-
when I load the pretrained model which is downloaded from
http://vllab.ucmerced.edu/ytsai/CVPR18/DeepLab_resnet_pretrained_init-f81d91e8.pth
then `torch.load()` will report an error
```
Tra…
-
Greetings！
I read your paper again and again recently, and I really learned a lot from your work. For the retrain part, I met some problems, would you like to help to answer?
At first, I noticed…
-
Improve the [current flood segmentation model](https://github.com/cc-ai/deeplab-pytorch) , see #62
We report below a comparison of a first series of flood segmentation models using mIoU on our han…
-
No module named 'torchvision.models.utils'
For all the people who have this error, just replace "from torchvision.models.utils import load_state_dict_from_url" by "from torch.hub import load_state_…
-
Would you tell me how did you get the models mentioned in 3.Download, about initializing the VGG-based DeepLab-LargeFOV network.
and initializing the ResNet-based DeepLab-LargeFOV.
Do they come fro…
-
When I run the following line:
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --backbone resnet --lr 0.007 --workers 4 --epochs 50 --batch-size 16 --gpu-ids 0,1,2,3 --checkname deeplab-resnet --eval-…
-
Hi author,
thanks for your impressive work. Anyhow I met an issue by run train_planenet.py with a pretrained deeplab model.
The model is downloaded from this page https://github.com/DrSleep/tensor…
-
## Reference
- [Github repo](https://github.com/tensorflow/models/tree/master/research/deeplab)
- [Project - DeepLab](http://liangchiehchen.com/projects/DeepLab.html)
- [DeepLab: Models](http:/…
-
I retrain the deeplab part and the result is 61% for baseline while 66% for dcn. This is a lot below the official result. I only changed the gpu to 2 and remove the multiprocess in loader. Anyone know…
-
**AssertionError happened when I run train_voc.sh, but I don't know how to solve this problem:**
Namespace(backbone='resnet', base_size=513, batch_size=16, checkname='deeplab-resnet', crop_size=513…