mailmail85/perturb-effv2l-adv

EfficientNetV2-L (torchvision efficientnet_v2_l, 1000 ImageNet classes) fine-tuned with adversarial training for the Perturb subnet (netuid 26).

  • miner hotkey: 5DLYHxKa1a65NXipakC7WV1fPq4SMjKYivdXGp9D4QEJjNfL
  • on-chain hash: sha256(model.safetensors || hotkey) = 1bbe02b1dc5be2068654ff766eefd4a34a4f30458449ca3be6cd373f468dbcb1
  • preprocessing: EfficientNet_V2_L_Weights.IMAGENET1K_V1.transforms() (bicubic resize 480, center crop 480, mean = std = 0.5)
from safetensors.torch import load_file
from torchvision.models import efficientnet_v2_l
model = efficientnet_v2_l(weights=None)
model.load_state_dict(load_file("model.safetensors"))
Downloads last month
27
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support