🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
fix: center_crop occasionally outputs off-by-one dimension matrix (#30934)
If required padding for a crop larger than input image is odd-numbered, the padding would be rounded down instead of rounded up, causing the output dimension to be one smaller than it should be.
M
Matthew Beckers committed
3b09d3f05f95629736bf5337ab118fa3327cc8c7
Parent: daf281f
Committed by GitHub <[email protected]>
on 5/21/2024, 12:56:52 PM