OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-07 12:21:27 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity

CoreML backend should log on failure not success (#82604)

Browse Source 
### Description
The original intention of this code was to log whenever inference fails, not whenever it succeeds. This change updates the logic of should_log to match this intention.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/82604
Approved by: https://github.com/SS-JIA
This commit is contained in:
John Detloff 2022-08-02 04:14:43 +00:00 committed by PyTorch MergeBot
parent 09a6d0b5bb
commit 7d490dba72
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
torch/csrc/jit/backends/coreml/objc/PTMCoreMLBackend.mm
View File

@ -187,8 +187,7 @@ class CoreMLBackend: public torch::jit::PyTorchBackendInterface {
// Check if this inference session is logged. If so, log every N inferences
bool succeeded = outputsProvider != nil;
bool should_log = load_id < kSampleThreshold && inferences > 1;
should_log = should_log && (inferences % kSampleEvery == 0);
should_log = should_log || succeeded;
should_log = !succeeded || (should_log && (inferences % kSampleEvery == 0));
observer->onExitExecuteModel(instance_key, inferences, succeeded, should_log);
}