efficientnetv2-xl-upsample-exp2
EfficientNetV2-XL fine-tuned on CIFAR-10 upsampled to 224x224.
Fine-tuned from ImageNet-pretrained weights (timm name tf_efficientnetv2_xl) on
CIFAR-10 as part of a native-resolution vs upsampling study.
Evaluation results (CIFAR-10 test set, 10,000 images)
| Metric | Value |
|---|---|
| Top-1 accuracy | 99.07% |
| Top-5 accuracy | 99.94% |
| F1 (macro) | 0.9907 |
| AUC (macro) | 0.9993 |
| ECE | 0.1157 |
- Parameters: 206.85M
- Input: CIFAR images upsampled to 224x224
- Preprocessing: resize to 224x224, then normalize with
CIFAR-10 mean
[0.4914, 0.4822, 0.4465]and std[0.247, 0.2435, 0.2616].
Usage
from cifar_classifier import CIFAR10Classifier
clf = CIFAR10Classifier.from_pretrained("DeKUT-DSAIL/convnextv2-huge-cifar10-upsample")
label, probs = clf.predict("image.jpg")
print(label, probs)
Get cifar_classifier.py from the hf_deployment/ folder of the training
repository. It only needs torch, torchvision, timm, Pillow and
huggingface_hub.
Classes
airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck
- Downloads last month
- -