
|||
|
|
print("回填：dwg_review/config.py 的 TEXT_READABLE_PX / LINE_READABLE_PX")
|
|||
|
|
finally:
|
|||
|
|
if handles and not args.keep:
|
|||
|
|
out = result_json(ctx.tools.call("delete_entities", {"handles": handles}), {})
|
|||
|
|
print(f"\n清理标定物：删除 {out.get('count')} 个，失败 {len(out.get('failed') or [])} 个")
|
|||
|
|
elif handles:
|
|||
|
|
print(f"\n--keep：保留 {len(handles)} 个标定物（图层 {CALIB_LAYER}）")
|
|||
|
|
ctx.tools.call("zoom_extents", {})
|
|||
|
|
|
|||
|
|
(out_dir / "summary.json").write_text(
|
|||
|
|
json.dumps(results, ensure_ascii=False, indent=2), encoding="utf-8"
|
|||
|
|
)
|
|||
|
|
print(f"输出目录：{out_dir}")
|
|||
|
|
return 0
|
|||
|
|
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
raise SystemExit(main())
|