-
Hi @dbolya, congrats for the Yolact++. It seems great improvement.
Maybe this is trivial for you but I am a little bit stuck due to a confusion.
I wonder how can I get features from intermediate lay…
-
@dbolya -
1. I used your github and followed all the steps
-Cloned the repo
-downloaded the resnet..50 weights
-copied up my train and val images and annotations
-modified the config
And when …
-
IT IS NOT ISSUE.
JUST FOR NOTE AND SHARING.
UBUNTU 18.04 / RTX2080TI / 1080P VIDEO /
CUDA10.0 + CUDNN7.6.5 / PYTORCH 1.4.0 /
MODEL : yolact_resnet50_54_800000.pth
![image](https://user-images…
-
Hi!
I am trying to use your very useful software, SBeA. I have successfully loaded the provided case data, fig2_data, and output the processed data. However, When I try to click the "train model" but…
-
Hello @dbolya , thanks for the awesome implementation and the excellent paper. I am planning on modifying the YOLACT architecture to be compatible with aspect ratios other than squares, so as to prese…
-
As you talked about in the Yolov4 paper anchor-free methods seem a good technic. Why did you keep the anchors in yolov4? Could elaborate a little bit on this configuration.
-
hi Alex,Thanks for your great work. Is it possible to implement a segmentation network under Darknet?
-
When doing eval.py in YOLACT, I am trying to display by combining 5 classes into 2 classes.
ex) {cat, dog, cow, tree, flower} -> {animal(cat, dog, cow), plant(tree, flower)}
What should I do?
-
Hi,
I'm trying to get YOLACT(++) to work with a custom dataset using Google Colab because I don't have acces to a powerfull GPU myself. When I run `train.py` it loads the .json files from the `con…
-
I am thinking of using the same yolact model as initial model for training another dataset, or on the same coco dataset with adding other categories. Any idea how to start with that? Thanks.