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
86 lines
3.7 KiB
PowerShell
86 lines
3.7 KiB
PowerShell
# 322K 全自动流水线: 构建数据集 → EXP_CUT → TRANS → 训练
|
|
$ErrorActionPreference = "Continue"
|
|
$PY = "C:/Program Files/Python313/python.exe"
|
|
$ICE = "C:\Users\Kirl\Desktop\ICEv2\ICE_Dataset"
|
|
$NN = "C:\Users\Kirl\Desktop\ICEv2\ICE_NNv2"
|
|
|
|
# ===== Step 1: Build CCPD_322K =====
|
|
Write-Host "`n===== 1/4 构建 CCPD_322K =====" -ForegroundColor Cyan
|
|
|
|
$SRC_SPE = "$ICE\CCPD_SPE\ccpd_base"
|
|
$SRC_RND = "$ICE\CCPD_Random_Blue150K_Green100K"
|
|
$DST = "$ICE\CCPD_322K"
|
|
|
|
if (Test-Path $DST) { Remove-Item -Recurse -Force $DST }
|
|
New-Item -ItemType Directory "$DST\train" -Force | Out-Null
|
|
New-Item -ItemType Directory "$DST\test" -Force | Out-Null
|
|
|
|
# SPE 9类 (9:1 split)
|
|
$types = @('police','army','gangao','shiguan_old','shiguan_new','lingguan_old','lingguan_new','coach','new_energy')
|
|
foreach ($t in $types) {
|
|
$src = "$SRC_SPE\$t"
|
|
if (-not (Test-Path $src)) { Write-Host " SKIP $t"; continue }
|
|
$files = Get-ChildItem $src -Filter *.jpg | Sort-Object Name
|
|
$n = $files.Count
|
|
$nTrain = [math]::Floor($n * 0.9)
|
|
for ($i = 0; $i -lt $n; $i++) {
|
|
$split = if ($i -lt $nTrain) { "train" } else { "test" }
|
|
$d = "$DST\$split\$t"; New-Item -ItemType Directory $d -Force | Out-Null
|
|
Copy-Item $files[$i].FullName "$d\" -Force
|
|
}
|
|
Write-Host " $t : $n (train=$nTrain test=$($n-$nTrain))"
|
|
}
|
|
|
|
# Random蓝绿 (9:1 split)
|
|
foreach ($t in @('blue','green')) {
|
|
$src = "$SRC_RND\$t"
|
|
if (-not (Test-Path $src)) { Write-Host " SKIP $t"; continue }
|
|
$files = Get-ChildItem $src -Filter *.jpg | Sort-Object Name
|
|
$n = $files.Count
|
|
$nTrain = [math]::Floor($n * 0.9)
|
|
for ($i = 0; $i -lt $n; $i++) {
|
|
$split = if ($i -lt $nTrain) { "train" } else { "test" }
|
|
$d = "$DST\$split\$t"; New-Item -ItemType Directory $d -Force | Out-Null
|
|
Copy-Item $files[$i].FullName "$d\" -Force
|
|
}
|
|
Write-Host " $t : $n (train=$nTrain test=$($n-$nTrain))"
|
|
}
|
|
|
|
$total = (Get-ChildItem $DST -Recurse -Filter *.jpg).Count
|
|
Write-Host " TOTAL: $total" -ForegroundColor Green
|
|
|
|
# ===== Step 2: EXP_CUT =====
|
|
Write-Host "`n===== 2/4 YOLO EXP_CUT =====" -ForegroundColor Cyan
|
|
$EXP_CUT = "$ICE\CCPD_322K_EXP_CUT"
|
|
if (Test-Path $EXP_CUT) { Remove-Item -Recurse -Force $EXP_CUT }
|
|
|
|
# Patch the build script with our paths
|
|
$script = Get-Content "$ICE\CCPD_19K_EXP_CUT\build_ccpd_19k_exp_cut.py" -Raw -Encoding UTF8
|
|
$script = $script -replace 'SRC_DIR = PROJ_ROOT / "ICE_Dataset" / "CCPD_19K"', "SRC_DIR = Path(r'$DST')"
|
|
$script = $script -replace 'DST_DIR = PROJ_ROOT / "ICE_Dataset" / "CCPD_19K_EXP_CUT"', "DST_DIR = Path(r'$EXP_CUT')"
|
|
$tmp = "$ICE\scripts\_exp_cut_322k.py"
|
|
[System.IO.File]::WriteAllText($tmp, $script, [System.Text.UTF8Encoding]::new($false))
|
|
& $PY $tmp --full
|
|
Remove-Item $tmp
|
|
|
|
# ===== Step 3: TRANS =====
|
|
Write-Host "`n===== 3/4 ICE-COR TRANS =====" -ForegroundColor Cyan
|
|
$TRANS = "$ICE\CCPD_322K_EXP_CUT_TRANS"
|
|
if (Test-Path $TRANS) { Remove-Item -Recurse -Force $TRANS }
|
|
|
|
$script = Get-Content "$ICE\CCPD_19K_EXP_CUT_TRANS\build_ccpd_19k_exp_cut_trans.py" -Raw -Encoding UTF8
|
|
$script = $script -replace 'SRC_DIR = PROJ_ROOT / "ICE_Dataset" / "CCPD_19K_EXP_CUT"', "SRC_DIR = Path(r'$EXP_CUT')"
|
|
$script = $script -replace 'DST_DIR = PROJ_ROOT / "ICE_Dataset" / "CCPD_19K_EXP_CUT_TRANS"', "DST_DIR = Path(r'$TRANS')"
|
|
$tmp = "$ICE\scripts\_trans_322k.py"
|
|
[System.IO.File]::WriteAllText($tmp, $script, [System.Text.UTF8Encoding]::new($false))
|
|
& $PY $tmp --full
|
|
Remove-Item $tmp
|
|
|
|
# ===== Step 4: Training =====
|
|
Write-Host "`n===== 4/4 ICE-OCR Training =====" -ForegroundColor Cyan
|
|
Write-Host " Data: $TRANS"
|
|
Write-Host " Launching..."
|
|
& $PY "$NN\ICE-OCR\script\train.py" --dataset ccpd_trans --epochs 100 --batch 128 --output ccpd_322k_best.pth --workers 2 --data-dir $TRANS
|
|
|
|
Write-Host "`n===== DONE =====" -ForegroundColor Green
|