rishikksh20/crossvit-pytorch

Implementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

Hi there, I'm Rishikesh, Speech and Computer Vision Researcher👋

Hi friends, I'm Rishikesh, Co-founder and CTO of Dubpro.ai (formely known as DeepSync Technologies). I graduated from NIT Silchar and immediately after my graduation I joined my first organisation, Nucleus Software as Full Stack Developer role. I have a keen interest in machine learning and deep learning research, especially in a field of speech synthesis and computer vision.

• 🔭 I’m currently working on Speech Synthesis and End to End Text to Speech (TTS) engines.
• 🌱 I love to code and contribute to Open Source.
• 💬 Ask me anything regarding my work, code and research here (Please tag me @rishikksh20 in your comment.).
• 📫 How to reach me: [email protected]

Connect with me:

Languages and Tools:

crossvit-pytorch's Issues

About the questions in Table 7 of the article

Hello,I am very interested in your job, but there is one thing I don't understand.I would like to ask you about the comparison between the information in Table 7 of the paper and the information in Crossvit -S, the first line should be K=3,N=1,M=4 and L=1. I don't quite understand the setting in the first line of Table 7, and I feel it is inconsistent with the content mentioned in the article. Maybe I haven't understood your meaning correctly, and I hope to receive your reply.Thank you!

Multilabel Image classification

@rishikksh20 thanks for sharing code base , i had few queries
1.can we train crossvit for multilabel classification problem , if so what is the procedure
2. i have a custom dataset of 10.5k with 25class labels with instance as label vectors of 0 and 1
3. can remove the pre-trained classifer head and add our customr classifier ?

Thanks in advance