A few more changes, ObjectDetectDataset
now takes slightly different arguments to make it consistent with the rest of the general API. There’s a full example creating one in the data block doc.
this i really a beautiful improvement- thx
Is there a good place to quickly see the list of breaking changes with each release version? If not, where would be a good place to list those?
Relatedly, is there interest in following https://semver.org/, so that versions that are not backward compatible are more clearly identified.
Certainly too early at this point - not sure it’s quite appropriate for something used mainly for prototyping/training. Still thinking about this.
We may need to separate out the part of the API that needs to be stable for production, and have some one to deal with that.
For now, you should read CHANGES.md if you update your fastai lib.
Thanks @jeremy. Good to know. Maybe worth putting front and center in the docs that there will be breaking changes, folks should read CHANGES.md, and folks should regularly update their fastai package versions.
That’s a good idea.
Maybe we could version docs and provide links for documentation in previous releases.
Can I specify databunch to be on cpu device?
like databunch(bs=64, device=‘cpu’)?
what do i need to do for the learner also to use cpu (although one may have a cuda device)?
Thanks much !
labeled images of camvid in camvid-tiny are gray-scale. I thought that was required only for caffe.
Am I wrong?
I am not sure if I should post such small things (if not, please tell me):
A small inconvenience I discovered when I was using ClassificationInterpretation
with normalize=True
is that the numbers are displayed with all decimals and the chart is very crowded.
A small change in line 122 of learner.py solves it to only show 3 decimals:
cm[i, j]
too "{:.3f}".format(cm[i, j])
I uploaded an notebook for visualization: https://nbviewer.jupyter.org/github/MicPie/fastai_course_v3/blob/master/ClassificationInterpretation_normalized.ipynb
If I should create a PR just tell me.
Probably it would be even better if you provide something like num_format='{:.3f}'
argument to override this value as needed.
You can create a PR, but only if you use f-strings, like everywhere in the library
Here is an example of formatted-float in f-string.
Thank you for the tips, I incorporated both in the PR: https://github.com/fastai/fastai/pull/1052
I’m probably totally missing something so I apologize, but I see the bb_pad_collate function being defined but I can’t find it actually being used anywhere so it seems like the default data_collate method is being used for ObjectDetectDataset. If data_collate is being used instead of bb_pad_collate does this cause an issue or is bb_pad_collate being used and I’m just not finding it.
A collate function is to collate elements in a dataloader. There is no dataloader or databunch for object detection inside the library but when you want to build one, you’ll need to use that function. There’s one example in the docs (scroll a bit down from that link).