Closed wuterry closed 2 years ago
In file _mmdet/models/roi_heads/bbox_heads/adamixer_decoderstage.py line 353,avg_factor = reduce_mean(num_pos) should be modified as 'avg_factor = max(reduce_mean(num_pos), 1)' to support training pure background images.
avg_factor = reduce_mean(num_pos)
In file _mmdet/models/roi_heads/bbox_heads/adamixer_decoderstage.py line 353,
avg_factor = reduce_mean(num_pos)
should be modified as 'avg_factor = max(reduce_mean(num_pos), 1)' to support training pure background images.