Conversation
It doesn't make sense to complain about input not being batch-sized if it isn't even 4-d in the first place.
An input_scale of zero should produce warnings/errors/infinities rather than being the same as an input_scale of one. A channel_order of () or 0 should not be equivalent to the default ordering.
Member
|
Thanks for the Python fixes Jon! I'll combine with improvements from #735 and release to master. |
This was referenced Jul 28, 2014
Merged
RazvanRanca
pushed a commit
to RazvanRanca/caffe
that referenced
this pull request
Nov 4, 2014
pycaffe fixes
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I haven't tested these exact commits yet, although I've made the same changes elsewhere in the past.
These three commits:
set_meanis never called,channel_orderandinput_scaleso that pathological input behaves closer to expectation.Expanding on the last point in particular:
input_scaleto zero is the same as settinginput_scaleto one, due to the checkif input_scale. Allowing the multiplication/division by zero properly breaks things or produces warnings.channel_orderto()or0is the same as setting it to the identity, due to the checkif channel_order. Note that both of these are valid indices in numpy, although actually using them in this context is probably a mistake. Allowing the indexing will make such usages crash in most cases, instead of continuing as if the input were valid.