Add model files

README.md

@@ -1,3 +1,31 @@
 ---
 license: apache-2.0
+library_name: timm
 ---
+# WD SwinV2 Tagger v3
+
+Supports ratings, characters and general tags.
+
+Trained using https://github.com/SmilingWolf/JAX-CV.  
+TPUs used for training kindly provided by the [TRC program](https://sites.research.google/trc/about/).
+
+## Dataset
+Last image id: 7220105  
+Trained on Danbooru images with IDs modulo 0000-0899.  
+Validated on images with IDs modulo 0950-0999.  
+Images with less than 10 general tags were filtered out.  
+Tags with less than 600 images were filtered out.
+
+## Validation results
+`P=R: threshold = 0.xxxx, F1 = 0.xxxx`
+
+## What's new
+Model v1.0/Dataset v3:  
+More training images, more and up-to-date tags (up to 2024-02-28).  
+Now `timm` compatible! Load it up and give it a spin using the canonical one-liner!  
+ONNX model is compatible with code developed for the v2 series of models.  
+The batch dimension of the ONNX model is not fixed to 1 anymore. Now you can go crazy with batch inference.
+
+## Final words
+Subject to change and updates.
+Downstream users are encouraged to use tagged releases rather than relying on the head of the repo.

config.json

@@ -0,0 +1,37 @@
+{
+  "architecture": "swinv2_base_window8_256",
+  "num_classes": 10861,
+  "num_features": 1024,
+  "global_pool": "avg",
+  "model_args": {
+    "act_layer": "gelu_tanh",
+    "img_size": 448,
+    "window_size": 14
+  },
+  "pretrained_cfg": {
+    "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
+  }
+}

model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcdeb6cf20b4674c02bb2761109e2ed40a850d72c24de2ee093de143b83fb66d
+size 413777297

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622d33fc180ed3ecbd886a5318059ea03b5a6df93c170662725104c339cb8b9c
+size 467460978

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a626e5dd214c0c0d36894c62296d2c74c9fec8399b4ce6664dfd239bd40816
+size 392149220

sw_jax_cv_config.json

@@ -0,0 +1,18 @@
+{
+    "model_name": "swinv2_base",
+    "model_args": {
+        "image_size": 448,
+        "patch_size": 4,
+        "in_chans": 3,
+        "num_classes": 10861,
+        "embed_dim": 128,
+        "window_size": 14,
+        "mlp_ratio": 4.0,
+        "qkv_bias": true,
+        "drop_rate": 0.0,
+        "attn_drop_rate": 0.0,
+        "drop_path_rate": 0.1,
+        "patch_norm": true,
+        "layer_norm_eps": 1e-05
+    }
+}