DE⫶TR: End-to-End Object Detection with Transformers
PyTorch training code and pretrained models for DETR The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss that forces unique predictions via bipartite matching, and a transformer encoder-decoder architecture.
Github: https://github.com/facebookresearch/detr
Paper: https://arxiv.org/abs/2005.12872v1
Code: https://colab.research.google.com/github/facebookresearch/detr/blob/colab/notebooks/detr_demo.ipynb
PyTorch training code and pretrained models for DETR The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss that forces unique predictions via bipartite matching, and a transformer encoder-decoder architecture.
Github: https://github.com/facebookresearch/detr
Paper: https://arxiv.org/abs/2005.12872v1
Code: https://colab.research.google.com/github/facebookresearch/detr/blob/colab/notebooks/detr_demo.ipynb
How MTS used smart contract to build a system for selecting best technological projects.
https://habr.com/ru/company/ru_mts/blog/504058
https://habr.com/ru/company/ru_mts/blog/504058
Towards computer-aided severity assessment: training and validation of deep neural networks for geographic extent and opacity extent scoring of chest X-rays for SARS-CoV-2 lung disease severity
The COVID-Net models provided here are intended to be used as reference models that can be built upon and enhanced as new data becomes available.
Github: https://github.com/lindawangg/COVID-Net
Paper: https://arxiv.org/abs/2005.12855v1
The COVID-Net models provided here are intended to be used as reference models that can be built upon and enhanced as new data becomes available.
Github: https://github.com/lindawangg/COVID-Net
Paper: https://arxiv.org/abs/2005.12855v1
GitHub
GitHub - lindawangg/COVID-Net: COVID-Net Open Source Initiative
COVID-Net Open Source Initiative. Contribute to lindawangg/COVID-Net development by creating an account on GitHub.
👍1
Segmentation Loss Odyssey
Loss functions for image segmentation
Github: https://github.com/JunMa11/SegLoss
Paper: https://arxiv.org/abs/2005.13449v1
Loss functions for image segmentation
Github: https://github.com/JunMa11/SegLoss
Paper: https://arxiv.org/abs/2005.13449v1
Analyzing pretraining approaches for vision and language tasks
Simple design choices in pretraining can help us achieve close to state-of-art results on downstream tasks without any architectural changes.
https://ai.facebook.com/blog/analyzing-pretraining-approaches-for-vision-and-language-tasks/
Github: https://github.com/facebookresearch/mmf/tree/master/projects/pretrain_vl_right
Paper: https://arxiv.org/abs/2004.08744
Simple design choices in pretraining can help us achieve close to state-of-art results on downstream tasks without any architectural changes.
https://ai.facebook.com/blog/analyzing-pretraining-approaches-for-vision-and-language-tasks/
Github: https://github.com/facebookresearch/mmf/tree/master/projects/pretrain_vl_right
Paper: https://arxiv.org/abs/2004.08744
Facebook
Analyzing pretraining approaches for vision and language tasks
We show how several simple, infrequently explored design choices in pretraining can help achieve high performance on tasks that combine language and visual understanding.
👍1
NeuralPy
NeuralPy: A Keras like deep learning library works on top of PyTorch PyTorch is an open-source machine learning framework that accelerates the path from research prototyping to production deployment developed by Facebook runs on both CPU and GPU.
Github: https://github.com/imdeepmind/NeuralPy
Project: https://neuralpy.imdeepmind.com/
NeuralPy: A Keras like deep learning library works on top of PyTorch PyTorch is an open-source machine learning framework that accelerates the path from research prototyping to production deployment developed by Facebook runs on both CPU and GPU.
Github: https://github.com/imdeepmind/NeuralPy
Project: https://neuralpy.imdeepmind.com/
GitHub
GitHub - imdeepmind/NeuralPy: NeuralPy: A Keras like deep learning library works on top of PyTorch
NeuralPy: A Keras like deep learning library works on top of PyTorch - imdeepmind/NeuralPy
Text Mining in Python: Steps and Examples
This blog summarizes text preprocessing and covers the NLTK steps including Tokenization, Stemming, Lemmatization, POS tagging, Named entity recognition and Chunking.
https://www.kdnuggets.com/2020/05/text-mining-python-steps-examples.html
This blog summarizes text preprocessing and covers the NLTK steps including Tokenization, Stemming, Lemmatization, POS tagging, Named entity recognition and Chunking.
https://www.kdnuggets.com/2020/05/text-mining-python-steps-examples.html
Acme: A research framework for reinforcement learning
Acme strives to expose simple, efficient, and readable agents, that serve both as reference implementations of popular algorithms and as strong baselines, while still providing enough flexibility to do novel research
Github: https://github.com/deepmind/acme
Paper: https://arxiv.org/abs/2006.00979
Acme strives to expose simple, efficient, and readable agents, that serve both as reference implementations of popular algorithms and as strong baselines, while still providing enough flexibility to do novel research
Github: https://github.com/deepmind/acme
Paper: https://arxiv.org/abs/2006.00979
A Smooth Representation of SO(3) for Deep Rotation Learning with Uncertainty
In this work presented a novel symmetric matrix representation of rotations that is singularity-free and requires marginal computational overhead
Website: https://papers.starslab.ca/bingham-rotation-learning/
Paper: https://arxiv.org/abs/2006.01031
Github: https://github.com/utiasSTARS/bingham-rotation-learn
In this work presented a novel symmetric matrix representation of rotations that is singularity-free and requires marginal computational overhead
Website: https://papers.starslab.ca/bingham-rotation-learning/
Paper: https://arxiv.org/abs/2006.01031
Github: https://github.com/utiasSTARS/bingham-rotation-learn
Introduction to Convolutional Neural Networks
The article focuses on explaining key components in CNN and its implementation using Keras python library.
https://www.kdnuggets.com/2020/06/introduction-convolutional-neural-networks.html
The article focuses on explaining key components in CNN and its implementation using Keras python library.
https://www.kdnuggets.com/2020/06/introduction-convolutional-neural-networks.html
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Recursive Feature Pyramid implements thinking twice at the macro level, where the outputs of FPN are brought back to each stage of the bottom-up backbone through feedback connections
Github: https://github.com/joe-siyuan-qiao/DetectoRS
Paper: https://arxiv.org/abs/2006.02334v1
Recursive Feature Pyramid implements thinking twice at the macro level, where the outputs of FPN are brought back to each stage of the bottom-up backbone through feedback connections
Github: https://github.com/joe-siyuan-qiao/DetectoRS
Paper: https://arxiv.org/abs/2006.02334v1
A Scalable and Cloud-Native Hyperparameter Tuning System
Katib is a Kubernetes-based system for Hyperparameter Tuning and Neural Architecture Search. Katib supports a number of ML frameworks, including TensorFlow, Apache MXNet, PyTorch, XGBoost, and others.
Github: https://github.com/kubeflow/katib
Getting started with Katib: https://www.kubeflow.org/docs/components/hyperparameter-tuning/hyperparameter/
Paper: https://arxiv.org/abs/2006.02085v1
Katib is a Kubernetes-based system for Hyperparameter Tuning and Neural Architecture Search. Katib supports a number of ML frameworks, including TensorFlow, Apache MXNet, PyTorch, XGBoost, and others.
Github: https://github.com/kubeflow/katib
Getting started with Katib: https://www.kubeflow.org/docs/components/hyperparameter-tuning/hyperparameter/
Paper: https://arxiv.org/abs/2006.02085v1
Introducing Neuropod, Uber ATG’s Open Source Deep Learning Inference Engine
Neuropod makes it easy for researchers to build models in a framework of their choosing while also simplifying productionization of these models.
It currently supports TensorFlow, PyTorch, TorchScript, and Keras.
https://eng.uber.com/introducing-neuropod/
Github: https://github.com/uber/neuropod
Neuropod Tutorial: https://neuropod.ai/tutorial/
Neuropod makes it easy for researchers to build models in a framework of their choosing while also simplifying productionization of these models.
It currently supports TensorFlow, PyTorch, TorchScript, and Keras.
https://eng.uber.com/introducing-neuropod/
Github: https://github.com/uber/neuropod
Neuropod Tutorial: https://neuropod.ai/tutorial/
Uber Blog
Introducing Neuropod, Uber ATG’s Open Source Deep Learning Inference Engine | Uber Blog
Developed by Uber ATG, Neuropod is an abstraction layer that provides a universal interface to run models across any deep learning framework.
❤1
Part 2: Fast, scalable and accurate NLP: Why TFX is a perfect match for deploying BERT
https://blog.tensorflow.org/2020/06/part-2-fast-scalable-and-accurate-nlp.html
Code: https://colab.research.google.com/github/tensorflow/workshops/blob/master/blog/TFX_Pipeline_for_Bert_Preprocessing.ipynb
https://blog.tensorflow.org/2020/06/part-2-fast-scalable-and-accurate-nlp.html
Code: https://colab.research.google.com/github/tensorflow/workshops/blob/master/blog/TFX_Pipeline_for_Bert_Preprocessing.ipynb
This media is not supported in your browser
VIEW IN TELEGRAM
PEGASUS: A State-of-the-Art Model for Abstractive Text Summarization
https://ai.googleblog.com/2020/06/pegasus-state-of-art-model-for.html
Github: https://github.com/google-research/pegasus
Paper: https://arxiv.org/abs/1912.08777
https://ai.googleblog.com/2020/06/pegasus-state-of-art-model-for.html
Github: https://github.com/google-research/pegasus
Paper: https://arxiv.org/abs/1912.08777
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Github: https://github.com/implus/GFocal
Paper: https://arxiv.org/abs/2006.04388v1
Github: https://github.com/implus/GFocal
Paper: https://arxiv.org/abs/2006.04388v1
YOLOv5 is Here: State-of-the-Art Object Detection at 140 FPS
Realtime object detection is improving quickly. The rate of improvement is improving even more quickly. The results are stunning.
https://blog.roboflow.ai/yolov5-is-here/
Github: https://github.com/ultralytics/yolov5
GCP Quickstart: https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart
Realtime object detection is improving quickly. The rate of improvement is improving even more quickly. The results are stunning.
https://blog.roboflow.ai/yolov5-is-here/
Github: https://github.com/ultralytics/yolov5
GCP Quickstart: https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart
Roboflow Blog
YOLOv5 is Here: State-of-the-Art Object Detection at 140 FPS
Less than 50 days after the release YOLOv4, YOLOv5 improves accessibility for realtime object detection.
June 29, YOLOv5 has released the first official version of the repository. We wrote a new deep dive on YOLOv5.
June 12, 8:08 AM CDT Update: In response…
June 29, YOLOv5 has released the first official version of the repository. We wrote a new deep dive on YOLOv5.
June 12, 8:08 AM CDT Update: In response…
Deploy a Machine Learning Pipeline to the Cloud Using a Docker Container
https://www.kdnuggets.com/2020/06/deploy-machine-learning-pipeline-cloud-docker.html
https://www.kdnuggets.com/2020/06/deploy-machine-learning-pipeline-cloud-docker.html
VirTex: Learning Visual Representations from Textual Annotations
VirTex is a pretraining approach which uses semantically dense captions to learn visual representations.VirTex matches or outperforms models which use ImageNet for pretraining -- both supervised or unsupervised -- despite using up to 10x fewer images.
https://kdexd.github.io/virtex/
Github: https://github.com/kdexd/virtex
Paper: arxiv.org/abs/2006.06666
VirTex is a pretraining approach which uses semantically dense captions to learn visual representations.VirTex matches or outperforms models which use ImageNet for pretraining -- both supervised or unsupervised -- despite using up to 10x fewer images.
https://kdexd.github.io/virtex/
Github: https://github.com/kdexd/virtex
Paper: arxiv.org/abs/2006.06666
