-
`for dir_name in [
"train2017",
"test2017",
"train2017_base",
"train2017_novel",
"val2017_base",
"val2017_novel",
]:`
should be
`for di…
-
Hello, thanks to you, I'm using the mmdetection platform well.
Learning seems to be progressing, but I'm asking because some problems have occurred.
First, I changed the Cityscapes dataset to COCO…
-
### COCO is a large-scale object detection, segmentation, and captioning dataset. COCO has several features: Object segmentation, Recognition in context, Superpixel stuff segmentation, 330K images (>…
-
## Instructions To Reproduce the 🐛 Bug:
1. Full changes I have made:
```
def setup(args):
"""
Create configs and perform basic setups.
"""
cfg = get_cfg()
args.config_file …
-
I have a custom COCO dataset in object detection format with also the segmented masks for each instance.
What I want to do is to convert the COCO json file from object detection task to stuff task. …
-
#### 数据集名称与简介(Dataset Overview)
[Microsoft COCO](http://cocodataset.org/#home)
COCO is a large-scale object detection, segmentation, and captioning dataset. COCO has several features:
- Object se…
-
Hi, im try to train yolact to detect cars with images from COCO.
I take all of the images with cars in it and make dataset from them.
My config look like this:
`
only_cars_coco2017_dataset = datas…
-
I wanted to use the coco 2017 stuff dataset for training a semantic segmentation network,
but I found that in the png segmentation masks that coco provided seems to have 3 channels.
I would very muc…
-
## ❓ How to train Panoptic Segmentation on a custom dataset ?
Hello everyone,
My question is two-fold :
1. What is the expected Detectron2 format for Panoptic Segmentation ? In the PS paper, they…
-
In the tutorial https://cloud.google.com/tpu/docs/tutorials/mask-rcnn
```
cd /usr/share/ && python tpu/models/official/mask_rcnn/mask_rcnn_main.py \
--use_tpu=True \
--tpu=${TPU_NAME:?} \
--mod…