Tim Meinhardt

LSTM weights not optimised

3

The `LayerNormLSTMCell` modules initialised in the `MetaOptimizer` class are not properly registered as parameters of the `MetaOptimizer` model. Appending them to the `self.lstms` list: https://github.com/ikostrikov/pytorch-meta-optimizer/blob/0154d4d4fc856163885a62bac06174311aa58caf/meta_optimizer.py#L27 will not add their trainable...

Correlation always zero if multiple GPUs

15

The following code snippet reproduces the bug: ``` import torch from spatial_correlation_sampler import spatial_correlation_sample def run_spatial_corr(rank): corr = spatial_correlation_sample(torch.ones(1, 512, 12, 27).to(f"cuda:{rank}"), torch.ones(1, 512, 12, 27).to(f"cuda:{rank}")).mean() print(corr) run_spatial_corr(0) run_spatial_corr(1) ```...

YouTube-VIS and OVIS ablation study splits

2

In the IDOL paper you run ablation studies on a split of the training set. I also found those in the dataset registration but you did not provide the json...

Writable warning even if WAND_DIR is different and writeable.

10

I am getting the warning that root_dir is not writeable even if I set WAND_DIR to something else that is writeable. The warning is either false or confusing. https://github.com/wandb/wandb/blob/893602fc8e2ba49b84ed62f42eec34af2f5263bc/wandb/old/core.py#L40C14-L40C14