README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- custom_code
|
5 |
+
---
|
6 |
+
# How to use
|
7 |
+
you can the model via the command
|
8 |
+
```python
|
9 |
+
from transformers import AutoModelForImageClassification
|
10 |
+
model = AutoModelForImageClassification.from_pretrained("not-lain/MyRepo", trust_remote_code=True)
|
11 |
+
```
|
12 |
+
or you can use the pipeline
|
13 |
+
```python
|
14 |
+
from transformers import pipeline
|
15 |
+
pipe = pipeline(model="not-lain/MyRepo", trust_remote_code=True)
|
16 |
+
pipe(
|
17 |
+
"url",
|
18 |
+
download=True, # will call the download_img method
|
19 |
+
clean_output=False # will be passed as postprocess_kwargs
|
20 |
+
)
|
21 |
+
```
|
22 |
+
# parameters
|
23 |
+
the pipeline supports the following parameters :
|
24 |
+
* download
|
25 |
+
* clean_output
|
26 |
+
|
27 |
+
you can also use the following method to download images from the web
|
28 |
+
```python
|
29 |
+
pipe.download_img(url)
|
30 |
+
```
|
31 |
+
|