bev-project/执行此命令启动训练.txt

34 lines
1.6 KiB
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

═══════════════════════════════════════════════════════════════════
Task-specific GCA训练启动命令
═══════════════════════════════════════════════════════════════════
在Docker容器内依次执行以下3条命令:
1. docker exec -it bevfusion bash
2. cd /workspace/bevfusion
3. bash START_PHASE4A_TASK_GCA.sh
然后输入 'y' 确认启动
═══════════════════════════════════════════════════════════════════
启动后查看日志:
tail -f /data/runs/phase4a_stage1_task_gca/*.log
检查Task-specific GCA是否启用:
grep "Task-specific GCA mode enabled" /data/runs/phase4a_stage1_task_gca/*.log
═══════════════════════════════════════════════════════════════════
预期性能:
✅ 检测mAP: 0.68 → 0.70 (+2.9%)
✅ 分割mIoU: 0.55 → 0.61 (+11%)
✅ Divider Dice Loss: 0.525 → 0.420 (-20% = 变好!)
注: Dice Loss越低越好负数是改善
═══════════════════════════════════════════════════════════════════