Epiphqny / Solov2
Licence: apache-2.0
SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)
Stars: ✭ 174
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Solov2
Ac Fpn
Implement of paper 《Attention-guided Context Feature Pyramid Network for Object Detection》
Stars: ✭ 117 (-32.76%)
Mutual labels: instance-segmentation
Remo Python
🐰 Python lib for remo - the app for annotations and images management in Computer Vision
Stars: ✭ 138 (-20.69%)
Mutual labels: instance-segmentation
Deepco3
[CVPR19] DeepCO3: Deep Instance Co-segmentation by Co-peak Search and Co-saliency (Oral paper)
Stars: ✭ 127 (-27.01%)
Mutual labels: instance-segmentation
Copy Paste Aug
Copy-paste augmentation for segmentation and detection tasks
Stars: ✭ 132 (-24.14%)
Mutual labels: instance-segmentation
Data science bowl 2018
My 5th place (out of 816 teams) solution to The 2018 Data Science Bowl organized by Booz Allen Hamilton
Stars: ✭ 147 (-15.52%)
Mutual labels: instance-segmentation
Lanenet Lane Detection
Unofficial implemention of lanenet model for real time lane detection using deep neural network model https://maybeshewill-cv.github.io/lanenet-lane-detection/
Stars: ✭ 1,690 (+871.26%)
Mutual labels: instance-segmentation
Awesome Satellite Imagery Datasets
🛰️ List of satellite image training datasets with annotations for computer vision and deep learning
Stars: ✭ 2,447 (+1306.32%)
Mutual labels: instance-segmentation
Psconv
[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer
Stars: ✭ 138 (-20.69%)
Mutual labels: instance-segmentation
Instance Segmentation With Discriminative Loss Tensorflow
Tensorflow implementation of "Semantic Instance Segmentation with a Discriminative Loss Function"
Stars: ✭ 158 (-9.2%)
Mutual labels: instance-segmentation
Paz
Hierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.
Stars: ✭ 131 (-24.71%)
Mutual labels: instance-segmentation
Weakly Supervised Panoptic Segmentation
Weakly- and Semi-Supervised Panoptic Segmentation (ECCV18)
Stars: ✭ 149 (-14.37%)
Mutual labels: instance-segmentation
Mask rcnn pytorch
Mask R-CNN for object detection and instance segmentation on Pytorch
Stars: ✭ 123 (-29.31%)
Mutual labels: instance-segmentation
Adelaidet
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
Stars: ✭ 2,565 (+1374.14%)
Mutual labels: instance-segmentation
Bmaskr Cnn
Boundary-preserving Mask R-CNN (ECCV 2020)
Stars: ✭ 116 (-33.33%)
Mutual labels: instance-segmentation
Jsis3d
[CVPR'19] JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds
Stars: ✭ 144 (-17.24%)
Mutual labels: instance-segmentation
Ciou
Complete-IoU (CIoU) Loss and Cluster-NMS for Object Detection and Instance Segmentation (YOLACT)
Stars: ✭ 166 (-4.6%)
Mutual labels: instance-segmentation
Keraspersonlab
Keras-tensorflow implementation of PersonLab (https://arxiv.org/abs/1803.08225)
Stars: ✭ 163 (-6.32%)
Mutual labels: instance-segmentation
Tfvos
Semi-Supervised Video Object Segmentation (VOS) with Tensorflow. Includes implementation of *MaskRNN: Instance Level Video Object Segmentation (NIPS 2017)* as part of the NIPS Paper Implementation Challenge.
Stars: ✭ 151 (-13.22%)
Mutual labels: instance-segmentation
SOLOv2
The code is an unofficial pytorch implementation of SOLOv2: Dynamic, Faster and Stronger
Install
Please check SOLOv1 for installation instructions.
Training
Follows the same way as SOLOv1.
single GPU:
python tools/train.py configs/solov2/solov2_r101_3x.py
multi GPU (for example 8):
./tools/dist_train.sh configs/solov2/solov2_r101_3x.py 8
Weights
Trained model can be download in Google drive BaiduYun 提取码: qw4e
Results
After training 36 epochs(3x) on the coco dataset using the resnet-101 backbone, the mAP is 39.5 on COCO test-dev2017 dataset. In the original paper, the model achieves 39.7 after 72 epochs(6x).
Visualization（1 epoch)
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].