Update README.md

README.md

@@ -5,6 +5,7 @@ base_model: SmilingWolf/wd-swinv2-tagger-v3
 inference: false
 tags:
 - wd-tagger
+- optimum
 ---
 
 # WD SwinV2 Tagger v3 with 🤗 transformers
@@ -13,6 +14,14 @@ Converted from [SmilingWolf/wd-swinv2-tagger-v3](https://huggingface.co/SmilingW
 
 ## Example
 
+[![](https://camo.githubusercontent.com/f5e0d0538a9c2972b5d413e0ace04cecd8efd828d133133933dfffec282a4e1b/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667)](https://colab.research.google.com/gist/p1atdev/d420d9fcd5c8ea66d9e10918fc330741/wd-swinv2-tagger-v3-hf-pipe.ipynb)
+
+### Installation
+
+```bash
+pip install optimum[onnxruntime] transformers
+```
+
 ### Pipeline
 
 ```py
@@ -30,18 +39,10 @@ print(pipe("sample.webp", top_k=15))
 # {'label': 'dress', 'score': 0.9539461135864258},
 # {'label': 'hat', 'score': 0.9511678218841553},
 # {'label': 'outdoors', 'score': 0.9438753128051758},
-# {'label': 'sky', 'score': 0.9195725917816162},
-# {'label': 'sitting', 'score': 0.9178725481033325},
-# {'label': 'looking up', 'score': 0.9122412800788879},
-# {'label': 'short hair', 'score': 0.8630313873291016},
-# {'label': 'cloud', 'score': 0.8609118461608887},
-# {'label': 'brown hair', 'score': 0.7723952531814575},
-# {'label': 'short sleeves', 'score': 0.7649227380752563},
-# {'label': 'day', 'score': 0.7641971111297607},
-# {'label': 'rating:general', 'score': 0.7605368494987488},
-# {'label': 'white dress', 'score': 0.7596388459205627}]
+# ...
 ```
 
+
 ### AutoModel
 
 
@@ -81,22 +82,40 @@ print(results)  # rating tags and character tags are also included
 # 'dress': tensor(0.9539),
 # 'hat': tensor(0.9512),
 # 'outdoors': tensor(0.9439),
-# 'sky': tensor(0.9196),
-# 'sitting': tensor(0.9179),
-# 'looking up': tensor(0.9122),
-# 'short hair': tensor(0.8630),
-# 'cloud': tensor(0.8609),
-# 'brown hair': tensor(0.7724),
-# 'short sleeves': tensor(0.7649),
-# 'day': tensor(0.7642),
-# 'rating:general': tensor(0.7605),
 # ...
 ```
 
+### Accelerate with 🤗 Optimum
+
+Maybe about 30% faster and about 50% light weight model size than transformers version.
+
+```bash
+pip install optimum[onnxruntime] 
+```
+
+```diff
+-from transformers import pipeline
++from optimum.pipelines import pipeline
+
+pipe = pipeline(
+    "image-classification",
+    model="p1atdev/wd-swinv2-tagger-v3-hf",
+    trust_remote_code=True,
+)
+
+print(pipe("sample.webp", top_k=15))
+#[{'label': '1girl', 'score': 0.9973934888839722},
+# {'label': 'solo', 'score': 0.9719744324684143},
+# {'label': 'dress', 'score': 0.9539461135864258},
+# {'label': 'hat', 'score': 0.9511678218841553},
+# {'label': 'outdoors', 'score': 0.9438753128051758},
+# ...
+```
+
+
 ## Labels
 
 All of rating tags have prefix `rating:` and character tags have prefix `character:`.
 
 - Rating tags: `rating:general`, `rating:sensitive`, ...
-- Character tags: `character:frieren`, `character:hatsune miku`, ...
-
+- Character tags: `character:frieren`, `character:hatsune miku`, ...