Alexey Kravets – Medium

Alexey Kravets

Pinned

Alexey Kravets
in
Towards Data Science

Improving CLIP performance in training-free manner with few-shot examples

Part 3 — a simple extension to zero-shot classification with Tip-Adapter.

7 min readJan 30, 2024

--

Improving CLIP performance in training-free manner with few-shot examples

--

Pinned

Alexey Kravets
in
Towards Data Science

Simple way of improving Zero-Shot CLIP performance

Part 1 — Customized Prompts via Language models (CuPL)

12 min readNov 3, 2023

--

Simple way of improving Zero-Shot CLIP performance

--

Pinned

Alexey Kravets
in
Towards Data Science

Deep Dive into the LSTM-CRF Model

With PyTorch code

23 min readOct 12, 2023

--

Deep Dive into the LSTM-CRF Model

--

Pinned

Alexey Kravets
in
Towards Data Science

A Deep Dive into the Code of the Visual Transformer (ViT) Model

Breaking down the HuggingFace ViT Implementation

14 min readAug 15, 2023

--

A Deep Dive into the Code of the Visual Transformer (ViT) Model

--

Pinned

Alexey Kravets
in
Towards Data Science

A Deep Dive into the Code of the BERT Model

Breaking down the HuggingFace BERT Implementation

14 min readDec 14, 2021

--

2

A Deep Dive into the Code of the BERT Model

--

2

Alexey Kravets
in
Towards Data Science

Improving performance and explainability of Zero-Shot CLIP

Part 2 — Visual classification via Description from LLMs

6 min readNov 25, 2023

--

1

Improving performance and explainability of Zero-Shot CLIP

--

1

Alexey Kravets
in
Towards Data Science

Variational Autoencoder (VAE) with Discrete Distribution using Gumbel Softmax

Theory and PyTorch Implementation

17 min readAug 9, 2023

--

1

Variational Autoencoder (VAE) with Discrete Distribution using Gumbel Softmax

--

1

Alexey Kravets
in
Towards AI

Streamlining File Management: A Guide to Connecting and Modifying Files on a Server or a Docker…

Clearly Explained

4 min readAug 5, 2023

--

Streamlining File Management: A Guide to Connecting and Modifying Files on a Server or a Docker…

--

Alexey Kravets
in
Towards Data Science

Multiple GPU training in PyTorch and Gradient Accumulation as an alternative to it

Code and Theory

7 min readJul 24, 2023

--

Multiple GPU training in PyTorch and Gradient Accumulation as an alternative to it

--

Alexey Kravets
in
Towards AI

Backpropagation and Vanishing Gradient Problem in RNN (Part 2)

How it is reduced in LSTM

11 min readJul 19, 2023

--

Backpropagation and Vanishing Gradient Problem in RNN (Part 2)

--

Alexey Kravets

Alexey Kravets

PhD student in AI at the University of Bath researching Vision & Language models. My LinkedIn profile: https://www.linkedin.com/in/alexey-kravets-647663137/

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams