-
As mentioned above.
-
```
!python demo/demo.py \
--config-file configs/CondInst/MS_R_50_1x.yaml \
--input 00070.jpg \
--opts MODEL.WEIGHTS training_dir/CondInst_MS_R_50_1x/model_final.pth
```
The above …
-
Thank you for your outstanding work!
Where can I find your supplementary materials? I want to learn about the difference between your clustering algorithm and pointgroup~
-
| | |
| --- | --- |
| Bugzilla Link | [42085](https://llvm.org/bz42085) |
| Resolution | FIXED |
| Resolved on | Feb 20, 2021 13:02 |
| Version | trunk |
| OS | Windows NT |
| CC | @bmrzycki,@topper…
-
Thanks for making this great work open source.
but I have trained 255K steps from scratch , and the totaltext hmean is always 0. (Use 8 GPUS,Pretrain/testr_r50.yaml and all the parameters are def…
-
Hi,
I am using CondInst for Multi-class Instance Segmentation for a custom dataset.
Here is what the log for inference looks like from the bottom.
```
[01/04 11:01:25 d2.data.dataset_mapper]…
-
Hi, I trained the CondInst on a custom dataset for 3000 epochs.
**Training losses:**
```
[01/08 15:07:24 d2.utils.events]: eta: 0:00:00 iter: 2999 total_loss: 1.592 loss_fcos_cls: 0.2424 l…
-
https://github.com/zymk9/Yet-Another-Anime-Segmenter
-
https://github.com/aim-uofa/AdelaiDet/blob/7e4c503fce1765b9eeaa65422d40a39fb358fde6/adet/modeling/condinst/mask_branch.py#L71-L84
How much is the influence on performance for this operation?
-
Hi:
I follow the instructions of this repo to train ConInst with Base-CondInst config. However, I obtain very poor performance, anything is wrong?
![image](https://user-images.githubusercontent.…