Hacktoberfest 2026:维护者为十月标记出来的 issue,仍然开放、适合新手。 浏览 Hacktoberfest issue

Reproduce fine tuning but score poorly on the evaluation dataset

未关闭
#20 6 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
4/5
预计耗时
3-5 天
新手友好度
25/100
Issue 类型
缺陷
描述清晰度
需要澄清
活跃度
停滞
技术栈
bash, python

调研方向

Start with training/train.py and the train_marigold_e2e_ft_depth.sh configuration, then compare the reported arguments with the project's reproduction guidance. Re-run fine-tuning and evaluation on NYUv2, KITTI, ETH3D, ScanNet, and DIODE, and determine why the reproduced scores differ from the expected results.

由索引模型根据 Issue 内容生成。

描述

Hi,
Thanks to the author for the contribution, but I had some problems reproducing it.
Why do I get bad scores on the evaluation dataset when reproducing fine-tuning results on my RTX3090?
The scores are as follows:

Dataset AbsRel ↓ Delta_1 ↑
NYUv2 0.056 0.963
KITTI 0.092 0.928
ETH3D 0.064 0.961
ScanNet 0.062 0.956
DIODE 0.299 0.780

The following is the train script configuration I use, refer to train_marigold_e2e_ft_depth.sh:

Note.
The following are the modified parts:
--checkpointing_steps 500 => to store the best checkpoint
--dataloader_num_workers 4 => speed up training time
--mixed_precision "bf16" => reduce memory usage
--seed 1234 => fixed seed

The complete script is as follows:

#!/bin/bash

accelerate launch training/train.py \
--pretrained_model_name_or_path "prs-eth/marigold-v1-0" \
--modality "depth" \
--noise_type "zeros" \
--max_train_steps 20000 \
--checkpointing_steps 500 \
--train_batch_size 2 \
--gradient_accumulation_steps 16 \
--gradient_checkpointing \
--learning_rate 3e-05 \
--lr_total_iter_length 20000 \
--lr_exp_warmup_steps 100 \
--dataloader_num_workers 4 \
--mixed_precision "bf16" \
--output_dir "model-finetuned/marigold_e2e_ft_depth_bf16" \
--enable_xformers_memory_efficient_attention \
--seed 1234 \
"$@"
主要语言
Python
星标
521
派生
22
PR 合并指标
30 天内没有已合并 PR

环境准备

我们还没有检查这个项目的环境配置文件。先看它的 README,通用步骤见我们的新手贡献指南。

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

VisualComputingInstitute/diffusion-e2e-ft 的其他 Issue

查看 VisualComputingInstitute/diffusion-e2e-ft 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。