Perturb submission from 5EnfSKsX (sha256 abd7f3dec8bcc9d3)

README.md

@@ -0,0 +1,32 @@
+---
+license: apache-2.0
+library_name: torchvision
+tags:
+  - image-classification
+  - adversarial-training
+  - efficientnet
+  - perturb
+  - bittensor
+---
+
+# imagemdtr/efficientnet-v2-l-adv-model
+
+EfficientNetV2-L (torchvision `efficientnet_v2_l`, 1000 ImageNet classes) fine-tuned with
+adversarial training for the [Perturb](https://perturbai.io) subnet (netuid 26).
+
+- miner hotkey: `5EnfSKsX6V6yihDsQrnHUNAMEnwZ6yPR49XvE5EEUbhMzowE`
+- weights: `model.safetensors` (sha256 `abd7f3dec8bcc9d3a1951464155686ee5fd5e49251d4f06827313861705ec89d`)
+- preprocessing: resize 480 (bicubic, antialias) → center crop
+  480 → normalize mean=[0.5, 0.5, 0.5] std=[0.5, 0.5, 0.5]
+  (identical to `EfficientNet_V2_L_Weights.IMAGENET1K_V1.transforms()`)
+
+
+
+## Load
+
+```python
+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"))
+```

config.json

@@ -0,0 +1,24 @@
+{
+  "architecture": "efficientnet_v2_l",
+  "framework": "torchvision",
+  "num_classes": 1000,
+  "base_weights": "torchvision/EfficientNet_V2_L_Weights.IMAGENET1K_V1",
+  "weights_file": "model.safetensors",
+  "preprocess": {
+    "resize": 480,
+    "crop": 480,
+    "interpolation": "bicubic",
+    "antialias": true,
+    "mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "std": [
+      0.5,
+      0.5,
+      0.5
+    ]
+  },
+  "step": 800
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd7f3dec8bcc9d3a1951464155686ee5fd5e49251d4f06827313861705ec89d
+size 476270096