-
While im trying to do a training on Faster RCNN (faster_rcnn_r50_caffe_fpn_mstrain_3x_coco_20210526_095054-1f77628b.pth) with my own custom dataset which i transformed into COCO format, i receive this…
-
When fine-tuning with following config:
```
import datetime
from detrex.config import get_config
from .models.dino_swin_large_384 import model
# number of classes
model.num_classes = 1
…
-
**Checklist**
1. I have searched related issues but cannot get the expected help.
2. I have read the [FAQ documentation](https://mmdetection.readthedocs.io/en/latest/faq.html) but cannot get the e…
-
Replace the seesaw loss function into a two-stage object detection model results in an error.
Question：1.How do I replace the sesaw loss function for the two-stage object detection model?
…
-
在使用dist_test.sh进行infer的时候报这个错误改怎么处理呢
```
Traceback (most recent call last):
File "/root/factory/mmdetection2_16/mmdet2.16/tools/test.py", line 264, in
main()
File "/root/factory/mmdetect…
-
I am evaluating the performance on different image ( people crowd ), the detection abilities on people are significatly lower than v3, as an example this image ( using web demo ):
[YOLOV3] ./darkne…
-
I get the following error:
```
file "/opt/conda/lib/python3.8/site-packages/torch/nn/functional.py", line 2805, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight,…
-
Hi,
I have a new dataset and I prepared coco-like annotations for instance level semantic segmentation task. When I want to train Mask RCNN on my own data, I get following error. I am wondering wha…
-
How can I calculate F1-score for instance segmentation task on my custom COCO dataset?
I want to calculate it at every IoU treshold, at maxDets and at max area range.
So diving into accumulate() fun…
-
Running detection2panoptic_coco_format.py first fails on untouched fresh unzipped coco-things
```
ubuntu@XXXXX:~/GitRepos/panopticapi$ python3 converters/detection2panoptic_coco_format.py --input…