Instructions to use Jiqing/resnet-backbone-downsample_in_bottleneck with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jiqing/resnet-backbone-downsample_in_bottleneck with Transformers:
# Load model directly from transformers import AutoImageProcessor, ResNetBackbone processor = AutoImageProcessor.from_pretrained("Jiqing/resnet-backbone-downsample_in_bottleneck") model = ResNetBackbone.from_pretrained("Jiqing/resnet-backbone-downsample_in_bottleneck", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- e8764bb8b0ee7f6b47dce329673876caf3cb380f51faed71e1f1369a634416ce
- Size of remote file:
- 94.4 MB
- SHA256:
- 508328391d53041d8ff6188c27bd2801157d9ea06f2f0932e5b7287b48786ae0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.