dmy1997

Results 2 issues of dmy1997

In the paper, R101 is frozen in stem and ResNet1 block. However, I print the weights and they are different from the in1k R101 model. Have they finetuned?

Hello, I noticed that, EVA "use block-wise masking with a masking ratio of 40%", while MAE compares three sampling strategies[Table 1f and Fig.6] and concludes randomly sampling is the best....