Feifei
Feifei
> How are you initializing your weights and cached states? I found that the numbers blew up for me like this when I started from a random initialization of the...
Got the same error here yesterday running on my custom data. Saw your post on refactoring their code. Any idea how to fix it? Edit: Found the cause, but not...
Update: I ran a few experiments to reproduce this issue. `IterBasedTrainLoop` works fine, but when `by_epoch = True`, and `max_iter` and `type` were removed from `train_cfg` to enable `EpochBasedTrainLoop`, the...
> ```python > sampler=dict(type='DefaultSampler', shuffle=True), > ``` Wow it works. Thank you @MiXaiLL76 ! We might want to have this in the docs?
> @ff98li I think it's time to close this issue Agree. Thanks for reminding me!
4090 is equipped with 24gb vram which should be enough. are you running 2d image training or 3d video training?
> running on HPC; > >  > > Any idea as to how to go about it would be great. Try reduing image size or video length. image size...
@AfrifaEben7 did you only modify the the image size in `args` without modifying the ymal config file? the training script args controls the image size coming out of the dataloader...