Jakub

Hmm hard to tell what is happenning but I'd play with the batch_size_train/inference for starters

Hi @xhh232018, I think what is happening here, is the out of fold predictions on train and test are appended to the list. Those will later be averaged (for test)...

Hmm I have to say that I simply ran this evaluation (that was written for DSB-2018), changed iou to coco implementation for speed, added handling for empty prediction and just...

You need to generate it first by running ```bash neptune run --config configs/neptune.yaml main.py prepare_metadata ``` remember to specify the paths in the `neptune.yaml` first. Thanks for spotting this. The...

Hi @LisburnLad There was a typo-like mistake in the command. It should indeed, contain the reference to SAL-10 ```bash neptune send --worker m-p100 \ --environment pytorch-0.3.1-gpu-py3 \ --config configs/neptune.yaml \...

Hi there @OsloAI and sorry for late response. It seems that you are pointing to an empty directory of images in your `neptune.yaml`: ```yaml parameters: # Data Paths train_images_dir: PATH/TO/YOUR/salt/data/train...

Any news on this one @sfalkner ?

I guess you are right @sfalkner. Callbacks are a "nice to have", but definitely you can do pretty much whatever you need in the `__call__` function. I would love to...

Hi @sfalkner. I have been on and off trying to add this example but I am having trouble understanding how to build it. When I worked with rtd and sphinx...

Thanks @sfalkner ! Added example as you proposed in PR #65