Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Tete-Xiao/ReSim
/ types & classes
Types & classes
15 in github.com/Tete-Xiao/ReSim
⨍
Functions
67
◇
Types & classes
15
↓ 9 callers
Class
AverageMeter
Computes and stores the average and current value
main_moco.py:378
↓ 1 callers
Class
ProgressMeter
main_moco.py:403
↓ 1 callers
Class
ResNet
moco/models.py:139
↓ 1 callers
Class
Trainer
detection/train_net.py:28
Class
BasicBlock
moco/models.py:50
Class
Bottleneck
moco/models.py:90
Class
GaussianBlur
Gaussian blur augmentation in SimCLR https://arxiv.org/abs/2002.05709
moco/loader.py:18
Class
ImageFolder
A generic data loader where the images are arranged in this way: :: root/dog/xxx.png root/dog/xxy.png root/dog/xxz.png
moco/datasets.py:14
Class
MoCo
Build a MoCo model with: a query encoder, a key encoder, and a queue https://arxiv.org/abs/1911.05722
moco/builder.py:7
Class
PrRoIPool2D
lib/prroi_pool/prroi_pool.py:19
Class
PrRoIPool2DFunction
lib/prroi_pool/functional.py:41
Class
RandomHorizontalFlip
Horizontally flip the given PIL Image randomly with a given probability. Args: p (float): probability of the image being flipped. Default
moco/transforms.py:106
Class
RandomResizedCrop
Crop the given PIL Image to random size and aspect ratio. A crop of random size (default: of 0.08 to 1.0) of the original size and a random as
moco/transforms.py:19
Class
Res5ROIHeadsExtraNorm
As described in the MOCO paper, there is an extra BN layer following the res5 stage.
detection/train_net.py:15
Class
TwoCropsTransform
Take two random crops of one image as the query and key.
moco/loader.py:6