-
## 🐛 Bug
I see a table of different *default* behaviors for `log()`, which leads me to believe that if I want train/eval to have same behavior (e.g. reduction, frequency, etc.), I could just set th…
-
At the time of training, in the step "python tools/Train_HICO_DET_DJR.py --model --num_iteration 400000 "o, the value of loss in all of the images in NaN. why????
-
When I export my pytorch model to caffe model, I got bug as following:
Traceback (most recent call last):
File "caffe_export.py", line 22, in
from projects.bjzProject.projectbaseline i…
-
Hey! Thanks for your wonderful work!
Now i'm trying to reproduce the result of monodepth2 with resnet18 backbone. I used the train_kitti.yaml to train about 50 epochs. But the result is not good …
-
### Link Checker
Errors were reported while checking the connectivity of links.
```
CNAME
LICENSE
_posts/2009-11-14-British-Masters-Open-14-Nov-2009.md
_announcements/Christmas-training-pause.md
_anno…
-
Hi,
First off, really good work :) Is there any plans of adding the two stage training technique code? Is it handled as a post processing step by creating point clouds using depth estimates and app…
-
我在训练mgn网络时发现，相同超参下如果使用多卡训练，loss的下降速度明显变慢，最终效果会差比较多，考虑到可能是bn的问题，如果把backbone和heads中的bn换为syncBN也没有改善这个问题，请问有什么好的办法或经验使用多卡训练吗，谢谢
wbfor updated
3 years ago
-
Hello,
I'm trying to train a model with VelSupModel. And I find out that only single GPU is working. How to perform multi-GPU training? thx.
Mrils updated
3 years ago
-
My funannotate predict fails, apparently due to a missing hints file. How should I go about fixing this problem?
Best regards
Knud
Error
```
funannotate predict -i ${i}.masked.fa -o fun.predic…
-
I run the train_fold.py and meet the following problem when training.
`val_step() takes 2 positional arguments but 3 were given `
I have no idea what leads to this problem. In each step, we get a …