kirl
a64690477a
- Add README.md to all 16 dataset directories with script references - Centralize generation scripts under scripts/ with full README - Update .gitignore to cover all data directories, keep only metadata - Remove redundant CCPD/.gitignore (parent covers same rules) - Remove stale scripts/test/ (254MB pipeline residue) - Fix label parser reference: scripts are authoritative source of truth
65 lines
2.3 KiB
Python
65 lines
2.3 KiB
Python
#!/usr/bin/env python3
|
|
"""322K Pipeline Step 2-4: EXP_CUT -> TRANS -> Train"""
|
|
import os, sys, shutil, subprocess
|
|
from pathlib import Path
|
|
|
|
ICE = Path(r'C:\Users\Kirl\Desktop\ICEv2\ICE_Dataset')
|
|
PY = r'C:/Program Files/Python313/python.exe'
|
|
NN = Path(r'C:\Users\Kirl\Desktop\ICEv2\ICE_NNv2')
|
|
|
|
DATASET = ICE / 'CCPD_322K'
|
|
EXP_CUT = ICE / 'CCPD_322K_EXP_CUT'
|
|
TRANS = ICE / 'CCPD_322K_EXP_CUT_TRANS'
|
|
|
|
def run(cmd):
|
|
print(f" {str(cmd)[:150]}...")
|
|
if isinstance(cmd, list):
|
|
r = subprocess.run(cmd)
|
|
else:
|
|
r = subprocess.run(cmd, shell=True)
|
|
if r.returncode != 0: print(f" FAILED ({r.returncode})"); sys.exit(1)
|
|
|
|
# ===== Step 2: EXP_CUT =====
|
|
print("===== 2/4 EXP_CUT =====")
|
|
shutil.rmtree(EXP_CUT, ignore_errors=True)
|
|
EXP_CUT.mkdir(parents=True)
|
|
|
|
exp_py = ICE / 'CCPD_19K_EXP_CUT' / 'build_ccpd_19k_exp_cut.py'
|
|
code = exp_py.read_text(encoding='utf-8')
|
|
code = code.replace(
|
|
'SRC_DIR = PROJ_ROOT / "ICE_Dataset" / "CCPD_19K" # 源数据集',
|
|
f'SRC_DIR = Path(r"{DATASET}")')
|
|
code = code.replace(
|
|
'DST_DIR = SCRIPT_DIR # 本目录 (CCPD_19K_EXP_CUT)',
|
|
f'DST_DIR = Path(r"{EXP_CUT}")')
|
|
tmp = ICE / 'scripts' / '_e.py'
|
|
tmp.write_text(code, encoding='utf-8')
|
|
run([PY, str(tmp), '--full'])
|
|
tmp.unlink()
|
|
print(f" Images: {sum(1 for _ in EXP_CUT.rglob('*.jpg'))}")
|
|
|
|
# ===== Step 3: TRANS =====
|
|
print("===== 3/4 TRANS =====")
|
|
shutil.rmtree(TRANS, ignore_errors=True)
|
|
TRANS.mkdir(parents=True)
|
|
|
|
trans_py = ICE / 'CCPD_19K_EXP_CUT_TRANS' / 'build_ccpd_19k_exp_cut_trans.py'
|
|
code = trans_py.read_text(encoding='utf-8')
|
|
code = code.replace(
|
|
'SRC_DIR = PROJ_ROOT / "ICE_Dataset" / "CCPD_19K_EXP_CUT" # 源数据集',
|
|
f'SRC_DIR = Path(r"{EXP_CUT}")')
|
|
code = code.replace(
|
|
'DST_DIR = PROJ_ROOT / "ICE_Dataset" / "CCPD_19K_EXP_CUT_TRANS"',
|
|
f'DST_DIR = Path(r"{TRANS}")')
|
|
tmp = ICE / 'scripts' / '_t.py'
|
|
tmp.write_text(code, encoding='utf-8')
|
|
run([PY, str(tmp), '--full'])
|
|
tmp.unlink()
|
|
print(f" Images: {sum(1 for _ in TRANS.rglob('*.jpg'))}")
|
|
|
|
# ===== Step 4: Training =====
|
|
print("===== 4/4 Training =====")
|
|
os.chdir(str(NN / 'ICE-OCR'))
|
|
run([PY, 'script/train.py', '--dataset', 'ccpd_trans', '--epochs', '100', '--batch', '128', '--output', 'ccpd_322k_best.pth', '--workers', '2', '--data-dir', str(TRANS)])
|
|
print("DONE")
|