NorS

> has anyone solved this issue? I'm using pytorch=1.4.0, cuda=10.1 with a fresh conda environment. Still getting this error. I think this is because its extension "griding". Its output tensors...

> > Hi, when training a DepthFormerModel, in the process_stereo function > > https://github.com/TRI-ML/vidar/blob/a306e23cc47ae05a0c35b0bf8acf7112c87c049c/vidar/arch/models/depth/DepthFormerModel.py#L64 > > > > it fails if there is no 'pose' in the batch. is it...

same issue

> the dimensions should be multiple of 64.. But the question is how to deal with the dataset in which the images' width and height are not equal, e.g., 1024...

> Not yet, I trained BEVDepth official code with 1408x512 resolution a few days ago, but the results seemed like overfit (14.2 total loss, 29.4 NDS). However it's not reasonable...

16 GB is still limited as far as I concern.

> ``` > train_dataloader = dict( > batch_size=2, > num_workers=2, > persistent_workers=True, > sampler=dict(type='DefaultSampler', shuffle=True), > batch_sampler=dict(type='AspectRatioBatchSampler'), > dataset=dict( > type=dataset_type, > data_root=data_root, > ann_file=[ > data_root + "/mmdet/train/train_20230327.json", >...