#
hrnet
Here are 9 public repositories matching this topic...
Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)
pytorch
coco
eval
ccnet
cityscapes
mobilenet
xception
deeplabv3plus
deeplab-v3-plus
fast-scnn
hrnet
pointrend
-
Updated
May 3, 2020 - Python
Multi-person Human Pose Estimation with HRNet in Pytorch
machine-learning
computer-vision
deep-learning
pytorch
human-pose-estimation
coco-dataset
yolov3
keypoint-detection
hrnet
-
Updated
Apr 25, 2020 - Python
A treasure chest for image classification powered by PaddlePaddle
image-classification
knowledge-distillation
data-augmentation
mixup
xception
autoaugment
res2net
mobilenetv3
efficientnet
cutmix
hrnet
randaugment
gridmask
resnetvd
ssld
-
Updated
May 20, 2020 - Python
moontree
commented
Apr 16, 2020
dwmatrix = create_downsample_fn_matrix(self.num_branches, features, self.num_branches, output_channels)
should be
dwmatrix = create_downsample_fn_matrix(self.num_branches, features, self.num_outputs, output_channels)
Fast and accurate Human Pose Estimation using ShelfNet with PyTorch
real-time
deep-learning
pytorch
human-pose-estimation
ms-coco
keypoint-localization
human-pose-tracking
keypoint-detection
hrnet
shelfnet
ms-coco-keypoints
-
Updated
Feb 10, 2020 - Python
detectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn
-
Updated
May 6, 2020 - Python
DeepBlue AI Team's Winner Solutions for CVWC 2019 Tiger Pose Track Challenge
-
Updated
Aug 5, 2019 - Cuda
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
-
Updated
Apr 3, 2020 - Cuda
Improve this page
Add a description, image, and links to the hrnet topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the hrnet topic, visit your repo's landing page and select "manage topics."
如果设置
cfg.NUM_TRAINERS = 4
cfg.TRAINER_ID = 0,1,2,3
if self.shuffle and cfg.NUM_TRAINERS > 1: np.random.RandomState(self.shuffle_seed).shuffle(self.all_lines) num_lines = len(self.all_lines) // cfg.NUM_TRAINERS self.lines = self.all_lines[num_lines * cfg.TRAINER_ID: num_lines * (cfg.TRAINER_ID + 1)] self.shuffle_seed += 1上面代码中的self.