dataset
IMAGE-CAPTIONING-
KaranTalwalkar
or hover any field below to flag it
Overview
Name
IMAGE-CAPTIONING-
Source
KaranTalwalkar
Episodes
0
Robot count
0
Format
other
Description
Developed an image captioning model using the Flickr8k dataset with a CNN–LSTM/GRU architecture. Extracts visual features and generates meaningful, human-like captions. Trained end-to-end for accurate scene understanding and real-time caption generation.
Robots used
null
Links
HuggingFace dataset
null