aliabd HF staff commited on
Commit
e23f7c0
1 Parent(s): 931d54b

Upload with huggingface_hub

Browse files
Files changed (3) hide show
  1. DESCRIPTION.md +1 -0
  2. README.md +1 -1
  3. app.py +0 -9
DESCRIPTION.md ADDED
@@ -0,0 +1 @@
 
 
1
+ Image segmentation using DETR. Takes in both an inputu image and the desired confidence, and returns a segmented image.
README.md CHANGED
@@ -1,7 +1,7 @@
1
 
2
  ---
3
  title: image_segmentation
4
- emoji: 🤗
5
  colorFrom: indigo
6
  colorTo: indigo
7
  sdk: gradio
 
1
 
2
  ---
3
  title: image_segmentation
4
+ emoji: 🔥
5
  colorFrom: indigo
6
  colorTo: indigo
7
  sdk: gradio
app.py CHANGED
@@ -1,20 +1,14 @@
1
- # URL: https://huggingface.co/spaces/gradio/image_segmentation/
2
- # DESCRIPTION: Image segmentation using DETR. Takes in both an inputu image and the desired confidence, and returns a segmented image.
3
- # imports
4
  import gradio as gr
5
  import torch
6
  import random
7
  import numpy as np
8
  from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation
9
 
10
-
11
- # load model
12
  device = torch.device("cpu")
13
  model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-tiny-ade").to(device)
14
  model.eval()
15
  preprocessor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-tiny-ade")
16
 
17
- # define core and helper fns
18
  def visualize_instance_seg_mask(mask):
19
  image = np.zeros((mask.shape[0], mask.shape[1], 3))
20
  labels = np.unique(mask)
@@ -37,8 +31,6 @@ def query_image(img):
37
  results = visualize_instance_seg_mask(results)
38
  return results
39
 
40
- # define interface
41
-
42
  demo = gr.Interface(
43
  query_image,
44
  inputs=[gr.Image()],
@@ -47,5 +39,4 @@ demo = gr.Interface(
47
  examples=[["example_2.png"]]
48
  )
49
 
50
- # launch
51
  demo.launch()
 
 
 
 
1
  import gradio as gr
2
  import torch
3
  import random
4
  import numpy as np
5
  from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation
6
 
 
 
7
  device = torch.device("cpu")
8
  model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-tiny-ade").to(device)
9
  model.eval()
10
  preprocessor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-tiny-ade")
11
 
 
12
  def visualize_instance_seg_mask(mask):
13
  image = np.zeros((mask.shape[0], mask.shape[1], 3))
14
  labels = np.unique(mask)
 
31
  results = visualize_instance_seg_mask(results)
32
  return results
33
 
 
 
34
  demo = gr.Interface(
35
  query_image,
36
  inputs=[gr.Image()],
 
39
  examples=[["example_2.png"]]
40
  )
41
 
 
42
  demo.launch()