Image Classification
timm
PyTorch
English
timm/vit_base_patch16_224.orig_in21k_ft_in1k
cifar100
Eval Results (legacy)
Instructions to use edadaltocg/vit_base_patch16_224_in21k_ft_cifar100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use edadaltocg/vit_base_patch16_224_in21k_ft_cifar100 with timm:
import timm model = timm.create_model("hf_hub:edadaltocg/vit_base_patch16_224_in21k_ft_cifar100", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Preprocessing pipeline for inference
#2
by akulpakul - opened
Hi,
I am trying to set up the model for inference. I am getting to an accuracy 93.09%. I would like to know what I'm missing in my setup:
transform_test = transforms.Compose([
transforms.Resize((249, 249), interpolation=Image.BICUBIC), # Resize using bicubic interpolation
transforms.CenterCrop(224), # to get close to 90% crop pct
transforms.ToTensor(), # Convert to tensor
transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) # Normalize with specified mean and std
])
Thanks, and great job on open sourcing so many models :)