Closed wmj183363206 closed 1 year ago
You can use an existing shadow detector to pre-predicted a shadow mask, then input it into the ShadowFormer. Or you can re-train the model without the shadow mask.
OK. Thank you for your reply.
你好,我想问一下如果我是用宽度为960高度为720的图片,这个训练指令可以是这样的吗? python train.py --warmup --win_size 12 --train_ps 720
The train_ps
should be a multiple of the win_size
* 8. Thus you can train with the win_size
=10. Alternatively, the train_ps
=720 is very large, leading to a large GPU memory. You can choose a smaller train_ps
.
Thank you for your patient reply. ^ . ^
The
train_ps
should be a multiple of thewin_size
* 8. Thus you can train with thewin_size
=10. Alternatively, thetrain_ps
=720 is very large, leading to a large GPU memory. You can choose a smallertrain_ps
.
Have you experimented with the effect of adjusting the parameters --win_size
and --train_ps
on the effect of the model?
In addition does the program limit the upper limit of the parameters --win_size
and --train_ps
?
Can the ShadowFormer process the dataset without gt_mask ?