Probyto's Daily Knowledge Bytes - 136
A common refrain for computer vision researchers is that modern deep neural networks are always hungry for more labeled data — current state-of-the-art CNNs need to be trained on datasets such as OpenImages or Places, which consist of over 1M labelled images. However, for many applications, collecting this amount of labeled data can be prohibitive to the average practitioner. Check how Bit can be used to explore large scale Pre Training for Computer VIsion.
#OpenSourceBit #BigTransfer #ComputerVision #GoogleAI #Probyto