#!/bin/bash
# 启动修复后的增强版训练
# 使用GroupNorm替换BatchNorm，解决分布式死锁问题

set -e

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

echo "=================================================="
echo "启动修复后的EnhancedBEVSegmentationHead训练"
echo "修复内容：BatchNorm2d → GroupNorm (15处)"
echo "配置：Phase1 高分辨率 + ASPP + 注意力机制"
echo "从epoch_19.pth加载backbone和encoder权重"
echo "=================================================="

# 创建日志文件
LOG_FILE="training_enhanced_fixed_$(date +%Y%m%d_%H%M%S).log"

# 启动训练
/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 4 \
  2>&1 | tee "$LOG_FILE"

echo ""
echo "训练完成！日志保存在: $LOG_FILE"