zhaozhibin / udtl Goto Github PK

How did the author import the data set of Southeast University,After I import the data, filename only has a CSV file and nothing else can be found

Problem:

When using Python 3.9.0, the following error will occur:

AttributeError: '_SingleProcessDataLoaderIter' object has no attribute 'next'

Solution:

change line 260 target_inputs, _ = iter_target.next() in utils/train_utils_combines.py to target_inputs, _ = next(iter_target)

Thanks for your effort! This code helped me a lot : )

请问cruw的数据集的文件夹组织结构是什么样的

train_utils_combines文件中的torch.save代码应该放到所有epoch结束之后。torch.save前面的if循环条件中or后面的循环条件应该去除。

cwru_fft的时候出现维度不匹配，不知道怎么解决

stack expects each tensor to be equal size, but got [1, 15360] at entry 0 and [1, 15872] at entry 1

Hi Dr. Zhao,

I am trying to reproduce the results using your code, however, some of the dataset is not accessible. Can you please share the link to download the dataset "PHM_Society_2009_Competition_Expanded_txt.zip"? The original link on the PHM website is broken. Much appreciated!

Many thanks

self.classifier_layer = nn.Linear(self.model.output_num(), Dataset.class_num)
->
self.classifier_layer = nn.Linear(self.model.output_num(), Dataset.num_classes) ?

I can not find ‘class_num’, should it be replaced with 'num_classes'?

赵老师 我刚接触故障诊断以及机器学习算法 您所使用的CRWU数据集可以分享一下吗 在网上下载的数据集显示了很多格式错误

hello!!
i was runnimg the train_base.py i was not babe to find the 江南大学数据\数据/ib600_2.csv file and it is raising error "OSError: /tmp/D:/Data\江南大学数据\数据/ib600_2.csv not found." please could you guide me to find the .csv file?

当我在用CWRU数据集上由0到2迁移时，在middle epoch时报错：
Traceback (most recent call last):
File "E:\UDTL-master\train_advanced.py", line 88, in
trainer.train()
File "E:\UDTL-master\utils\train_utils_combines.py", line 286, in train
distance_loss = self.distance_loss([features.narrow(0, 0, labels.size(0)),
File "E:\UDTL-master\loss\JAN.py", line 44, in JAN
loss = torch.mean(XX + YY - XY - YX)
RuntimeError: The size of tensor a (20) must match the size of tensor b (64) at non-singleton dimension 1
在1迁移到2时则不会报错。
相应参数设置为：
04-09 11:14:17 model_name: resnet_mix_features_1d
04-09 11:14:17 data_name: CWRU
04-09 11:14:17 data_dir: E:\Data\CWRU
04-09 11:14:17 transfer_task: [[0], [2]]
04-09 11:14:17 normlizetype: mean-std
04-09 11:14:17 cuda_device: 0
04-09 11:14:17 checkpoint_dir: ./checkpoint
04-09 11:14:17 pretrained: False
04-09 11:14:17 batch_size: 64
04-09 11:14:17 num_workers: 0
04-09 11:14:17 bottleneck: True
04-09 11:14:17 bottleneck_num: 256
04-09 11:14:17 last_batch: False
04-09 11:14:17 distance_metric: True
04-09 11:14:17 distance_loss: JMMD
04-09 11:14:17 trade_off_distance: Step
04-09 11:14:17 lam_distance: 1
04-09 11:14:17 domain_adversarial: True
04-09 11:14:17 adversarial_loss: CDA
04-09 11:14:17 hidden_size: 1024
04-09 11:14:17 trade_off_adversarial: Step
04-09 11:14:17 lam_adversarial: 1
04-09 11:14:17 opt: adam
04-09 11:14:17 lr: 0.001
04-09 11:14:17 momentum: 0.9
04-09 11:14:17 weight_decay: 1e-05
04-09 11:14:17 lr_scheduler: step
04-09 11:14:17 gamma: 0.1
04-09 11:14:17 steps: 150, 250
04-09 11:14:17 middle_epoch: 5
04-09 11:14:17 max_epoch: 300
04-09 11:14:17 print_step: 50
04-09 11:14:17 using 1 gpus
麻烦赵老师有空帮我解答一下。非常感谢

赵老师 您好 麻烦请问一下 在标签不一致和多域模式下的UDTL 命令行代码怎么输入呢？ 我在train_advanced.py中并没有找到相关的输入参数
麻烦您解惑一下 万分感激

赵老师您好，您开源的代码对我帮助很大，十分感谢您。我在JN数据集上运行AdversarialNet网络，报了下面这个错，不知道如何解决，向您请教。再次感谢！
Traceback (most recent call last):
File "D:\Pycharmproject\TL\train_advanced.py", line 85, in
trainer.setup()
File "D:\Pycharmproject\TL\utils\train_utils_combines.py", line 64, in setup
self.model = getattr(models, args.model_name)(args.pretrained)
TypeError: init() missing 1 required positional argument: 'hidden_size'

When I used the CWRU data set, using the adversarial method, THERE would be 50 epoch errors
ValueError: Using a target size (torch.Size([128])) that is different to the input size (torch.Size([128, 1])) is deprecated. Please ensure they have the same size.
What can I do to fix it that doesn't happen when I use SEU data sets

您好！我在只修改数据集的情况下，报错Using a target size (torch.Size([128])) that is different to the input size (torch.Size([128, 1])) is deprecated. Please ensure they have the same size.请问您一下这是什么原因呢？非常感谢

When args.eval_all = False, is the for loop in line 170 and 160 duplicated?

after 1024 data, the source becomes 20 and the target becomes 64, not equal.
I am thinking it was the problem of dataloader

When using MMD, the 50th epoch will be wrong, because the dimension of Batch is not matched, your parser

parser.add_argument('--last_batch', type=bool, default=False, help='whether using the last batch')
drop_last=(True if args.last_batch and x.split('_')[1] == 'train' else False))
The default should be True