RhpNet - An Image based object detection Dataset

We used an 80/20 technique to categorize 8592 photos from multiple datasets and sources into Train and Test groups. The Train dataset has 35 categorized folders and 6881 photographs, whereas the Test dataset had 35 categorized folders and 1711 images. The goal is to classify each indoor or outdoor object into one of thirty-five categories based on the message delivered by the object in front of them (0=’1 Taka’, 1=’10 Taka’, 2=’100 Taka’, 3=’1000 Taka’, 4=’2 Taka’, 5=’20 Taka’, 6=’5 Taka’, 7=’50 Taka’, 8=’500 Taka’, 9=’Person’, 10=’bed’, 11=’bicycle’, 12=’bike’, 13=’boat’, 14=’bus’, 15=’c-n-g’, 16=’car’, 17=’chair’, 18=’desk’, 19=’door’, 20=’easybike’, 21=’horse-cart’, 22=’laptop’, 23=’launch’, 24=’leguna’, 25=’lorry’, 26=’mug’, 27=’rickshaw’, 28=’stair’, 29=’television’, 30=’thelagari’, 31=’tractor’, 32=’truck’, 33=’van’, 34=’window’).