| library_name: segmentation-models-pytorch | |
| license: other | |
| pipeline_tag: image-classification | |
| tags: | |
| - segmentation-models-pytorch | |
| - image-classification | |
| - pytorch | |
| - resnet | |
| languages: | |
| - python | |
| # Model card for resnet50. | |
| This repository contains the `swsl` pre-trained weights for the `resnet50` model used as | |
| encoder in the [segmentation-models-pytorch](https://github.com/qubvel-org/segmentation_models.pytorch) library. | |
| ### Example usage: | |
| 1. Install the library: | |
| ```bash | |
| pip install segmentation-models-pytorch | |
| ``` | |
| 2. Use the encoder in your code: | |
| ```python | |
| import segmentation_models_pytorch as smp | |
| model = smp.Unet("resnet50", encoder_weights="swsl") | |
| ``` | |
| ### References | |
| - Github: https://github.com/qubvel/segmentation_models.pytorch | |
| - Docs: https://smp.readthedocs.io/en/latest/ | |
| - Original weights URL: https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_weakly_supervised_resnet50-16a12f1b.pth | |