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
Synthesizing High-Resolution Images with StyleGAN2
https://www.youtube.com/watch?v=9QuDh3W3lOY&feature=emb_logo
Article: https://news.developer.nvidia.com/synthesizing-high-resolution-images-with-stylegan2/
https://www.youtube.com/watch?v=9QuDh3W3lOY&feature=emb_logo
Article: https://news.developer.nvidia.com/synthesizing-high-resolution-images-with-stylegan2/
YouTube
Synthesizing High-Resolution Images with StyleGAN2
This new project called StyleGAN2, developed by NVIDIA Research, and presented at CVPR 2020, uses transfer learning to produce seemingly infinite numbers of portraits in an infinite variety of painting styles. The work builds on the team’s previously published…
Rethinking the Truly Unsupervised Image-to-Image Translation - Official PyTorch Implementation
Here proposed the truly unsupervised image-to-image translation method (TUNIT) that simultaneously learns to separate image domains via an information-theoretic approach and generate corresponding images using the estimated domain labels.
Github: https://github.com/clovaai/tunit
Paper: https://arxiv.org/abs/2006.06500v1
Here proposed the truly unsupervised image-to-image translation method (TUNIT) that simultaneously learns to separate image domains via an information-theoretic approach and generate corresponding images using the estimated domain labels.
Github: https://github.com/clovaai/tunit
Paper: https://arxiv.org/abs/2006.06500v1
Using Multi-Scale Attention for Semantic Segmentation
https://devblogs.nvidia.com/using-multi-scale-attention-for-semantic-segmentation/
Paper: https://arxiv.org/abs/2005.10821
https://devblogs.nvidia.com/using-multi-scale-attention-for-semantic-segmentation/
Paper: https://arxiv.org/abs/2005.10821
NVIDIA Technical Blog
Using Multi-Scale Attention for Semantic Segmentation
There’s an important technology that is commonly used in autonomous driving, medical imaging, and even Zoom virtual backgrounds: semantic segmentation. That’s the process of labelling pixels in an…
From singing to musical scores: Estimating pitch with SPICE and Tensorflow Hub
Pitch is quantified by frequency, measured in Hertz (Hz), where one Hz corresponds to one cycle per second. The higher the frequency, the higher the note.
https://blog.tensorflow.org/2020/06/estimating-pitch-with-spice-and-tensorflow-hub.html
Model: https://tfhub.dev/google/spice/2
Colab code: https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/spice.ipynb
Pitch is quantified by frequency, measured in Hertz (Hz), where one Hz corresponds to one cycle per second. The higher the frequency, the higher the note.
https://blog.tensorflow.org/2020/06/estimating-pitch-with-spice-and-tensorflow-hub.html
Model: https://tfhub.dev/google/spice/2
Colab code: https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/spice.ipynb
❤1
This media is not supported in your browser
VIEW IN TELEGRAM
SimCLR - A Simple Framework for Contrastive Learning of Visual Representations
The findings described in this paper can potentially be harnessed to improve accuracy in any application of computer vision where it is more expensive or difficult to label additional data than to train larger models.
Github: https://github.com/google-research/simclr
Paper: https://arxiv.org/abs/2006.10029
The findings described in this paper can potentially be harnessed to improve accuracy in any application of computer vision where it is more expensive or difficult to label additional data than to train larger models.
Github: https://github.com/google-research/simclr
Paper: https://arxiv.org/abs/2006.10029
Data-Efficient GANs with DiffAugment
Differentiable Augmentation (DiffAugment), a simple method that improves the data efficiency of GANs by imposing various types of differentiable augmentations on both real and fake samples.
Github: https://github.com/mit-han-lab/data-efficient-gans
Paper: https://arxiv.org/abs/2006.10738
Training code: https://github.com/mit-han-lab/data-efficient-gans/tree/master/DiffAugment-stylegan2
Differentiable Augmentation (DiffAugment), a simple method that improves the data efficiency of GANs by imposing various types of differentiable augmentations on both real and fake samples.
Github: https://github.com/mit-han-lab/data-efficient-gans
Paper: https://arxiv.org/abs/2006.10738
Training code: https://github.com/mit-han-lab/data-efficient-gans/tree/master/DiffAugment-stylegan2
The Most Important Fundamentals of PyTorch you Should Know
https://blog.exxactcorp.com/the-most-important-fundamentals-of-pytorch-you-should-know/
Code: https://github.com/tirthajyoti/PyTorch_Machine_Learning
https://blog.exxactcorp.com/the-most-important-fundamentals-of-pytorch-you-should-know/
Code: https://github.com/tirthajyoti/PyTorch_Machine_Learning
Exxactcorp
Blog - the most important fundamentals of pytorch you should know | Exxact
This media is not supported in your browser
VIEW IN TELEGRAM
Machine Learning in Dask
In this article you can learn how Dask works with a huge dataset on local machine or in a distributed manner.
https://www.kdnuggets.com/2020/06/machine-learning-dask.html
In this article you can learn how Dask works with a huge dataset on local machine or in a distributed manner.
https://www.kdnuggets.com/2020/06/machine-learning-dask.html
Denoising Diffusion Probabilistic Models
Рigh quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.
https://hojonathanho.github.io/diffusion/
Github: https://github.com/hojonathanho/diffusion
Paper: https://arxiv.org/abs/2006.11239
Рigh quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.
https://hojonathanho.github.io/diffusion/
Github: https://github.com/hojonathanho/diffusion
Paper: https://arxiv.org/abs/2006.11239
Introducing a New Privacy Testing Library in TensorFlow
https://blog.tensorflow.org/2020/06/introducing-new-privacy-testing-library.html
Github: https://github.com/tensorflow/privacy
https://blog.tensorflow.org/2020/06/introducing-new-privacy-testing-library.html
Github: https://github.com/tensorflow/privacy
blog.tensorflow.org
Introducing a New Privacy Testing Library in TensorFlow
The TensorFlow blog contains regular news from the TensorFlow team and the community, with articles on Python, TensorFlow.js, TF Lite, TFX, and more.
This media is not supported in your browser
VIEW IN TELEGRAM
The NetHack Learning Environment
The NetHack Learning Environment (NLE) is a Reinforcement Learning environment based on NetHack 3.6.6. NLE is designed to provide a standard RL interface to the game, and comes with tasks that function as a first step to evaluate agents on this new environment.
Github: https://github.com/facebookresearch/nle
Paper: https://arxiv.org/abs/2006.13760v1
Project: https://nethack.org/
The NetHack Learning Environment (NLE) is a Reinforcement Learning environment based on NetHack 3.6.6. NLE is designed to provide a standard RL interface to the game, and comes with tasks that function as a first step to evaluate agents on this new environment.
Github: https://github.com/facebookresearch/nle
Paper: https://arxiv.org/abs/2006.13760v1
Project: https://nethack.org/
Enhance your TensorFlow Lite deployment with Firebase
https://blog.tensorflow.org/2020/06/enhance-your-tensorflow-lite-deployment-with-firebase.html
https://blog.tensorflow.org/2020/06/enhance-your-tensorflow-lite-deployment-with-firebase.html
blog.tensorflow.org
Enhance your TensorFlow Lite deployment with Firebase
Learn how to use Firebase to deploy your TensorFlow Lite models over-the-air, monitor performance in production, and A/B test multiple model versions.
Computer Vision using Tensorflow
https://levelup.gitconnected.com/computer-vision-using-tensorflow-946718d3c123
Full Code can be found on my Github
https://levelup.gitconnected.com/computer-vision-using-tensorflow-946718d3c123
Full Code can be found on my Github
Medium
Computer Vision using Tensorflow
Giving computers the ability to see through Machine Learning
Extracting the main trend in a dataset: the Sequencer algorithm
The Sequencer is an algorithm that attempts to reveal the main sequence in a dataset, if it exists.
https://sequencer.org/
Github: https://github.com/dalya/Sequencer
Paper: https://arxiv.org/abs/2006.13948v1
The Sequencer is an algorithm that attempts to reveal the main sequence in a dataset, if it exists.
https://sequencer.org/
Github: https://github.com/dalya/Sequencer
Paper: https://arxiv.org/abs/2006.13948v1
Unsupervised Discovery of Object Landmarks via Contrastive Learning
Approach is motivated by the phenomenon of the gradual emergence of invariance in the representation hierarchy of a deep network.
https://people.cs.umass.edu/~zezhoucheng/contrastive_landmark/
Code: https://github.com/cvl-umass/ContrastLandmark
Paper: https://arxiv.org/abs/2006.14787
Approach is motivated by the phenomenon of the gradual emergence of invariance in the representation hierarchy of a deep network.
https://people.cs.umass.edu/~zezhoucheng/contrastive_landmark/
Code: https://github.com/cvl-umass/ContrastLandmark
Paper: https://arxiv.org/abs/2006.14787
👍1
SpineNet: A Novel Architecture for Object Detection Discovered with Neural Architecture Search
https://ai.googleblog.com/2020/06/spinenet-novel-architecture-for-object.html
Paper: https://arxiv.org/abs/1912.05027
https://ai.googleblog.com/2020/06/spinenet-novel-architecture-for-object.html
Paper: https://arxiv.org/abs/1912.05027