A Gaussian Noise test was performed on resnet-50
, in which
a 30% failure rate was observed.
In at least one case, the model's prediction changed 0.99. This caused the label to change from schipperke to soccer ball.
This test measures the robustness of the model to Gaussian Noise transformations. It does this by taking a sample input, adding gaussian noise to the image, and measuring the behavior of the model on the transformed input.
Production inputs can have unusual variations amongst many different dimensions, ranging from lighting changes to sensor errors to compression artifacts. It is important that the models are robust to the introduction of such variations.
resnet-50
pkg:huggingface/microsoft/resnet-50@f5104f67a0a8892c17fa776add3e55999dc67893
This report was automatically generated by the scanning engine rime-0.21.0rc4.post195+git.2a88076b.d
on 2023-01-07 17:28.