Cross-channel LRN bounds checking for GPU implementation #1922
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Outdated suggestions cannot be applied.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.
Fixes #1864.
When the
local_size
of aLRNLayer
inACROSS_CHANNELS
mode is larger than the number of channels in a blob, we get some nasty indexing errors in the GPU implementation (the CPU implementation is fine). This pull request consists of two contributions:TestForwardAcrossChannelsLargeRegion
andTestGradientAcrossChannelsLargeRegion
that use alocal_size
of 15 on a blob with 7 channels. These tests break the current master implementation.As far as I can tell, this PR is complete, though if anyone finds anything wrong with it of course I'd be happy to fix.