Transfer-Learning-Library
Transfer-Learning-Library copied to clipboard
thuml
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] **Describe the solution you'd...
For fine-tune the unsupervised pre-trained model, Only the erm reult can be repeat, the co_tuning、bi_tuning accuray is lower than erm
我在阅读DAN时，注意到原文是一个minimax过程，在学习网络参数（\Theta）外，还需要学习多核权重（\beta）；而后者似乎未在此代码文件中体现，5个核被分配了相同的权重；我写了一个二次规划求核权重的函数，供参考讨论 :-) ` def train_weights(train_source_iter: DataLoader, train_traget_iter: DataLoader, model: ImageClassifier, kernels: list): print("=>Train Beta(weights) of the kernels") num_kernels = len(kernels) #协方差矩阵（原文中的矩阵Q） covar_matrix = torch.zeros((num_kernels, num_kernels)) for i in range(num_kernels): for...
```txt data/synthia ├── RGB ├── synthia_mapped_to_cityscapes └── ... ``` 我在那个官网上下载了 SYNTHIA-RAND-CITYSCAPES (CVPR16) 但里面没有这个文件，我之前跑的网络用的是上面这个数据及，但这个我看 UDA里面 synthia里面 readme有要这个文件
When i try to run source_only.py I get the error message "No module named 'tlllib.vision.models.object_detection.backbone.mmdetection'" If I try to import "tlllib.vision.models.object_detection" it seems that the error is in the file...
I try to run the same exact code, but I get this on all datasets.
Thank you for all the work you have done !! however, there are several environment problems about numpy, torchvision and so on. So i'm asking for the probability of listing...
The URL for PACS dataset seems not working any more. So could you please provide us with a valid URL that can let us download the datasets? Thanks!
报错内容如下： Traceback (most recent call last): File "dann.py", line 261, in main(args) File "dann.py", line 70, in main train_target_iter = ForeverDataIterator(train_target_loader) File "D:\soft\anaconda3\envs\pytorch_transfer_1.7.1\lib\site-packages\tllib-0.4-py3.8.egg\tllib\utils\data.py", line 45, in __init__ File "D:\soft\anaconda3\envs\pytorch_transfer_1.7.1\lib\site-packages\torch\utils\data\dataloader.py", line...
