Thomas Capelle
Thomas Capelle
Would be cool to do something like this: https://www.angioi.com/time-series-encoder-decoder-tensorflow/ using the new `GaussianLoss` in pytorch 1.8, basically, instead of doing a regression, you predict mean and std and fit a...
Just create a new PR
You could ask people to execute: ```python from fastai.test_utils import show_install show_install() ``` 
I am trying to solve this issue, but it is pretty hard. Debugging `state_dict'`s is not very practical.... I really don't get why this is happening. You can put some...
Your batch has zero images, check with ''' dls.one_batch() ''' And inspect dimensions. The problem rises because your list of images is empty, so it cannot stack them together as...
That's more than one question 😜, The actual code expects individual frames, so you need to process them. Metrics can be found on sklearn and use the fastai wrapper, so...
let me look into this tomorrow. Look at here: https://docs.fast.ai/distributed.html
Wow that's pretty low. It depends one the split of you train/valid. Are you using random default? Set a seed so you are sure to be comparing apple to apples...
ohh thanks =)
I am not sure how to make a requirements file with specific pointed depndencies. Added the pip install command to my bash script.