Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

pytorch1.0 updated. Support cpu test and demo. (Use detectron2, it's a masterpiece)

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

Tutorials on how to implement a few key architectures for image classification using PyTorch and TorchVision.

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

Automatic image captioning model based on Caffe, using features from bottom-up attention.

Official codes for the paper "Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech"

Code for DiagNet: Bridging Text and Image

neural module network on the GQA dataset