dino
pytorch-lightning
Our great sponsors
dino | pytorch-lightning | |
---|---|---|
7 | 19 | |
5,854 | 19,188 | |
3.4% | - | |
1.0 | 9.9 | |
20 days ago | almost 2 years ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
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.
dino
- Batch-wise processing or image-by-image processing? (DINO V1)
-
[P] Image search with localization and open-vocabulary reranking.
I also implemented one based on the self attention maps from the DINO trained ViT’s. This worked pretty well when the attention maps were combined with some traditional computer vision to get bounding boxes. It seemed an ok compromise between domain specialization and location specificity. I did not try any saliency or gradient based methods as i was not sure on generalization and speed respectively. I know LAVIS has an implementation of grad cam and it seems to work well in the plug'n'play vqa.
-
Unsupervised semantic segmentation
You will probably need an unwieldy amount of data and compute to reproduce it, so your best option would be to use the pretrained models available on github.
-
[D] Why Transformers are taking over the Compute Vision world: Self-Supervised Vision Transformers with DINO explained in 7 minutes!
[Full Explanation Post] [Arxiv] [Project Page]
-
A major part of real-world AI has to be solved to make unsupervised, generalized full self-driving work, as the entire road system is designed for biological neural nets with optical imagers
Except he is actually talking about the new DINO model created by facebook that was released on friday. Which is a new approach to image transformers for unsupervised segmentation. Here's its github.
-
[D] Paper Explained - DINO: Emerging Properties in Self-Supervised Vision Transformers (Full Video Analysis)
Code: https://github.com/facebookresearch/dino
- [R] DINO and PAWS: Advancing the state of the art in computer vision with self-supervised Transformers
pytorch-lightning
-
Problem with pytorch lightning and optuna with multiple callbacks
def on_validation_end(self, trainer: Trainer, pl_module: LightningModule) -> None: # Trainer calls `on_validation_end` for sanity check. Therefore, it is necessary to avoid # calling `trial.report` multiple times at epoch 0. For more details, see # https://github.com/PyTorchLightning/pytorch-lightning/issues/1391. if trainer.sanity_checking: return
-
Please comment on my planned research project structure
Under the hood, the ModelWrapper object will create a ML model based on the config (so far, an XGBoost model and a PyTorch Lightning model). Each of those will have a wrapper that conducts training and evaluation (since from my understanding of Lightning, Trainers are required to be outside of the class). In lack of a better name, I call these wrappers Fitters. For uniformity, I thought about adding a common interface IFitter, which is inherited by all model wrappers as outlined below.
-
Watch out for the (PyTorch) Lightning
Join their Slack to ask the community questions and check out the GitHub here.
-
[P] Composer: a new PyTorch library to train models ~2-4x faster with better algorithms
Pytorch lightning benchmarks against pytorch on every PR (benchmarks to make sure that it is mot slower.
-
[D] What Repetitive Tasks Related to Machine Learning do You Hate Doing?
There is already a ton of momentum around automating ML workflows. I would suggest you contribute to a preexisting project like, for instance, PyTorch Lightning or fast.ai.
- PyTorch Lightening
-
[D] Are you using PyTorch or TensorFlow going into 2022?
Is the problem the sheer number of options, or the fact that they are all together in one place? Would it be better if they were organized into the different trainer entrypoints (fit, validate, ...)? If that is the case, there was an RFC proposing this which you might find interesting, feel free to drop by and comment on the issue: https://github.com/PyTorchLightning/pytorch-lightning/issues/10444
-
[D] Colab TPU low performance
I wanted to make a quick performance comparison between the GPU (Tesla K80) and TPU (v2-8) available in Google Colab with PyTorch. To do so quickly, I used an MNIST example from pytorch-lightning that trains a simple CNN.
-
[D] How to avoid CPU bottlenecking in PyTorch - training slowed by augmentations and data loading?
We've noticed GPU 0 on our 3 GPU system is sometimes idle (which would explain performance differences). However its unclear to us why that may be. Similar to this issue
-
[P] An introduction to PyKale https://github.com/pykale/pykale, a PyTorch library that provides a unified pipeline-based API for knowledge-aware multimodal learning and transfer learning on graphs, images, texts, and videos to accelerate interdisciplinary research. Welcome feedback/contribution!
If you want a good example for reference, take a look at Pytorch Lightning's readme (https://github.com/PyTorchLightning/pytorch-lightning) It answers the 3 questions of "what is this", "why should I care", and "how do i use it" almost instantly
What are some alternatives?
simsiam-cifar10 - Code to train the SimSiam model on cifar10 using PyTorch
mmdetection - OpenMMLab Detection Toolbox and Benchmark
Transformer-SSL - This is an official implementation for "Self-Supervised Learning with Swin Transformers".
pytorch-grad-cam - Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
pytorch-metric-learning - The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
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)
fastai - The fastai deep learning library
lightly - A python library for self-supervised learning on images.
composer - Supercharge Your Model Training
solo-learn - solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
sparktorch - Train and run Pytorch models on Apache Spark.