| library_name: pytorch | |
| tags: | |
| - vision-transformer | |
| - cifar-100 | |
| - imagenet-200 | |
| - in-synapse-activation | |
| # ISA Vision checkpoints | |
| Model-only PyTorch checkpoints for the ISA vision experiments. The repository contains CIFAR-100 and ImageNet-200 checkpoints for hybrid and physical models at tiny, mid, and small scales. | |
| ## Device equation | |
| The physical operator evaluates | |
| \[ | |
| I(V,V_{th}) = I_S\frac{\operatorname{softplus}^2\!\left(\frac{V-V_{th}}{2nU_T}\right)-\operatorname{softplus}^2\!\left(\frac{V-V_{th}-V_D}{2nU_T}\right)}{1+V/V_{sat}}. | |
| \] | |
| The checkpoint tensors already contain the fitted threshold and TIA parameters required by this operator. | |
| ## Layout | |
| ```text | |
| {cifar100,imagenet200}/{hybrid,physical}/{tiny,mid,small}/model.pt | |
| ``` | |
| ## Loading | |
| ```python | |
| import torch | |
| from huggingface_hub import hf_hub_download | |
| path = hf_hub_download( | |
| repo_id="Viligance/ISA-Vision", | |
| filename="cifar100/physical/small/model.pt", | |
| ) | |
| checkpoint = torch.load(path, map_location="cpu") | |
| model.load_state_dict(checkpoint["model"], strict=True) | |
| model.eval() | |
| ``` | |
| `checkpoint_manifest.json` records each file's SHA256 digest, size, layer count, and evaluation metadata. `release_validation.json` summarizes artifact checks. | |