sagemaker-training-toolkit
image-super-resolution
sagemaker-training-toolkit | image-super-resolution | |
---|---|---|
1 | 19 | |
468 | 4,499 | |
2.4% | 0.8% | |
6.3 | 0.0 | |
about 1 month ago | about 2 months 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.
sagemaker-training-toolkit
-
Distributed training with Horovod/MPI
I'm using sagemaker-training-toolkit to attempt hyperparameter optimization and trying to take advantage of all the cores on each machine using their MPI options (which uses Horovod with MPI to my understanding). I'm pretty new to this space and can't find anything that describes in somewhat lay-terms how training works in this distributed model. With AllReduce, how often does the reduce happen? I'm trying to figure out if all training threads are training a shared model such that every thread is training on the "latest" version of the model.
image-super-resolution
- A tech worker is selling a children's book he made using AI. Professional illustrators are pissed.
- Low quality surveillance footage from a hit and run that happened today. Greatly appreciate if anyone has any ideas on how to get the plate number.
-
[R] What are the best pretrained super-resolution GAN models on GitHub?
Currently, I have already implemented the pretrained GAN model from here, however I am not yet satisfied with the results. Indeed, I will go with this one if there's no other option, but I was hoping maybe someone here can point me to a better direction. Thank you!
- [P] Tutorial on using image super-resolution without Photoshop
- [P] Tutorial on how to use image super-resolution without photoshop
- What’s an extremely useful website most people probably don’t know about?
- Hit and Run Can someone help me figure out what the plate says? Also any advice I've never been in an accident before
- VC#4 - pancake - vc.ajmoon.uk - VQGAN/CLIP + 3D Photo Inpainting + Image Super-Resolution
What are some alternatives?
jina - ☁️ Build multimodal AI applications with cloud-native stack
SwinIR - SwinIR: Image Restoration Using Swin Transformer (official repository)
Activeloop Hub - Data Lake for Deep Learning. Build, manage, query, version, & visualize datasets. Stream data real-time to PyTorch/TensorFlow. https://activeloop.ai [Moved to: https://github.com/activeloopai/deeplake]
VQGAN-CLIP - Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
torchlambda - Lightweight tool to deploy PyTorch models to AWS Lambda
video2x - A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley II, 2018.
spotty - Training deep learning models on AWS and GCP instances
DeepCreamPy - Decensoring Hentai with Deep Neural Networks
sagemaker-tensorflow-training-toolkit - Toolkit for running TensorFlow training scripts on SageMaker. Dockerfiles used for building SageMaker TensorFlow Containers are at https://github.com/aws/deep-learning-containers.
waifu2x - Image Super-Resolution for Anime-Style Art
data-science-ipython-notebooks - Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
MAX-Image-Resolution-Enhancer - Upscale an image by a factor of 4, while generating photo-realistic details.