u52f85420
04bf90c09b
- 新增 irstd 核心包、scripts、tests、configs - 新增研究文档：literature_review / mathematical_analysis / novelty_matrix / experiment_plan / research_decision / research_log / manuscript_outline - 新增 evidence、results 数据与审计产物 - 新增 pyproject.toml、requirements、.gitignore
25 lines
1.6 KiB
Python
25 lines
1.6 KiB
Python
import argparse,json
|
|
from collections import Counter
|
|
from pathlib import Path
|
|
import numpy as np
|
|
from irstd.data import read_manifest,read_pair,sha
|
|
from irstd.core import components,centers
|
|
|
|
def main():
|
|
p=argparse.ArgumentParser();p.add_argument('--manifest',required=True);p.add_argument('--out',required=True);a=p.parse_args()
|
|
rows=read_manifest(a.manifest);areas=[];dist=[];sizes=Counter();counts=[];empty=0
|
|
for r in rows:
|
|
x,y=read_pair(r);ms=components(y);areas.extend(int(m.sum()) for m in ms);counts.append(len(ms));empty+=not len(ms)
|
|
sizes[str(x.shape)]+=1;c=centers(ms)
|
|
if len(c)>1:
|
|
d=np.linalg.norm(c[:,None]-c[None,:],axis=-1);np.fill_diagonal(d,np.inf);dist.extend(d.min(1).tolist())
|
|
def quant(v):return dict(zip(['min','q25','median','q75','max'],map(float,np.quantile(v,[0,.25,.5,.75,1])))) if v else None
|
|
result=dict(manifest_sha256=sha(a.manifest),splits=dict(Counter(r['split'] for r in rows)),
|
|
groups=len(set(r['group'] for r in rows)),resolutions=dict(sizes),empty_images=empty,
|
|
target_area_pixels=quant(areas),targets_per_image=quant(counts),nearest_target_distance=quant(dist),
|
|
area_bins={'1-4':sum(1<=v<=4 for v in areas),'5-9':sum(5<=v<=9 for v in areas),'10-25':sum(10<=v<=25 for v in areas),'26+':sum(v>=26 for v in areas)},
|
|
image_hashes={r['id']:sha(r['image']) for r in rows},mask_hashes={r['id']:sha(r['mask']) for r in rows},
|
|
limitations='Does not verify licensing, missing annotations, visual near-duplicates, source identities, or independence.')
|
|
Path(a.out).write_text(json.dumps(result,indent=2))
|
|
if __name__=='__main__':main()
|