COCO split for pre-training
sanjayss34 opened this issue · comments
Hi @dandelin , thanks for this great repo and work! Could you please say what COCO split was used for pre-training? (was it 2014, 2017, Karpathy, or something else?) Thanks!
Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"
sanjayss34 opened this issue · comments
Hi @dandelin , thanks for this great repo and work! Could you please say what COCO split was used for pre-training? (was it 2014, 2017, Karpathy, or something else?) Thanks!