Open rod409 opened 3 years ago
This pull request proposes a bug fix. In base_loader.py, the read_images function generates a mask without checking keys in an original copy. This causes problems on some datasets where mask values are incorrectly replaced. The change would make the mask generation in the base_loader.py match the method used in uniform.py. https://github.com/NVIDIA/semantic-segmentation/blob/7726b144c2cc0b8e09c67eabb78f027efdf3f0fa/datasets/base_loader.py#L176-L178 https://github.com/NVIDIA/semantic-segmentation/blob/7726b144c2cc0b8e09c67eabb78f027efdf3f0fa/datasets/uniform.py#L112-L115
This pull request proposes a bug fix. In base_loader.py, the read_images function generates a mask without checking keys in an original copy. This causes problems on some datasets where mask values are incorrectly replaced. The change would make the mask generation in the base_loader.py match the method used in uniform.py. https://github.com/NVIDIA/semantic-segmentation/blob/7726b144c2cc0b8e09c67eabb78f027efdf3f0fa/datasets/base_loader.py#L176-L178 https://github.com/NVIDIA/semantic-segmentation/blob/7726b144c2cc0b8e09c67eabb78f027efdf3f0fa/datasets/uniform.py#L112-L115