chethu commited on
Commit
7e17841
·
verified ·
1 Parent(s): b000cd6

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +27 -22
app.py CHANGED
@@ -1,27 +1,32 @@
1
- import gradio as gr
 
 
 
2
  from transformers import pipeline
 
 
 
 
 
 
 
 
 
 
 
 
3
 
4
- # Load the image-to-text pipeline
5
- image_to_text_pipelines = {
6
- "Salesforce/blip-image-captioning-base": pipeline("image-to-text", model="Salesforce/blip-image-captioning-base"),
7
- # Add more models if needed
8
- }
9
 
10
- def generate_caption(input_image, model_name="Salesforce/blip-image-captioning-base"):
11
- # Generate caption for the input image using the selected model
12
- image_to_text_pipeline = image_to_text_pipelines[model_name]
13
- caption = image_to_text_pipeline(input_image)[0]['generated_text']
14
- return caption
15
 
16
- # Interface for launching the model
17
- interface = gr.Interface(
18
- fn=generate_caption,
19
- inputs=gr.Image(type='pil', label="Input Image"),
20
- outputs="text",
21
- title="Image Captioning Model",
22
- description="This model generates captions for images.",
23
- theme="default",
24
- )
25
 
26
- # Launch the interface
27
- interface.launch()
 
 
 
 
 
1
+ import streamlit as st
2
+ from PIL import Image
3
+ from PIL import Image, ImageDraw
4
+ from image_whisper_helper import summarize_predictions_natural_language, render_results_in_image
5
  from transformers import pipeline
6
+ from tokenizers import Tokenizer, Encoding
7
+ from tokenizers import decoders
8
+ from tokenizers import models
9
+ from tokenizers import normalizers
10
+ from tokenizers import pre_tokenizers
11
+ from tokenizers import processors
12
+ import io
13
+ import matplotlib.pyplot as plt
14
+ import requests
15
+ import inflect
16
+ from PIL import Image
17
+ from predictions import get_predictions # Replace 'your_module' with the name of the module where your function is defined
18
 
19
+ def main():
20
+ st.title("Object Detection App")
 
 
 
21
 
22
+ uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
 
 
 
 
23
 
24
+ if uploaded_image is not None:
25
+ processed_image, text, audio = get_predictions(uploaded_image)
 
 
 
 
 
 
 
26
 
27
+ st.image(processed_image, caption='Processed Image', use_column_width=True)
28
+ st.write(f"Predictions: {text}")
29
+ st.audio(audio, format='audio/wav')
30
+
31
+ if __name__ == '__main__':
32
+ main()