Vishakaraj commited on
Commit
84f9b87
1 Parent(s): 2dc45c3

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. README.md +2 -8
  2. app.py +26 -0
  3. example_1.jpg +0 -0
  4. example_2.jpg +0 -0
  5. example_3.jpg +0 -0
  6. requirements.txt +1 -0
README.md CHANGED
@@ -1,12 +1,6 @@
1
  ---
2
- title: Image Captioning
3
- emoji: 🔥
4
- colorFrom: yellow
5
- colorTo: pink
6
  sdk: gradio
7
  sdk_version: 3.44.1
8
- app_file: app.py
9
- pinned: false
10
  ---
11
-
12
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
  ---
2
+ title: Image_Captioning
3
+ app_file: app.py
 
 
4
  sdk: gradio
5
  sdk_version: 3.44.1
 
 
6
  ---
 
 
app.py ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import torch
2
+ from PIL import Image
3
+ import gradio as gr
4
+
5
+ from lavis.models import load_model_and_preprocess
6
+
7
+ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
8
+
9
+ model, vis_processors, _ = load_model_and_preprocess(
10
+ name="blip_caption", model_type="large_coco", is_eval=True, device=device
11
+ )
12
+
13
+ def predict(image):
14
+ pre_processed_image = vis_processors["eval"](image).unsqueeze(0).to(device)
15
+ response = model.generate({"image": pre_processed_image}, use_nucleus_sampling=True, num_captions=3)
16
+ return image, ",\n".join(response)
17
+
18
+ demo = gr.Interface(
19
+ title="Image Captioning - BLIP",
20
+ fn=predict,
21
+ inputs=gr.Image(type='pil', label="Original Image"),
22
+ outputs=[gr.Image(type="pil"), gr.Textbox()],
23
+ examples=["example_1.jpg", "example_2.jpg"],
24
+ )
25
+
26
+ demo.launch()
example_1.jpg ADDED
example_2.jpg ADDED
example_3.jpg ADDED
requirements.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ salesforce-lavis