Instructions to use timm/swinv2_base_window12_192.ms_in22k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/swinv2_base_window12_192.ms_in22k with timm:
import timm model = timm.create_model("hf_hub:timm/swinv2_base_window12_192.ms_in22k", pretrained=True) - Transformers
How to use timm/swinv2_base_window12_192.ms_in22k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="timm/swinv2_base_window12_192.ms_in22k", device_map="auto") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/swinv2_base_window12_192.ms_in22k", dtype="auto", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Is this encoder pre-trained in a supervised or unsupervised fashion?
#1
by vadoriv - opened
It is unclear from the description whether the encoder swinv2_base_window12_192.ms_in22k corresponds to a model pre-trained using unsupervised learning or one trained for classification. I suspect it is the latter, but I am not certain. Could anyone clarify?