Mask_RCNN
Mask-RCNN-TF2.7.0-keras2.7.0
Our great sponsors
Mask_RCNN | Mask-RCNN-TF2.7.0-keras2.7.0 | |
---|---|---|
28 | 1 | |
24,014 | 43 | |
0.7% | - | |
0.0 | 0.0 | |
about 1 month ago | over 1 year ago | |
Python | Python | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Mask_RCNN
-
Analyze defects and errors in the created images
Mask R-CNN
-
List of AI-Models
Click to Learn more...
-
Thought Dump About Recent AI Advancements And Palantir
- Mask RCNN https://github.com/matterport/Mask_RCNN (open source, so also not Palantir's)
-
Why are python dependencies so broken?
pip install git+https://github.com/matterport/Mask_RCNN
-
DeepCreamPy & Hent-AI Guide: Installation and anime censorship removal (Version 2)
It is important to realize that to do its masking procedures, Hent-AI uses the Mask RCNN (MRCNN) package from Matterport. The problem with this version of MRCNN is that it is not compatible with Tensorflow 2.X versions, essentially limiting Hent-AI compatibility to strict Tensorflow 1.X versions. Since Tensorflow 1.15 is the last of the Tensorflow 1.X versions and uses CUDA 10.0, which supports a maximum compute capability of 7.5, this means that the last NVIDIA GPU series that is compatible with the original Hent-AI implementation is the RTX 2000 series. This is, of course, not optimal since it means that RTX 3000 series and later GPUs cannot be used despite their significant computing power and high VRAM.
-
[P] Mask R-CNN (matterport) does not generate masks or just generates them randomly
I read that it could bethe problem with scipy version (https://github.com/matterport/Mask_RCNN/issues/2122) so I downgraded it, I also tried to modify shift = np.array([0, 0, 1., 1.]) in utils.py but nothing helped.
-
MRCNN TF==2.7.0
Hello AI learners, check out my own development of Mask-RCNN supporting Tensorflow2.7.0 and Keras2.8.0. This is an edit of MRCNN which supports Tensoflow1.0, only.
- Open source - that means free to use commercially right? ... right?
-
Mask_RCNN adapted and trained on AWS sagemaker
We started from matterport/Mask_RCNN and we adapted it to be trained on Sagemaker spot intances.
Mask-RCNN-TF2.7.0-keras2.7.0
-
MRCNN TF==2.7.0
My Development
What are some alternatives?
Swin-Transformer-Object-Detection - This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.
yolact - A simple, fully convolutional model for real-time instance segmentation.
mmdetection - OpenMMLab Detection Toolbox and Benchmark
mmsegmentation - OpenMMLab Semantic Segmentation Toolbox and Benchmark.
Mask-RCNN-training-with-docker-containers-on-Sagemaker
Mask-RCNN-Implementation - Mask RCNN Implementation on Custom Data(Labelme)
yolact - Tensorflow 2.x implementation YOLACT
labelme - Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
SOLO - SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
Moby - The Moby Project - a collaborative project for the container ecosystem to assemble container-based systems
labelme2coco - A lightweight package for converting your labelme annotations into COCO object detection format.
FreeCAD - This is the official source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.