-
If you do not know the root cause of the problem / bug, and wish someone to help you, please
post according to this template:
## Instructions To Reproduce the Issue:
1. what changes you made (`…
-
Hello,
I am experiencing some odd behavior when trying to train on a custom dataset in COCO format. So far I have tried training faster-rcnn and retinanet models but the bbox loss is always zero. T…
-
i try to train htc
`python /mmdetection/tools/train.py 'htc_hrnetv2p_w18_20e_coco.py'`
and this is the config file
```
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = …
-
- problem: I'm trying to load a custom COCO-style dataset, following the tutorial:
https://detectron2.readthedocs.io/tutorials/datasets.html
- I think the issue might be in the dependency `pycocoto…
-
I meet a ERROR when I trained my custom dataset whose format is COCO.
I browsed some **issues** but them couldn't help me solve this problem.
# My config file
```python
_base_ = './faster_rcnn/f…
-
After updating to v2.5.0, training faster_rcnn model on customized dataset (COCO-like format) seem to have broken. The validation accuracy does stays close to 0 starting at the second epoch and stays …
-
I tried training the mask rcnn with both detectron2 and mmdetection and the training speed gap is huge
mmdetection offers a lot of preimplemented models that I want to run my tests with but I'm st…
-
## ❓ Questions and Help
So let's say that I have trained a model on keypoints or instance segmentation with datasets that are on coco-format, and used that trained model to get some outputs (Infere…
-
python tools/train.py configs/st_bottle_models/cascade_models/cascade_rcnn_r50_caffe_fpn_mstrain_3x_diou_coco.py
2020-11-18 21:18:30,386 - mmdet - INFO - Environment info:
--------------------------…
-
hi,i'm trying to implement **mask_rcnn** on **colab** for a **custom dataset(GWHD)** provided in coco style(json file) with config below:
> model = dict(
> type='MaskRCNN',
> pretrained='…