#!/bin/bash
# 使用最保守配置启动增强版训练
# workers_per_gpu=0 避免数据加载死锁

set -e

export PATH=/opt/conda/bin:$PATH

echo "=================================================="
echo "启动增强版训练（保守配置）"
echo "修复：GroupNorm替代BatchNorm"
echo"workers=0（避免数据加载死锁）"
echo "=================================================="

LOG_FILE="training_enhanced_safe_$(date +%Y%m%d_%H%M%S).log"

/opt/conda/bin/torchpack dist-run -np 8 /opt/conda/bin/python tools/train.py \
  configs/nuscenes/det/transfusion/secfpn/camera+lidar/swint_v0p075/multitask_enhanced_phase1_HIGHRES.yaml \
  --model.encoders.camera.backbone.init_cfg.checkpoint pretrained/swint-nuimages-pretrained.pth \
  --load_from runs/run-326653dc-74184412/epoch_19.pth \
  --data.samples_per_gpu 2 \
  --data.workers_per_gpu 0 \
  2>&1 | tee "$LOG_FILE"

echo "训练日志: $LOG_FILE"