High-Performance Large-Scale Image Recognition Without Normalization

NFNet Pytorch Implementation This repo contains pretrained NFNet models F0-F6 with high ImageNet accuracy from the paper High-Performance Large-Scale Image Recognition Without Normalization. The small models are as accurate as an EfficientNet-B7, but train 8.7 times faster. The large models set a new SOTA top-1 accuracy on ImageNet. NFNet F0 F1 F2 F3 F4 F5 F6+SAM Top-1 accuracy Brock et al. 83.6 84.7 85.1 85.7 85.9 86.0 86.5 Top-1 accuracy this implementation 82.82 84.63 84.90 85.46 85.66 85.62 TBD All […]

Read more

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

SETR – Pytorch Since the original paper (Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers.) has no official code,I implemented SETR-Progressive UPsampling(SETR-PUP) using pytorch. Original paper: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers. Vit The Vit model is also implemented, and you can use it for image classification. Usage SETR from SETR.transformer_seg import SETRModel import torch if __name__ == “__main__”: net = SETRModel(patch_size=(32, 32), in_channels=3, out_channels=1, hidden_size=1024, num_hidden_layers=8, num_attention_heads=16, decode_features=[512, 256, 128, 64]) t1 = torch.rand(1, 3, […]

Read more

Python SDK for the Buycoins API

Buycoins Python Library This library provides easy access to the Buycoins API using the Python programming language. It provides all the feature of the API so that you don’t need to interact with the API directly. This library can be used with Python 3.6+ Installation You can install this package using pip: pip install –upgrade buycoins Introduction Primer The library is structured around the concept of a type, so everything is a type. All date quantities are specified as timestamps. […]

Read more

Graphical tool to make photo collage posters in python

PhotoCollage Graphical tool to make photo collage posters PhotoCollage allows you to create photo collage posters. It assembles the input photographs it is given to generate a big poster. Photos are automatically arranged to fill the whole poster, then you can change the final layout, dimensions, border or swap photos in the generated grid. Eventually the final poster image can be saved in any size. The algorithm generates random layouts that place photos while taking advantage of all free space. […]

Read more

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery (ICCV 2021 Oral) StyleCLIP: Text-Driven Manipulation of StyleGAN ImageryOr Patashnik*, Zongze Wu*, Eli Shechtman, Daniel Cohen-Or, Dani Lischinski*Equal contribution, ordered alphabeticallyhttps://arxiv.org/abs/2103.17249 Abstract: Inspired by the ability of StyleGAN to generate highly realistic images in a variety of domains, much recent work has focused on understanding how to use the latent spaces of StyleGAN to manipulate generated and real images. However, discovering semantically meaningful latent manipulations typically involves painstaking human examination of the many degrees […]

Read more

Python library that converts the output of popular command-line tools and file-types to JSON or Dictionaries

jc CLI tool and python library that converts the output of popular command-line tools and file-types to JSON or Dictionaries. This allows piping of output to tools like jq and simplifying automation scripts. JSON CLI output utility jc JSONifies the output of many CLI tools and file-types for easier parsing in scripts. See the Parsers section for supported commands and file-types. dig example.com | jc –dig [{“id”:38052,”opcode”:”QUERY”,”status”:”NOERROR”,”flags”:[“qr”,”rd”,”ra”],”query_num”:1,”answer_num”:1, “authority_num”:0,”additional_num”:1,”opt_pseudosection”:{“edns”:{“version”:0,”flags”:[],”udp”:4096}},”question”: {“name”:”example.com.”,”class”:”IN”,”type”:”A”},”answer”:[{“name”:”example.com.”,”class”:”IN”,”type”:”A”,”ttl”: 39049,”data”:”93.184.216.34″}],”query_time”:49,”server”:”2600:1700:bab0:d40::1#53(2600:1700:bab0:d40::1)”,”when”: “Fri Apr 16 16:09:00 PDT 2021″,”rcvd”:56,”when_epoch”:1618614540,”when_epoch_utc”:null}] This allows further command-line […]

Read more

A Flask extension for preventing cross-site request forgery

Flask-SeaSurf SeaSurf is a Flask extension for preventing cross-site request forgery (CSRF). CSRF vulnerabilities have been found in large and popular sites such as YouTube. These attacks are problematic because the mechanism they use is relatively easy to exploit. This extension attempts to aid you in securing your application from such attacks. This extension is based on the excellent Django middleware. Installation Install the extension with one of the following commands: $ easy_install flask-seasurf or alternatively if you have pip […]

Read more

A simple scheduler tool that provides desktop notifications about classes

Online Class Automation This application provides desktop notifications about classes and opens their meet links in browser automatically at the start of the class. It works both in windows and linux. But runs better in linux when used with cron. Code Overview class-data.json: Stores the timetable in simple json format. Specify the name and meet link of classes with their timings according to your timetable. The time of a class is specified by day and hour. Day ranges from 0 […]

Read more

An Exploration of JSON Interoperability Vulnerabilities

JSON Interoperability Vulnerability Labs These are the companion labs to my research article “An Exploration of JSON Interoperability Vulnerabilities”. Lab 1: Free purchases in an E-commerce Application Key Collision Attacks: Inconsistent Duplicate Key Precedence Inconsistent Large Number Representations Lab 2: Privilege Escalation in a Multi-tenant Application Key Collision Attacks: Character Truncation These labs bind to host ports 5000-5004, by default. Attack Techniques 1. Key Collisions Inconsistent Duplicate Key Precedence {“qty”: 1, “qty”: -1} Character Truncation Truncation in last-key precedence parsers […]

Read more

A collection of fancy functional tools focused on practicality

A collection of fancy functional tools focused on practicality. Inspired by clojure, underscore and my own abstractions. Keep reading to get an overview or read the docs. Or jump directly to cheatsheet. Works with Python 2.7, 3.4+ and pypy. Installation pip install funcy Overview Import stuff from funcy to make things happen: from funcy import whatever, you, need Merge collections of same type (works for dicts, sets, lists, tuples, iterators and even strings): merge(coll1, coll2, coll3, …) join(colls) merge_with(sum, dict1, […]

Read more
1 509 510 511 512 513 928