-
I found the training with DCN is unstable. Will you release some models or the training codes to train from scratch?
-
Thanks for the DCN impl. in caffe. I am curious about the performance of the baseline model w/o deform_conv. Besides, have you tried more complex model such as ResNet-101?
-
i cannot find dcn model in the leaderboard of squad2.0, could you show the f1 and em to compare?
-
if replace DCN with normal conv, How much performance drop does it make? such as resnet18, AP 28.1 will drop to ??
-
Hi，after downloading the dcn file from EDVR ,How to get the DCNv2 model file which has to be saved in .\ckpt\
-
Please tell me, I use the be command python tools/train.py configs/madet/madet_r101_fpn_1x_coco.py for training, but an error like this occurs, nexpected key in source state_dict: fc.weight, fc.bias
…
-
### What is the feature?
I would like use `DeformConv2d` in my model, and I find mmcv have a good implementation. So I used this module in my work as below.
~~~py
from mmcv.ops import DeformConv2…
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmrotate/issues) and [Discussions](https://github.com/open-mmlab/mmrotate/discussions) but cannot get the expected help.
…
-
Hi,
I'm a beginner in video restoration and I am a bit confused about the Alignment Study part in the paper (Section 5 & Section B.1 in the supp). For all the models listed in Table 1, which part …
-
hi xi11xi19,
i use your code and had convert .pth to .pt
then i want to test the .pt file, use :
module = torch::jit::load()
to load this model, i met this error:
terminate called after throwin…