Custom architectures with HuggingFace 🤗
not-lain
• • 30# Load model directly
from transformers import AutoModelForImageClassification
model = AutoModelForImageClassification.from_pretrained("not-lain/MyRepo", trust_remote_code=True, dtype="auto")Quick Links
how to create custom architectures
you can read this blogpost to find out more 📖
How to use
you can the model via the command
from transformers import AutoModelForImageClassification
model = AutoModelForImageClassification.from_pretrained("not-lain/MyRepo", trust_remote_code=True)
or you can use the pipeline
from transformers import pipeline
pipe = pipeline(model="not-lain/MyRepo", trust_remote_code=True)
pipe(
"url",
download=True, # will call the download_img method
clean_output=False # will be passed as postprocess_kwargs
)
parameters
the pipeline supports the following parameters :
- download
- clean_output
you can also use the following method to download images from the web
pipe.download_img(url)
- Downloads last month
- 19
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="not-lain/MyRepo", trust_remote_code=True) pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")