simclr
moco
Our great sponsors
simclr | moco | |
---|---|---|
13 | 4 | |
3,927 | 4,550 | |
1.8% | 2.3% | |
2.9 | 3.7 | |
11 months ago | 4 months ago | |
Jupyter Notebook | Python | |
Apache License 2.0 | MIT License |
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.
simclr
-
Positive and Negative Sampling Strategies for Representation Learning in Semantic Search
For visual representations, you could look into SimCLR and MoCo. https://github.com/google-research/simclr https://github.com/facebookresearch/moco
-
[D] Why is random cropping necessary in SimCLR?
Yeah I think so, it's not hard to check https://github.com/google-research/simclr/blob/2fc637bdd6a723130db91b377ac15151e01e4fc2/data_util.py
-
[R] Deep Learning with a Small Training Batch (or Lack Thereof). Part 1
Code for https://arxiv.org/abs/2006.10029 found: https://github.com/google-research/simclr
-
[D] Current trends in computer vision related to unsupervised learning
SimCLR v2.0 - https://arxiv.org/abs/2006.10029
-
Self-Supervised Contrastive Learning model for video dataset?
My data consists of binary labels (normal & anomalous) where the videos are already broken up into frames in the directory, I'm looking for a model where I can feed a normal-labeled video alongside an anomalous-labeled video like visualized in this example from the SimCLR Repo, a dog will represent the normal video and the chair the anomalous video.
-
[P] Choosing a self-supervised learning framework that's easy to use
No, go to the "tf2" folder in the repo root. https://github.com/google-research/simclr/tree/master/tf2
-
[D] What is meant by width in the SimCLRv2 paper?
Code for https://arxiv.org/abs/2006.10029 found: https://github.com/google-research/simclr
-
[D] Funding PhD in Europe
[1] https://github.com/google-research/simclr [2] https://www.tensorflow.org/tfrc?hl=en&authuser=2
moco
-
Positive and Negative Sampling Strategies for Representation Learning in Semantic Search
For visual representations, you could look into SimCLR and MoCo. https://github.com/google-research/simclr https://github.com/facebookresearch/moco
- [D] Self-Supervised Contrastive Approaches that don’t use large batch size.
-
[D] Significant differences in Training on 1 GPU vs 8GPU ?
I am looking at the official code for MOCO-v2 linear evaluation here: https://github.com/facebookresearch/moco The command to execute suggests running a 256 sized batch across 8 GPUs for a Resnet-50. Do keep in mind that for the linear evaluation the model is frozen till the end and only the final fully connected layer is fine-tuned.
-
[D] Momentum Contrast for Unsupervised Visual Representation Learning MoCo v1 & v2 by Kwonjoon Lee et al.
[Full Explanation Post / Blog Post] [Arxiv] [Code]
What are some alternatives?
swav - PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882
Unsupervised-Classification - SCAN: Learning to Classify Images without Labels, incl. SimCLR. [ECCV 2020]
unsupervised-depth-completion-visual-inertial-odometry - Tensorflow and PyTorch implementation of Unsupervised Depth Completion from Visual Inertial Odometry (in RA-L January 2020 & ICRA 2020)
SimCLR - PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
torchlars - A LARS implementation in PyTorch
Supervised-Constrastive-Learning-in-TensorFlow-2 - Implements the ideas presented in https://arxiv.org/pdf/2004.11362v1.pdf by Khosla et al. [Moved to: https://github.com/sayakpaul/Supervised-Contrastive-Learning-in-TensorFlow-2]
CodeSearchNet - Datasets, tools, and benchmarks for representation learning of code.
soft-vc - Soft speech units for voice conversion