# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("fxmarty/tiny-testing-remote-code", trust_remote_code=True)
model = AutoModelForImageClassification.from_pretrained("fxmarty/tiny-testing-remote-code", trust_remote_code=True)Quick Links
Use at your own risk:
from transformers import AutoFeatureExtractor, AutoModelForImageClassification
from datasets import load_dataset
import torch
feature_extractor = AutoFeatureExtractor.from_pretrained("fxmarty/tiny-testing-remote-code")
model = AutoModelForImageClassification.from_pretrained("fxmarty/tiny-testing-remote-code", trust_remote_code=True)
dataset = load_dataset("huggingface/cats-image")
image = dataset["test"]["image"][0]
inputs = feature_extractor(image, return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits
# model predicts one of the 1000 ImageNet classes
predicted_label = logits.argmax(-1).item()
print(model.config.id2label[predicted_label])
- Downloads last month
- 23
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="fxmarty/tiny-testing-remote-code", trust_remote_code=True) pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")