Upload 3 files

README.md

@@ -0,0 +1,12 @@
+---
+license: apache-2.0
+library_name: timm
+tags:
+- image-feature-extraction
+- timm
+---
+# Model card for vit_base_patch16_224_waifumerge
+
+A Vision Transformer (ViT) image feature model. Trained with Self-Supervised DINO method.
+
+[Model Stock](https://github.com/naver-ai/model-stock) merge of *vit_base_patch16_224.dino*, *vit_base_patch16_224.augreg2_in21k_ft_in1k* and *wd-vit-tagger-v3* just to see what would happen ¯\_(ツ)_/¯

config.json

@@ -0,0 +1,40 @@
+{
+  "architecture": "vit_base_patch16_224",
+  "num_classes": 10861,
+  "num_features": 768,
+  "global_pool": "avg",
+  "model_args": {
+    "img_size": 448,
+    "class_token": false,
+    "global_pool": "avg",
+    "fc_norm": false,
+    "act_layer": "gelu_tanh"
+  },
+  "pretrained_cfg": {
+    "tag": "waifumerge",
+    "custom_load": false,
+    "input_size": [
+      3,
+      448,
+      448
+    ],
+    "fixed_input_size": false,
+    "interpolation": "bicubic",
+    "crop_pct": 1.0,
+    "crop_mode": "center",
+    "mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "num_classes": 10861,
+    "pool_size": null,
+    "first_conv": null,
+    "classifier": null
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf570937ea78f75df7c9d95b0b8378e79f2bd90c9b6b79573439f5e0e96ec9e4
+size 343250456