Unet训练验证时，MIOU为0，precission为0，recall为0，Kappa为0。

[SweepingMonkWWW]

当使用unet模型训练验证时，MIOU为0，precission为0，recall为0，Kappa为0。配置文件相同，其他模型均正常，请问是什么原因？

[SweepingMonkWWW]

保证数据集一致，配置文件一致，利用其他模型训练时则正常，unet训练就不行。下图为其他模型评估时的结果。

[SweepingMonkWWW]

相关配置文件如下 base: '../base/cityscapes.yml'

batch_size: 2 iters: 1000

model: type: UNetPlusPlus in_channels: 3 num_classes: 2 use_deconv: False align_corners: False pretrained: Null is_ds: True

batch_size: 2 iters: 80000

train_dataset: type: Dataset dataset_root: data/positive_data train_path: data/positive_data/train_list.txt num_classes: 2 mode: train transforms:

• type: ResizeStepScaling min_scale_factor: 0.5 max_scale_factor: 2.0 scale_step_size: 0.25
• type: RandomPaddingCrop crop_size: [512, 512]
• type: RandomHorizontalFlip
• type: RandomDistort brightness_range: 0.5 contrast_range: 0.5 saturation_range: 0.5
• type: Normalize

val_dataset: type: Dataset dataset_root: data/positive_data val_path: data/positive_data/val_list.txt num_classes: 2 mode: val transforms:

• type: Normalize

optimizer: type: sgd momentum: 0.9 weight_decay: 4.0e-5

lr_scheduler: type: PolynomialDecay learning_rate: 0.01 end_lr: 0 power: 0.9

loss: types:

• type: CrossEntropyLoss coef: [1]

[wuyefeilin]

只训练了1000iter，太短了，模型还不能收敛，训练长一些

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.