Data

Tools

Indexes

Applications

Experiments

Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / facebookresearch/simsiam issues and pull requests

#50 - Loss increasing

Issue - State: open - Opened by karthik1145 about 2 years ago

#49 - Could not find any class folder

Issue - State: open - Opened by chandagrover over 2 years ago

#48 - Why are training and testing so slow

Issue - State: open - Opened by InstantWindy over 2 years ago - 2 comments

#46 - self.encoder.fc in builder.py

Issue - State: closed - Opened by MSutharsan over 2 years ago

#45 - Stn

Pull Request - State: closed - Opened by ferreirafabio over 2 years ago - 2 comments

#44 - The value of loss function nn.CosineSimilarity is negative

Issue - State: open - Opened by zhang1hongliang almost 3 years ago - 1 comment

#43 - Pre-trained weights for SimCLR, MoCov2, BYOL, SwaV

Issue - State: open - Opened by ninatu almost 3 years ago - 1 comment

#42 - About the shape of image[0] and image[1]

Issue - State: open - Opened by Richard-Lu-badbird almost 3 years ago - 1 comment

#41 - add checkpoint saving path

Pull Request - State: closed - Opened by cogito288 almost 3 years ago

#40 - Loss collapse during training

Issue - State: open - Opened by aisagarw almost 3 years ago - 1 comment

#38 - SyncBatchnorm usage in main_lincls.py

Issue - State: closed - Opened by myoh97 over 3 years ago - 2 comments

#37 - Slow convergence with SGD linear evaluation

Issue - State: open - Opened by gergopool over 3 years ago - 1 comment

#36 - checkpoint for epoch 800

Issue - State: open - Opened by elias-ramzi over 3 years ago

#35 - larger batch size with linear scale does not work

Issue - State: open - Opened by liming-ai over 3 years ago

#34 - difference between byol in table19 and simsiam?

Issue - State: closed - Opened by LMerCy over 3 years ago - 1 comment

#33 - [Problem] problem occured when trained on custom dataset

Issue - State: closed - Opened by CaptainEven over 3 years ago - 4 comments

#32 - Checkpoints with 50 epochs

Issue - State: closed - Opened by kevinbro96 over 3 years ago - 1 comment

#31 - Loss descent slowly

Issue - State: closed - Opened by vincezengqiang over 3 years ago - 1 comment

#30 - Single GPU Training

Issue - State: closed - Opened by nixczhou over 3 years ago - 3 comments

#29 - loss question

Issue - State: closed - Opened by daeing over 3 years ago - 4 comments

#28 - zero_init_residual

Issue - State: closed - Opened by ifountalis over 3 years ago - 1 comment

#27 - General question regarding weight sharing and stop gradient

Issue - State: closed - Opened by ramchandracheke almost 4 years ago - 2 comments

#26 - Problems of reproducing the transfering results with SimSiam/MoCo-v2 on COCO

Issue - State: closed - Opened by thss15fyt almost 4 years ago - 1 comment

#25 - Question about the calculated details of std in the paper

Issue - State: closed - Opened by qxm1995716 almost 4 years ago - 2 comments

#24 - Questions about the optimal model for object detection

Issue - State: closed - Opened by bluenights almost 4 years ago - 2 comments

#23 - Failing on Reproducing ImageNet Linear Classification Results with SGD

Issue - State: closed - Opened by ferreirafabio almost 4 years ago - 6 comments

#22 - Learning rate scheduler setting for different epochs

Issue - State: closed - Opened by BaohaoLiao almost 4 years ago - 1 comment

#21 - Negative Loss

Issue - State: closed - Opened by say2sarwar almost 4 years ago - 1 comment

#19 - Checkpoints for COCO and VOC

Issue - State: closed - Opened by alexlioralexli about 4 years ago - 1 comment

#18 - Checkpoint with 200 epochs?

Issue - State: closed - Opened by lzyhha about 4 years ago - 7 comments

#17 - l2 normalize

Issue - State: closed - Opened by UQ-DongYuan about 4 years ago - 2 comments

#16 - Stuck in the DDP initiliazation step

Issue - State: closed - Opened by kxgong about 4 years ago - 2 comments

#15 - Question about batch size

Issue - State: closed - Opened by CoinCheung about 4 years ago

#14 - issue about the cosine similarity loss function

Issue - State: closed - Opened by sonnefred about 4 years ago - 1 comment

#13 - Question about the learning rate used in linear evaluation

Issue - State: closed - Opened by Vickeyhw about 4 years ago - 1 comment

#12 - SyncBatchNorm

Issue - State: closed - Opened by dengandong about 4 years ago - 5 comments

#11 - Fixed LR on predictor with LR warmup

Issue - State: closed - Opened by patrickpoirson about 4 years ago - 1 comment

#10 - kNN evaluation during training

Issue - State: closed - Opened by elias-ramzi about 4 years ago - 2 comments

#9 - Reproducing CIFAR-10 Results

Issue - State: open - Opened by ardywibowo about 4 years ago - 14 comments

#8 - AssertionError: assert set(msg.missing_keys) == {"fc.weight", "fc.bias"}

Issue - State: closed - Opened by etetteh about 4 years ago - 3 comments

#7 - Why BYOL without the momentum encoder collapses but SimSiam does not?

Issue - State: closed - Opened by zhujiagang about 4 years ago - 1 comment

#6 - A question about projection and prediction MLP

Issue - State: closed - Opened by CaptainPrice12 about 4 years ago - 3 comments

#5 - Open-source improved implementations of BYOL, SWAV, etc.?

Issue - State: closed - Opened by DrJimFan about 4 years ago - 3 comments

#4 - Adding Code of Conduct file

Pull Request - State: closed - Opened by facebook-github-bot over 4 years ago
Labels: CLA Signed

#3 - Adding Contributing file

Pull Request - State: closed - Opened by facebook-github-bot over 4 years ago
Labels: CLA Signed

#2 - teaser

Issue - State: closed - Opened by endernewton over 4 years ago

#1 - Teaser

Issue - State: closed - Opened by endernewton over 4 years ago