Hi, the results of my repeated training on ADE20K using the BEiT-base pretrain model were 53.2 and 53.3 respectively. 0.3-0.4 lower than the official result (53.2 vs. 53.6). We are using the official config entirely.
Same situation. Beit-Base I only obtain 53.0, and Beit-Large 55.9, following the official implementation of MMSegmentation. It is hard to reproduce the results mentioned in the paper.
Hi, the results of my repeated training on ADE20K using the BEiT-base pretrain model were 53.2 and 53.3 respectively. 0.3-0.4 lower than the official result (53.2 vs. 53.6). We are using the official config entirely.