hsiangyuzhao / rcps Goto Github PK
View Code? Open in Web Editor NEWofficial implementation of rectified contrastive pseudo supervision
License: MIT License
official implementation of rectified contrastive pseudo supervision
License: MIT License
请问数据是怎么处理的呢?
您好,我在运行train.py时出现了以上的报错,可以请您帮忙看下是什么问题吗
Hello, I'm new in medical image segmentation and I wanna change ratio in la.cfg. So I wonder what cps_ratio and con_ratio mean in la.cfg? Or I just need change the ratio into 0.2?
At present, I am unable to obtain LA dataset. Can you share it with me? I will only be doing academic research, and this is my student email address [email protected]
你好,感谢您的工作和分享。在尝试复现你们工作时我需要申请对应环境的服务器,但是我没有在文档中看到代码的requirements,能麻烦您告知吗?
您好,我在前10个epoch的训练中,阶段性的得到了这样的结果,这是全监督还是半监督呢?
wandb: Run summary:
wandb: train/train_contrastive_l_loss_mean 0.98026
wandb: train/train_contrastive_u_loss_mean 1.18749
wandb: train/train_cosine_l_loss_mean 0.36995
wandb: train/train_cosine_u_loss_mean 0.49217
wandb: train/train_cps_l_loss_mean 1.59464
wandb: train/train_cps_u_loss_mean 2.29451
wandb: train/train_seg_loss_mean 5.00324
wandb: val/val_loss_mean 1.86493
wandb: val/val_metric_mean 0.6811
终端的部分输出如下:
Semi-Supervised Medical Image Segmentation Training
Mixed Precision - True; CUDNN Benchmark - True; Num GPU - 1; Num Worker - 8
successfully loaded config file: {'MODEL': {'PROJECT_DIM': 64, 'LEAKY': True, 'NORM': 'BATCH'}, 'TRAIN': {'LR': 0.01, 'MOMENTUM': 0.9, 'DECAY': 0.0001, 'BURN_IN': 5, 'BURN': 0, 'RAMPUP': 100, 'EPOCHS': 100, 'BATCHSIZE': 1, 'SEED': 42, 'RATIO': 0.1, 'LOSS_TYPE': 1, 'SAMPLE_NUM': 400, 'BUFFER_SIZE': 1, 'CPS_RATIO': 0.1, 'CON_RATIO': 0.1}, 'TEST': {'BATCHSIZE': 4}}
Task la prepared. Num labeled subjects: 8; Num unlabeled subjects: 72; Num validation subjects: 20
这里我把ratio设置为0.1,但我的数据文件夹是按照训练和验证,图像和标签,分为四个子文件夹的,且我没有将您在readme文档半监督训练需要进行替换的代码放进train.py文件,那么理论上应当按照全监督去训练。不过运行结果里显示还是有Num unlabeled subjects: 72。请问在全监督训练中是如何保证有标注图像中ratio以外的数据没有参与到训练中的呢?
期待您百忙之中的回答,祝您工作顺利,生活愉快。
你好,感谢您的工作和分享。您提供的LA数据集的链接无法打开,请问方便使用邮箱或者网盘给我一份吗?非常感谢!
我的邮箱号是[email protected]
Hello hsiangyuzhao! I saw the Figure 2 in your paper that has blue lines denote the predictions and I wonder how can I get that cut line after training my own mould? In other word, I wanna test the train mould I got and make some predictions. Is it mark red in the train_visualization?
Hi, thanks for your excellent work. When will you release the code?
请问数据集是怎么处理的呢?
Thank you for your If you encounter issues downloading the data, you may find the same data at : https://academictorrents.com/details/80ecfefcabede760cdbdf63e38986501f7becd49
Please note that the orientation of the data downloaded from this link is not correct, please correct them manually.
请问这里的 "correct them manually"具体指什么呢?
Hello,thanks for your sharing very much.When I tried to run the train.py,the Error always happened no matter how many Gpus I used. It is strange that different Gpus require different amounts of memory.The best Gpu I used is 4 NVIDIA A100 . Training is good but on the fifth iteration evaluation loop started, the error always arised. Do you know how to fix it?
Hello, how will I use a single card for training, and what are the commands?
Hi, thank you for the README update and congratulations to the acceptance!
What is the different between real semi-supervised scene and changing label ratios?
To make sure, when changing label ratios, the model didn't use the label to compute segmentation loss, isn't this the same as real semi-supervised scene?
A follow up question:
Will there be precision change (drop) when switching to real semi-supervised scene compared to the results reported on the paper?
Many Thanks.
Author, thank you for your work. But when I reproduced the code, I set the negative samples to N=100, but there is still a little gap between my results and your paper.
LA dataset:
bg_dice: 0.9896 ± 0.0049; la_dice: 0.8712 ± 0.0577; bg_hd95: 2.2933 ± 1.3194; la_hd95: 15.1779 ± 16.0119; bg_asd: 0.4185 ± 0.2263; la_asd: 3.6897 ± 3.3981;
Pancreas dataset:
bg_dice: 0.996 ± 0.0015; pancreas_dice: 0.7719 ± 0.0702; bg_hd95: 1.2585 ± 0.4075; pancreas_hd95: 12.1445 ± 10.8312; bg_asd: 0.2605 ± 0.1133; pancreas_asd: 2.8957 ± 1.3297;
Here is my training command:
CUDA_VISIBLE_DEVICES=0,1 torchrun --nproc_per_node=2 train.py --mixed --benchmark --task pancreas --exp_name pancreas --wandb
paper result:
你们好,首先非常感谢你们的工作!我想请问如果要尝试在自己的数据集上进行训练的话,需要改那些文件?我发现你们还没有提供对自己数据集的支持,但是非常想尝试用你们的模型试着跑跑实验看看分割效果
感谢:)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.