search

jlcsilva / EfficientUNetPlusPlus

Decoder architecture based on the UNet++. Combining residual bottlenecks with depthwise convolutions and attention mechanisms, it outperforms the UNet++ in a coronary artery segmentation task, while being significantly more computationally efficient.
https://arxiv.org/abs/2106.11447
MIT License
64 stars 10 forks source link

erros when training #5

Open Yilp opened 2 years ago

Yilp commented 2 years ago

Hello,Sir!

Thanks for your sharing! But I encountered some difficulties when I trained the model using my own data.

Could you give me some advice? Thanks! Best Wishes！ ''' Traceback (most recent call last): File "C:\Users\Admin\Desktop\EfficientUNetPlusPlus\train.py", line 198, in training_set = CoronaryArterySegmentationDataset(args.train_img_dir if args.train_img_dir is not None else 'Coronary/train/imgs/', TypeError: init() got an unexpected keyword argument 'crop_size' '''

jiangyuqiswpu commented 1 year ago

Me too. Have you solved it now？

Yilp commented 1 year ago

去掉crop_size代码就能运行了

------------------ 原始邮件 ------------------ 发件人: "jlcsilva/EfficientUNetPlusPlus" @.>; 发送时间: 2023年3月13日(星期一) 下午4:34 @.>; @.**@.>; 主题: Re: [jlcsilva/EfficientUNetPlusPlus] erros when training (Issue #5)

Me too. Have you solved it now？

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>