OBA-Research commited on
Commit
9f450e7
·
verified ·
1 Parent(s): 29627c3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -6
README.md CHANGED
@@ -93,14 +93,17 @@ Follow the official PyTorch installation guide for your platform:
93
 
94
  VAAS will automatically detect PyTorch at runtime and raise a clear error if it is missing.
95
 
96
-
97
  ## Usage
98
 
99
- ### Basic inference
 
 
100
 
101
  ```python
102
  from vaas.inference.pipeline import VAASPipeline
103
  from PIL import Image
 
 
104
 
105
  pipeline = VAASPipeline.from_pretrained(
106
  "OBA-Research/vaas-v1-df2023",
@@ -108,11 +111,18 @@ pipeline = VAASPipeline.from_pretrained(
108
  alpha=0.5
109
  )
110
 
111
- image = Image.open("example.jpg").convert("RGB")
 
 
 
 
 
 
112
  result = pipeline(image)
113
 
114
  print(result)
115
  anomaly_map = result["anomaly_map"]
 
116
  ```
117
 
118
  #### Output Format
@@ -126,7 +136,7 @@ anomaly_map = result["anomaly_map"]
126
  }
127
  ```
128
 
129
- ### Inference with visual explanation
130
 
131
  VAAS can also generate a qualitative visualization combining:
132
 
@@ -135,8 +145,9 @@ VAAS can also generate a qualitative visualization combining:
135
  * Final hybrid anomaly score (S_H)
136
 
137
  ```python
 
138
  pipeline.visualize(
139
- image="image.jpg",
140
  save_path="vaas_visualization.png",
141
  mode="all", # options: "all", "px", "binary", "fx"
142
  threshold=0.5,
@@ -236,6 +247,14 @@ If you use VAAS in your research, please cite both the software and the associat
236
 
237
  ---
238
 
 
 
 
 
 
 
 
 
239
  ## License
240
 
241
  MIT License
@@ -245,4 +264,5 @@ MIT License
245
  ## Maintainers
246
 
247
  **OBA-Research**
248
- [https://huggingface.co/OBA-Research](https://huggingface.co/OBA-Research)
 
 
93
 
94
  VAAS will automatically detect PyTorch at runtime and raise a clear error if it is missing.
95
 
 
96
  ## Usage
97
 
98
+ ---
99
+
100
+ ### 1. Basic inference on local and online images
101
 
102
  ```python
103
  from vaas.inference.pipeline import VAASPipeline
104
  from PIL import Image
105
+ import requests
106
+ from io import BytesIO
107
 
108
  pipeline = VAASPipeline.from_pretrained(
109
  "OBA-Research/vaas-v1-df2023",
 
111
  alpha=0.5
112
  )
113
 
114
+ # # Option A: Using a local image
115
+ # image = Image.open("example.jpg").convert("RGB")
116
+ # result = pipeline(image)
117
+
118
+ # Option B: Using an online image
119
+ url = "https://raw.githubusercontent.com/OBA-Research/VAAS/main/examples/images/COCO_DF_C110B00000_00539519.jpg"
120
+ image = Image.open(BytesIO(requests.get(url).content)).convert("RGB")
121
  result = pipeline(image)
122
 
123
  print(result)
124
  anomaly_map = result["anomaly_map"]
125
+
126
  ```
127
 
128
  #### Output Format
 
136
  }
137
  ```
138
 
139
+ ### 2. Inference with visual explanation
140
 
141
  VAAS can also generate a qualitative visualization combining:
142
 
 
145
  * Final hybrid anomaly score (S_H)
146
 
147
  ```python
148
+
149
  pipeline.visualize(
150
+ image=image,
151
  save_path="vaas_visualization.png",
152
  mode="all", # options: "all", "px", "binary", "fx"
153
  threshold=0.5,
 
247
 
248
  ---
249
 
250
+ ## Contributing
251
+
252
+ We welcome contributions that improve the usability, robustness, and extensibility of VAAS.
253
+
254
+ Please see the full guidelines on [**Github**](https://github.com/OBA-Research/VAAS) in **[CONTRIBUTING.md](https://github.com/OBA-Research/VAAS/blob/main/CONTRIBUTING.md)**.
255
+
256
+ ---
257
+
258
  ## License
259
 
260
  MIT License
 
264
  ## Maintainers
265
 
266
  **OBA-Research**
267
+ - [https://github.com/OBA-Research](https://github.com/OBA-Research)
268
+ - [https://huggingface.co/OBA-Research](https://huggingface.co/OBA-Research)