yolact
yolact copied to clipboard
dbolya
A simple, fully convolutional model for real-time instance segmentation.
hello. I have three questions regarding the yolact model. 1. Mask R-CNN performs instance segmentation by putting a mask on each bounding box of the object detected by faster R...
how do deal with it: "Attempted to set the storage of a tensor on device "cuda:0" to a storage on different device "cpu". This is no longer allowed; the devices...
Hello, is there a way to calculate the area / contour of the masked image? Thanks.
verts, faces = measure._marching_cubes_classic(Z, 0) TypeError: 'module' object is not callable 
Hi, I trained yolact_base with a custom dataset with only 1 object. I have retrieved weights but I am unable to load it back to use it in inference. ```...
`Calculating mAP... | all | .50 | .55 | .60 | .65 | .70 | .75 | .80 | .85 | .90 | .95 | -------+-------+-------+-------+-------+-------+-------+-------+-------+-------+-------+-------+ box | 54.24 |...
Hey everyone, in my trainning sets, there are about 20 classes and also have lots numbers of crack images, However, the confidence evaluation of crack images for the train images...
could somebody help me with producing boxAP and maskAP for each class.
Hey everyone, I successfully trained Mask-RCNN for my custom Dataset of Wood-Logs. However it turns out to be too slow for deployment. That's why I'm looking for a fast but...
I think I found a bug when there are too many classes in an image. I work with images of size [1024, 1024], and experimentally determined that if there are...
