Update README.md
Browse files
README.md
CHANGED
@@ -87,7 +87,7 @@ print(results) # rating tags and character tags are also included
|
|
87 |
|
88 |
### Accelerate with 🤗 Optimum
|
89 |
|
90 |
-
Maybe about 30% faster and about 50% light weight model size than transformers version.
|
91 |
|
92 |
```bash
|
93 |
pip install optimum[onnxruntime]
|
@@ -104,11 +104,11 @@ pipe = pipeline(
|
|
104 |
)
|
105 |
|
106 |
print(pipe("sample.webp", top_k=15))
|
107 |
-
#[{'label': '1girl', 'score': 0.
|
108 |
-
# {'label': 'solo', 'score': 0.
|
109 |
-
# {'label': 'dress', 'score': 0.
|
110 |
-
# {'label': 'hat', 'score': 0.
|
111 |
-
# {'label': 'outdoors', 'score': 0.
|
112 |
# ...
|
113 |
```
|
114 |
|
|
|
87 |
|
88 |
### Accelerate with 🤗 Optimum
|
89 |
|
90 |
+
Maybe about 30% faster and about 50% light weight model size than transformers version, but the accuracy is slightly degraded.
|
91 |
|
92 |
```bash
|
93 |
pip install optimum[onnxruntime]
|
|
|
104 |
)
|
105 |
|
106 |
print(pipe("sample.webp", top_k=15))
|
107 |
+
#[{'label': '1girl', 'score': 0.9966088533401489},
|
108 |
+
# {'label': 'solo', 'score': 0.9740601778030396},
|
109 |
+
# {'label': 'dress', 'score': 0.9618403911590576},
|
110 |
+
# {'label': 'hat', 'score': 0.9563733339309692},
|
111 |
+
# {'label': 'outdoors', 'score': 0.945336639881134},
|
112 |
# ...
|
113 |
```
|
114 |
|