Weird border artifacts when training a CNN

I’ve been trying to use this DeepLabv3+ implementation with my dataset (~1000 annotated images of the same box, out of the same video sequence): https://github.com/srihari-humbarwadi/person_segmentation_tf2.0 But I get border artifacts like this: Any ideas what could be causing it? Note that if I use bigger batches and train for more epochs, the borders tend to…

Weird border artifacts when training a CNN

I’ve been trying to use this DeepLabv3+ implementation with my dataset (~1000 annotated images of the same box, out of the same video sequence): https://github.com/srihari-humbarwadi/person_segmentation_tf2.0 But I get border artifacts like this: Any ideas what could be causing it? Note that if I use bigger batches and train for more epochs, the borders tend to…

Weird border artifacts when training a CNN

I’ve been trying to use this DeepLabv3+ implementation with my dataset (~1000 annotated images of the same box, out of the same video sequence): https://github.com/srihari-humbarwadi/person_segmentation_tf2.0 But I get border artifacts like this: Any ideas what could be causing it? Note that if I use bigger batches and train for more epochs, the borders tend to…

Which deep earning framework is highly recommended to get professional in computer vision community?

I have tried to get the basic grasp of the following deep learning frameworks with python: Keras Pytorch Caffe However, I have lately noticed that people in computer vision community care less and less about Caffe as being somehow unpopular these days apart from its easy implementation and learning pace. Can anyone suggest a good…