Which folder should I put the pretrained model dml_str_lapa.pth in?

Dear Author:
Thank you for open-source such a great work！
When testing pretrained models,I encountered the following problems：
After downloading dml_csr_lapa.pth,I have no idea which folder in my project to put in,so I creat a folder named snapshots and ran the folowing command:
```
python test.py --data-dir ./dataset/NeRSemble/ --out-dir ./output/ --restore-from ./snapshots/dml_csr_lapa.pth --gpu 0 --batch-size 7 --input-size 473,473 --dataset test --n
um-classes 19
```
Program error：
```
RuntimeError: Error(s) in loading state_dict for DML_CSR:
size mismatch for layer6.conv4.weight: copying a param with shape torch.Size([11, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([19, 256, 1, 1]).
size mismatch for layer6.conv4.bias: copying a param with shape torch.Size([11]) from checkpoint, the shape in current model is torch.Size([19]).
```
This demonstrates the folder information within my project.

Start with test.py and the reported --restore-from command, then compare the checkpoint's 11-channel layer6.conv4 tensors with the model configured for --num-classes 19. Check how the project expects pretrained files such as dml_csr_lapa.pth or dml_str_lapa.pth to be located; done means the compatible path and model configuration are clear.

Written by the indexing model from the issue text.