# pip install -U transformers accelerate
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("eren23/pneumonia_test_attempt")
model = AutoModelForImageClassification.from_pretrained("eren23/pneumonia_test_attempt", device_map="auto")Quick Links
pneumonia-bielefeld-dl-course
This registry contains the model for making pneumonia predictions and was prepared for Bielefeld University Deep Learning course homework.
The code used for this implementation mostly comes from here: https://github.com/nateraw/huggingpics it was a ready pipeline for model fine-tuning with huggingface and PyTorch Lightning for another dataset.
- Downloads last month
- 9
Evaluation results
- Accuracyself-reported0.978
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="eren23/pneumonia_test_attempt") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")