Chengfang Lu
e72bc061c5
Major changes: - New frontend (platform/web/): Vite + React 18 + TypeScript + Tailwind - 4-module navigation: 数据送标 / 模型管理 / 车队管理 / 系统管理 - Data catalog with charts (DMS/ADAS/Lane 3-tab view) - Quality review workflow (标注质检): Good/Fine/Bad scoring with auto-advance - Audit enhancements: batch operations, rejection categories, Feishu notifications - Operation audit log (操作日志) - World model simulation studio (仿真工坊) - Dataset version management with snapshots and diff - ADAS 7-class dataset integration (138K images organized + compressed) - User management with Feishu integration and pagination - CRUD/search/filter on all pages, card layout redesign - PIL-optimized image overlay rendering - Auto-snapshot on build, in_review workflow stage - Removed embedded algorithm code (now in workspace)
26 lines
703 B
Bash
26 lines
703 B
Bash
#!/bin/bash
|
|
backend="cpp" # or python
|
|
echo experiment name: $1
|
|
echo status: $2
|
|
echo save dir: $3
|
|
|
|
if [ "${backend}" = "cpp" ]; then
|
|
cd tools/culane_evaluation
|
|
else
|
|
echo Although python version works, we still suggest using the official Cpp version when possible!
|
|
echo At least try them when you are writing a paper.
|
|
echo Cpp and Python backends yield slightly different results.
|
|
cd tools/culane_evaluation_py
|
|
fi
|
|
|
|
if [ "$2" = "test" ]; then
|
|
# Perform test with official scripts
|
|
./eval.sh $1 $3
|
|
# Calculate overall F1 score
|
|
python cal_total.py --exp-name=$1 --save-dir=$3
|
|
else
|
|
# Perform validation with official scripts
|
|
./eval_validation.sh $1 $3
|
|
fi
|
|
cd ../../
|