How to control input image dimensions of the network models?

qubvel-org / segmentation_models.pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

https://smp.readthedocs.io/

MIT License

9.52k stars 1.66k forks source link

How to control input image dimensions of the network models? #379

Closed hannes09 closed 2 years ago

hannes09 commented 3 years ago

Hi, can you explain how to contol the input dimensions of the images when training a network e. g. in https://github.com/qubvel/segmentation_models.pytorch/blob/master/examples/cars%20segmentation%20(camvid).ipynb

Lets assume my training data is 4K, but network should be trained with 1K resolution. Can I just rescale my training data and the network is always trained with my input image resolution?

github-actions[bot] commented 2 years ago

This issue is stale because it has been open 60 days with no activity. Remove stale label or comment or this will be closed in 7 days.

github-actions[bot] commented 2 years ago

This issue was closed because it has been stalled for 7 days with no activity.