# pip install -U transformers accelerate
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("hungdang1610/gender")
model = AutoModelForImageClassification.from_pretrained("hungdang1610/gender", device_map="auto")Quick Links
tags:
- image-classification
- pytorch metrics:
- accuracy
model-index: - name: gender-classification results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.970833
gender-classification
Evaluate set: 240 unseen images, from 27/05-29/05 from ShotX, no duplicate, clean, 120 male and 120 female. Loss function is CrossEntropy. Model finetuning on 1827 images from 15/05-21/05 from ShotX, base on rizvandwiki/gender-classification. . Using AdamW optimizer, weight_decay=0.05, CosineAnnealingLR scheduler, learning rate 5e-6, 20 epochs.
accuracy loss
0.970833 0.102212
Example Images
female
male
- Downloads last month
- 229
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="hungdang1610/gender") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")