no performance evaluation on MSCOCO
Did you create an account just to criticize the original posters work?
TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
11–20 of 43 posts
Re: TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
#12Earlier quoted context omitted.
To be fair, the academic article did include the code : https://github.com/facebookresearch/deepmask It was just in Lua.
Deepmask is something else.
You are right, it's a different paper. But they both do instance segmentation and both build upon faster r cnn.
Re: TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
#13This looks great! Thanks for releasing this.
Re: TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
#14Surprised I still haven't seen a pytorch translation of deepmask / sharpmask. But glad to see atleast a tensorflow implementation. Will definitely try it out.
Been out for a couple months:
Re: TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
#15no performance evaluation on MSCOCO
Evaluation code against MS COCO is included in the repository, both for bounding boxes and segmentation masks so it should be easy to run (but takes a long time).
We should publish more details, though. Thanks for bringing it up. Our implementation deviates a bit from the paper (as mentioned in the documentation), and optimizing for COCO was a 'nice to have' rather than being the main objective. We got pretty close to the reported numbers (within 3 to 4 percentage points) but that was with half the training steps compared to the paper. We'll try to add more details over the next few days.
Re: TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
#16Surprised I still haven't seen a pytorch translation of deepmask / sharpmask. But glad to see atleast a tensorflow implementation. Will definitely try it out.
Been out for a couple months: https://github.com/felixgwu/mask_rcnn_pytorch
> Unfortunately, we could not fit the model into the GPU we have and there is some ambiguity in the paper as well, so we decided to stop the project and wait until the official code being released.
Re: TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
#17Very cool! How is the performance? R-CNN used to be much slower comparing to YOLO or SSD; FCN seems to be very fast as well though requires a lot of GPU memory. Can that your version be used for realtime semantic segmentation?
Re: TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
#18God bless people who implement models from academic articles that should frankly include them to begin with. What's more is that this implementation has clear instructions for extending this to your datasets.
> academic articles that should frankly include them to begin with.
Boo hoo. Researchers tell the world for free exactly how to implement their state-of-the-art work (which probably cost north of $1M to develop) and promise to release code, and we're indignant because they didn't do it quite fast enough for us.
Re: TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
#19God bless people who implement models from academic articles that should frankly include them to begin with. What's more is that this implementation has clear instructions for extending this to your datasets.
> academic articles that should frankly include them to begin with. Boo hoo. Researchers tell the world for free exactly how to implement their state-of-the-art work (which probably cost north of $1M to develop) and promise to release code, and we're indignant because they didn't do it quite fast enough for us.
(1) It's not free when the research is funded by public tax dollars (which I grant is not always, but often the case).
(2) I'm not aware of this promise you're speaking of... my understanding is that authors of papers are under no obligation to produce any implementation, let alone usable, documented implementations.
Re: TensorFlow Mask R-CNN code for pixelwise object detection and segmentation
#20Earlier quoted context omitted.
> academic articles that should frankly include them to begin with. Boo hoo. Researchers tell the world for free exactly how to implement their state-of-the-art work (which probably cost north of $1M to develop) and promise to release code, and we're indignant because they didn't do it quite fast enough for us.
(1) It's not free when the research is funded by public tax dollars (which I grant is not always, but often the case). (2) I'm not aware of this promise you're speaking of... my understanding is that authors of papers are under no obligation to produce any implementation, let alone usable, documented implementations.
> (1) It's not free when the research is funded by public tax dollars (which I grant is not always, but often the case).
The work was done at FAIR (Facebook), so that's not applicable here.
> (2) I'm not aware of this promise you're speaking of... my understanding is that authors of papers are under no obligation to produce any implementation, let alone usable, documented implementations.
Look at the paper [1], it's the last sentence of the abstract: "Code will be made available."
[1] https://research.fb.com/wp-content/uploads/2017/08/maskrcnn....