-
Several image datasets (see examples below) contain segmentated images. Segmentated images contain multiple target labels. That means an instance has mutliple associated classes and not just one.
In …
NMO13 updated
6 years ago
-
Hey! Paul might share this too: a pipeline produces multiple kwcoco datasets for the same set of videos, with frame-wise activity classification ground truth, pose detection, and some object detection…
-
-
I am attempting to train on 2017 coco data. There is no valminusminival2017.json file.
The instances_valminusminival json files are for 2014 data only. There isn't one for 2017 data. I am guessing…
-
there is no file of annotations ,what's the matter?
.
How can I create such kind of masks for COOCEval?
I have tried feed in empty segmentation, i.e.…
-
I try to evaluate a trained keypoint detection model with the coco-evaluation in python. The result-dataset need to have a "score" of type float (see http://cocodataset.org/#format-results - Point "2.…
-
from the official coco website
Images
2014 Train images [83K/13GB]
2014 Val images [41K/6GB]
2014 Test images [41K/6GB]
2015 Test images [81K/12GB]
2017 Train images [118K/18GB]
2017 Val imag…
-
Hello, this is a wonderful work and I want to reproduce the results. But it seems that some pre-trained model or code is missing and the compilation fails. The details are as follows:
1. /mmdet/model…
-
when should you upload your model into [https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md](url) so we can easily use pre-trained weights to train …