search

HRNet / HRNet-Semantic-Segmentation

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
Other
3.16k stars 690 forks source link

How to use this function? elif 'test' in config.DATASET.TEST_SET: to Visualize the result. #143

Open sunny0414 opened 4 years ago

sunke123 commented 4 years ago

We save the segmentation mask in the testing process.

If you want to visualize the results, you can set the sv_pred flag as true.

https://github.com/HRNet/HRNet-Semantic-Segmentation/blob/f7dab6fb6344bbe9fee6606955c526f2e969931b/lib/core/function.py#L103

https://github.com/HRNet/HRNet-Semantic-Segmentation/blob/f7dab6fb6344bbe9fee6606955c526f2e969931b/lib/core/function.py#L154

sunny0414 commented 4 years ago

If I set the sv_pred flag as true，then，if I need to write additional codes to disaplay the segmentation mask? I'm sorry to ask the Inferior question and I'm just satring learn the deep learing.

sunke123 commented 4 years ago

You can find the segmentation mask under the given sv_dir without any extra codes.

sunny0414 commented 4 years ago

Thanks you sir,I find the dir.

umairanis03 commented 4 years ago

Hi @sunny0414 How did you inference on your own images?