metadata
license: apache-2.0
library_name: torchvision
tags:
- image-classification
- adversarial-training
- efficientnet
- perturb
- bittensor
Samonte/pertrub158
EfficientNetV2-L (torchvision efficientnet_v2_l, 1000 ImageNet classes) fine-tuned with adversarial
training for the Perturb subnet (netuid 26).
- miner hotkey:
5H8t4i1evmMSDvwQstyWrxGNTVP2ykakEahnpwg5SaDmaZxH - on-chain hash: sha256(model.safetensors || hotkey) =
2d8b029b34fdd26ea31e504ea935e0f69d74a98551a25a20a229156ca17b29be - 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"))