Try using U-net segmentation.
Awesome! Did you guys manage to get this working?
Also, do you have any thoughts on applying this to a new dataset and roughly how much training data you’d need to annotate?
Any update on Mask R-CNN code?
I found AffordanceNet code can do multiclass instance segmentation, but they only used VGG16.
Hey, did you implement the Mask R-CNN in PyTorch? Is there a good PyTorch implementation for it on github?
We are actually trying to use the following repository https://github.com/matterport/Mask_RCNN
What do you think about?
Any progress to implement it here?
I have been using that. I really like the notebooks and the examples using simple shapes as this allows you to experiment with small data. It definitely works. There is an existing port to pytorch but it is not working for training. Also they have not converted the notebooks and shapes; and have moved a lot of stuff around. I am still trying to understand all the different parts of maskRCNN but using both these projects to help me do that.
I am working with the Matterport code for both a Kaggle competition and for work, and am having a lot of trouble with it. It does not integrate well with standard keras code, and I am having a difficult job implementing basic tasks like image augmentation. Does anybody have any advice or a more mature mask rcnn tool written in either pytorch or keras? I’m currently wrangling with a branch of the Matterport code that has implemented image augmentation, and working from there.
We’ll be doing something like this in the new part 2, except more like SSD and RetinaNet (i.e. 1-pass rather than 2-pass approach).
One of the core contributors of torchvision has said he’s working on faster/maskrcnn.
Right now, there isn’t an official roi align layer or non-max suppression in pytorch which means you have to either build one of the cuda extensions floating around or use a very slow naive version. Those problems + messy anchor box assignment code seem to be making most of the current pytorch attempts hard to work with. Also, I “think” roi align and nms are coming in the next version of torchvision.
Also also, I wonder why nobody ever mentions the Light-Head rcnn paper. https://arxiv.org/pdf/1711.07264v1.pdf. I’d be interested in throwing a mask-head on that and seeing how well it does at instance segmentation.
Edit: Also also also, @jeremy. I saw that you were looking for a 1-pass instance segmentation network on twitter. Did you ever find anything or are you just going to do object detection for part 2? I was actually trying (and failing) to hack a mask head onto retinanet as I saw that tweet. Perhaps you could point me in the right direction? The only thing I’ve been able to find is this (class agnostic) https://arxiv.org/abs/1711.07618 and the code isn’t available yet.
I am to implement this model in production, and main constrain is inference time. I’m going to start with https://github.com/facebookresearch/Detectron
Final goal is to run this model in TensorRT but at the moment it is not supporting custom layers.
Any suggestions about production performance is wellcome.
I have two more questions: what is “Bells and whistles” from original article and what is Tiramisu?