Update app.py
Browse files
app.py
CHANGED
|
@@ -5,13 +5,10 @@ from PIL import Image
|
|
| 5 |
import io
|
| 6 |
|
| 7 |
# function part
|
| 8 |
-
def generate_image_caption(
|
| 9 |
"""Generates a caption for the given image using a pre-trained model."""
|
| 10 |
img2caption = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
|
| 11 |
-
|
| 12 |
-
# Read the image file
|
| 13 |
-
image = Image.open(image_file)
|
| 14 |
-
|
| 15 |
# Generate caption
|
| 16 |
result = img2caption(image)
|
| 17 |
return result[0]['generated_text']
|
|
@@ -32,11 +29,12 @@ def main():
|
|
| 32 |
uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
|
| 33 |
|
| 34 |
if uploaded_image is not None:
|
| 35 |
-
|
|
|
|
| 36 |
|
| 37 |
# Stage 1: Image to Text
|
| 38 |
st.text('Processing img2text...')
|
| 39 |
-
image_caption = generate_image_caption(
|
| 40 |
st.write(image_caption)
|
| 41 |
|
| 42 |
if __name__ == "__main__":
|
|
|
|
| 5 |
import io
|
| 6 |
|
| 7 |
# function part
|
| 8 |
+
def generate_image_caption(image):
|
| 9 |
"""Generates a caption for the given image using a pre-trained model."""
|
| 10 |
img2caption = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
|
| 11 |
+
|
|
|
|
|
|
|
|
|
|
| 12 |
# Generate caption
|
| 13 |
result = img2caption(image)
|
| 14 |
return result[0]['generated_text']
|
|
|
|
| 29 |
uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
|
| 30 |
|
| 31 |
if uploaded_image is not None:
|
| 32 |
+
image = Image.open(uploaded_file).convert("RGB")
|
| 33 |
+
st.image(image, caption="Uploaded Image", use_column_width=True)
|
| 34 |
|
| 35 |
# Stage 1: Image to Text
|
| 36 |
st.text('Processing img2text...')
|
| 37 |
+
image_caption = generate_image_caption(image)
|
| 38 |
st.write(image_caption)
|
| 39 |
|
| 40 |
if __name__ == "__main__":
|