Biomacromolecule platform

2021SC@SDUSC 0. Preface This blog post is mainly about the self attention mechanism of deep learning, qkv part and gradient in deep learning 1. Self attention mechanism of deep learning 1.1 basic concepts of self attention mechanism For the self attention mechanism, Q, K and V, that is, query, key and value, all come from the same inpu ...

Posted by loudrake on Wed, 13 Oct 2021 22:13:57 +0200

Readme report for C language beginners (Continued)

Preface: I haven't sorted it out for a long time, but I'm actually lazy and haven't learned much, so I'll briefly talk about what I've learned at the beginning, and talk about the problems encountered in learning and a little trivial experience. (the last part of the previous article is about the tips of variable types) Small review: 1.const ...

Posted by taiger on Wed, 13 Oct 2021 15:42:21 +0200

Natural language processing - text preprocessing

Similar to other data preprocessing of machine learning, natural language processing also needs text preprocessing, such as word segmentation in Chinese and part of speech restoration in English. Common pretreatment methods 1. Text normalization Capital to lowercase output_str = input_str.lower() Digital processing Remove all numbers imp ...

Posted by khaitan_anuj on Tue, 12 Oct 2021 22:15:07 +0200

Detailed explanation of edit distance and its code implementation

summary The Minimum Edit Distance (MED) was proposed by Vladimir Levenshtein, a Russian scientist, in 1965, hence the name Levenshtein Distance. Levenshtein Distance is an index used to measure the similarity of two sequences in the fields of information theory, linguistics and computer science. Generally speaking, editing distance refers t ...

Posted by ferronrsmith on Tue, 05 Oct 2021 01:12:22 +0200

Task 10: Transformers solve machine translation

1 fine tune the transformer model to solve the translation task ! pip install datasets transformers "sacrebleu>=1.4.12,<2.0.0" sentencepiece model_checkpoint = "Helsinki-NLP/opus-mt-en-ro" # Select a model checkpoint As long as the pre trained transformer model contains the head layer of seq2seq structure, this notebook can theo ...

Posted by MBenefactor on Thu, 30 Sep 2021 21:34:54 +0200

Super Simple High Score baseline

1. Introduction to Twitter Text Emotional Classification Contest Practice match address: https://www.heywhale.com/home/activity/detail/611cbe90ba12a0001753d1e9/content This exercise has 13 emotional categories, so the score is low... Twitter tweets have many features. First, unlike Facebook, tweets are text-based and can be registered and do ...

Posted by Andy-H on Mon, 27 Sep 2021 19:17:29 +0200

AttributeError: Can't get attribute 'xxx' on <module '__main__' from 'xxx'

AttributeError: Can't get attribute 'xxx' on < module 'main' from 'xxx' another possible solution Problem Restatement: when learning pytorch, I learned to serialize the Word2Seq class using the pickle module and save the serialization in the ws.pkl file. Then I created the lib.py file again. This problem occurs when I deserialize ws.pkl wit ...

Posted by RyanJones on Sat, 25 Sep 2021 11:51:34 +0200

Implementation and explanation of simple countermeasure neural network GAN - picture countermeasure

1. The theoretical explanation is clear and easy to understand: Understand the basic principle of "generating countermeasure network GAN" + 10 typical algorithms + 13 applications (easyai.tech) 2. Code implementation set: GitHub - eriklindernoren/Keras-GAN: Keras implementations of Generative Adversarial Networks. 3. Here is a bri ...

Posted by funkyres on Tue, 07 Sep 2021 06:34:45 +0200

[NLP] ⚠️ Learn not to hit me! Learn basic operation in half an hour 2 ⚠️ key word

summary From today on, we will start a journey of natural language processing (NLP). NLP can let us process, understand and use human language to realize the communication bridge between machine language and human language key word Keywords, i.e. key words, can describe the essence of an article and have important applications in docum ...

Posted by kundan on Mon, 06 Sep 2021 05:57:58 +0200