-
- Dimensions mismatch
```
Config '/opt/detectron2/projects/CenterMask2/configs/centermask/centermask_lite_V_19_slim_dw_eSE_FPN_ms_4x.yaml' has no VERSION.
Assuming it to be compatible with lates…
-
I am following the Mask R-CNN tutorial and changed the dataset_dict to support segmentation maps in bitmap format using RLE instead of polygons. I confirmed the data is processed properly using detect…
-
@youngwanLEE
- I trained both `centermask_V_39_eSE_FPN_ms_3x` and `centermask_lite_V_19_slim_dw_eSE_FPN_ms_4x`
- After ~70,000 iterations, the results were bad, and the `total_loss` doesn't stabi…
-
Hi! Got the error `FloatingPointError: Loss became infinite or NaN at iteration=137!`
Any help is applicable! Thanks!
```
-- Process 1 terminated with the following error:
Traceback (most rece…
-
Now I am using python 3.6, pytorch 1.5.0 and detectron2 v0.2. The problem that I encounter is that the centermask2 model now import a file that the detectron2 v 0.2 does not have:
centermask2/center…
-
微博内容精选
-
When I run "python train_net.py --config-file "configs/centermask/centermask_lite_V_39_eSE_FPN_ms_4x.yaml" --num-gpus 8 ", it can not find the coco json file.
-
Hello,
I am trying to implement CenterMask2 [https://github.com/youngwanLEE/centermask2](url) which makes use of Detectron2.
My annotations are in COCO RLE format, my data registration is success…
-
Hi!
I would like to build a one-stage instance segmentation model using a SWIN backbone and FCOS object detection.
My own tries to get this to work has fallen flat and any input on how to construc…
-
Hi, I'm trying to export [centermask2](https://github.com/youngwanLEE/centermask2) to onnx. It's a FCOS head + maskhead. I did some modifications for using caffe2_converter.py. It seems I cannot use t…