Author: Deep Learner

Compiler

Domain-specific compiler for Finite Difference/Volume/Element Earth-system models in Fortran

PSyclone Welcome to PSyclone. PSyclone is a code generation system that generates appropriate code for the PSyKAl code structure developed in the GungHo project. Please see psyclone.pdf in this directory (or on ReadTheDocs) for more information. If you would prefer to build the documentation, please see the README file in the “doc” directory. Some of the examples are available as Jupyter notebooks. These may be launched using Binder from the links below. (Note that the first time this is done, […]

Read more
Python

A Python Guide to the Fibonacci Sequence

With stacks, you’ll effectively see how each call in a recursive function is handled. The way each call is pushed onto the stack and popped off is exactly how the program is run, and it’ll clearly demonstrate how calculating large numbers will take a long time, if not optimized. Illustrating Visualization Using a Call Stack In a call stack, whenever a function call returns a result, a stack frame representing the function call is popped off the stack. Whenever you […]

Read more
Debugger

A Practical Debugging Tool for Training Deep Neural Networks

pip install ‘git+https://github.com/f-dangel/cockpit.git’ Cockpit is a visual and statistical debugger specifically designed for deep learning. Training a deep neural network is often a pain! Successfully training such a network usually requires either years of intuition or expensive parameter searches involving lots of trial and error. Traditional debuggers provide only limited help: They can find syntactical errors but not training bugs such as ill-chosen learning rates. Cockpit offers a closer, more meaningful look into the training process with multiple well-chosen instruments. […]

Read more
AWS

Call any existing AWS Lambda Function you have in a future time

aws-lambda-scheduler lets you call any existing AWS Lambda Function you have in the future. This functionality is achieved by dynamically managing the EventBridge Rules. aws-lambda-scheduler also has optimizations you can configure and extend yourself. AWS allows maximum of 300 EventBridge rules in a region. If you are expecting to create more than 300 rules, check out Optimizations section below. Example Usage When you set up the aws-lambda-scheduler in your AWS environment, you can simply call it with a json data […]

Read more
Deep Learning

Deep Extraction of Manga Structural Lines in python

The (Official) PyTorch Implementation of the paper “Deep Extraction of Manga Structural Lines” Usage model_torch.py [source folder] [output folder] Example: model_torch.py ./pytorchTestCases/ ./pytorchResults/ The model weights (erika.pth) Please refer to the release section of this repo. Alternatively, you may use this link: https://www.dropbox.com/s/y8pulix3zs73y62/erika.pth?dl=0 Requirement Python3 PyTorch (tested on version 1.9) Python-opencv How the model is prepared The PyTorch weights are exactly the same as the theano(!) model. I make some efforts to convert the original weights to the new model […]

Read more
Detection

Prototype for Baby Action Detection and Classification

An attempt to harness the power of Deep Learning to come up with a solution that can let us detect various classes of activities an infant, toddler or a baby is performing in real-time. This POC can then be published as an end-to-end deployable cloud project. The model does not restrict predictions for babies only, it is applicable to all entities that appears in a human posture. So temporary, this needs to be handled at project level. Special thanks to […]

Read more
Search

Searching for Efficient Multi-Stage Vision Transformers in Pytorch

This repository contains the official Pytorch implementation of “Searching for Efficient Multi-Stage Vision Transformers” and is based on DeiT and timm. Illustration of the proposed multi-stage ViT-Res network. Illustration of weight-sharing neural architecture search with multi-architectural sampling. Accuracy-MACs trade-offs of the proposed ViT-ResNAS. Our networks achieves comparable results to previous work. Requirements The codebase is tested with 8 V100 (16GB) GPUs. To install requirements: pip install -r requirements.txt Docker files are provided to set up the environment. Please run: cd […]

Read more
Annotation

Annotation tool using GrabCut() of OpenCV

Annotation tool using GrabCut() of OpenCV. It can be used to create datasets for semantic segmentation. * Due to GrabCut’s algorithm, it is suitable for annotation of data with clear boundaries. opencv-python 4.5.2.54 or later Pillow 7.2.0 or later PySimpleGUI 4.32.1 or later │  app.py │  config.json │ ├─core │  │  gui.py │  └─util.py │ ├─input │ └─output ├─image └─annotation app.py, core/gui.py, core/util.py Source code. input Image files are stored in this directory. output Directory to save annotation results. image：The […]

Read more
Weather

A Python interface between Earth Engine and xarray for processing weather and climate data

What is wxee? wxee was built to make processing gridded, mesoscale time series weather and climate data quick and easy by integrating the data catalog and processing power of Google Earth Engine with the flexibility of xarray, with no complicated setup required. To accomplish this, wxee implements convenient methods for data processing, aggregation, downloading, and ingestion. Features Time series image collections to xarray, NetCDF, or GeoTIFF in one line of code Climatological means and temporal aggregation Parallel processing for fast […]

Read more
1 … 528 529 530 531 532 … 991