hilab-git/dag4mia

Domain Adaptation and Generalization for Medical Image Analysis

dag4mia's Issues

The exception of consistency loss

During the training process, the consistency loss is getting bigger and bigger, and the other losses are getting smaller and smaller. Is it normal? Is it what we expect?

            consistency_loss = 0
            consistency_weight = get_current_consistency_weight(iter_num//len(loader_train_s), max_epoch)
            consistency_dist = consistency_criterion(predout_t[train_params['labeled_bs']:], ema_output)    #(batch, 3, 256, 256)
            consistency_dist = torch.mean(consistency_dist)
            consistency_loss = consistency_dist * consistency_weight

🐱‍👤

cscada_net.py code has error

hello, First of all, thank you very much for opening up the source code, but I found a problem in your code
line 64 code: up_4 = self.up4(conv4, center, domain_label)
but up4 code in line 130: def forward(self, down_outputs, domain_label): only has 3 position, up4(conv4, center, domain_label) + self has 4 postion, not match

我代码运行过程中出现了错误

raise IndexError('index {} is out of range'.format(idx))
IndexError: index 1 is out of range

出现问题的地方实在container.py中：
def _get_abs_string_index(self, idx):
"""Get the absolute index for the list of modules"""
idx = operator.index(idx)
print(idx)
if not (-len(self) <= idx < len(self)):#这里
raise IndexError('index {} is out of range'.format(idx))
if idx < 0:
idx += len(self)
return str(idx)

sdnet没有

跪求大佬上传sdnet 如果不方便 麻烦私发[email protected]

sdnet没有

from models.networks.sdnet import MEncoder, AEncoder, Segmentor, Ada_Decoder
这个无法导入，请问作者这个sdnet您能上传一下吗。谢谢！

关于MS-CMRSeg 2019 datasets

作者你好，这个怎么处理这个数据集啊？

sdnet没有

could you share the code?

missing the main network architecture sdnet.py

Hi, could you release the most important part sdnet.py?

没有 sdnet

你好，这个是缺少一个文件吧？

“from models.networks.sdnet import MEncoder, AEncoder, Segmentor, Ada_Decoder
ModuleNotFoundError: No module named 'models.networks.sdnet' ”

train_cddsa.py

from utils import ramps,losses 报错

we find no ramps.py in utils, so i have question about how can get this part of ramps

请问超参数num_domains=1是正确的吗，为什么但我设置num_domains=1报错了，设置为=2没问题

报错内容：
Traceback (most recent call last):
File "/home/compare/train_3d_DAG4MIA.py", line 295, in
seg_pred_t, high_r_t_tb = model(img_t, domain_label=1)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 171, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 181, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/parallel_apply.py", line 89, in parallel_apply
output.reraise()
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/_utils.py", line 644, in reraise
raise exception
IndexError: Caught IndexError in replica 0 on device 0.
Original Traceback (most recent call last):
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/parallel_apply.py", line 64, in _worker
output = module(*input, **kwargs)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/compare/models/networks/cscada_net.py", line 62, in forward
conv1 = self.conv1(x, domain_label)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/compare/models/networks/cscada_net.py", line 106, in forward
x = self.bn(x, domain_label)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/compare/models/layers/dsbn.py", line 28, in forward
bn = self.bns[domain_label]
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/container.py", line 295, in getitem
return self._modules[self._get_abs_string_index(idx)]
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/container.py", line 285, in _get_abs_string_index
raise IndexError('index {} is out of range'.format(idx))
IndexError: index 1 is out of range