[General Issue]只训练了一个epoch就自动停止了，也没报错

[19961115]

Thanks for your issue. To help us solve the issue better, please provide following information：

1. PaddleSeg version: (please specify the branch as well，e.g. PaddleSeg release/2.3)
2. PaddlePaddle version: (e.g. PaddlePaddle 2.1.0)
3. Operation system: (e.g. Linux/Windows/MacOS)
4. Python version: (e.g. Python3.6/7/8)
5. CUDA/cuDNN version: (e.g. CUDA10.2/cuDNN 7.6.5)
6. Additional context: (Add any other context about the problem)

---

欢迎您反馈PaddleSeg使用问题，辛苦您提供以下信息，方便我们快速定位和解决问题：

1. PaddleSeg版本：（请提供版本号和分支信息，如PaddleSeg release/2.3）
2. PaddlePaddle版本：（如PaddlePaddle 2.1.0）
3. 操作系统信息：（如Linux/Windows/MacOS）
4. Python版本号：（如Python3.6/7/8）
5. CUDA/cuDNN版本：（ 如CUDA10.2/cuDNN 7.6.5等）
6. 其他内容: （增加其他与问题相关的内容）

[juncaipeng]

麻烦将配置的yaml文件发出来看下。

[lyf6]

i have also met this problem. PaddleSeg版本：PaddleSeg release/2.5.0 PaddlePaddle版本：PaddlePaddle 2.3.0 操作系统信息：Windows Python版本号：Python3.6 CUDA/cuDNN版本：CUDA10.2/cuDNN 7.6 here is my config file: batch_size: 2 iters: 2000 loss: coef:

• 1
• 1
• 1 types:
• min_kept: 260000 type: OhemCrossEntropyLoss
• min_kept: 260000 type: OhemCrossEntropyLoss
• min_kept: 260000 type: OhemCrossEntropyLoss lr_scheduler: end_lr: 0 learning_rate: 0.001 power: 0.9 type: PolynomialDecay warmup_iters: 1000 warmup_start_lr: 1.0e-05 model: arm_out_chs:
• 32
• 64
• 128 backbone: pretrained: https://bj.bcebos.com/paddleseg/dygraph/PP_STDCNet1.tar.gz type: STDC1 seg_head_inter_chs:
• 32
• 64
• 64 type: PPLiteSeg optimizer: momentum: 0.9 type: sgd weight_decay: 0.0005 train_dataset: dataset_root: C:/Users/Administrator/Documents/ArcGIS/workdir ignore_index: 255 mode: train num_classes: 2 train_path: C:/Users/Administrator/Documents/ArcGIS/workdir\train.txt transforms:
• max_scale_factor: 1.2 min_scale_factor: 0.8 type: ResizeStepScaling
• crop_size:
  • 512
  • 512 type: RandomPaddingCrop
• type: RandomHorizontalFlip
• type: RandomVerticalFlip
• brightness_prob: 0.5 brightness_range: 0.3 contrast_prob: 0.5 contrast_range: 0.3 hue_prob: 0.5 hue_range: 15 saturation_prob: 0.5 saturation_range: 0.3 type: RandomDistort
• type: Normalize type: Dataset val_dataset: dataset_root: C:/Users/Administrator/Documents/ArcGIS/workdir mode: val num_classes: 2 transforms:
• type: Normalize type: Dataset val_path: C:/Users/Administrator/Documents/ArcGIS/workdir\train.txt

[lyf6]

I guess there is something wrong with the dataloader.