Spaces:
Running
Running
File size: 3,495 Bytes
6459986 6c79114 d1dce8a 6c79114 1d8d466 5f554b3 6c79114 5f554b3 6c79114 d1dce8a 6c79114 d1dce8a 02d80b6 80e2b7f 6c79114 80e2b7f 6c79114 80e2b7f 6c79114 80e2b7f 6c79114 80e2b7f 6c79114 d9ec95b 6c79114 40a87e2 6c79114 0837489 80e2b7f 6c79114 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
import os
import re
import io
import streamlit as st
from PIL import Image, ImageDraw
from google import genai
from google.genai import types
# Hilfsfunktionen
def parse_list_boxes(text):
"""Extrahiert Bounding Boxes aus dem Antworttext"""
pattern = r'\[([\d\.]+),\s*([\d\.]+),\s*([\d\.]+),\s*([\d\.]+)\]'
matches = re.findall(pattern, text)
return [[float(m) for m in match] for match in matches]
def draw_bounding_boxes(image, boxes):
"""Zeichnet Bounding Boxes auf das Bild"""
draw = ImageDraw.Draw(image)
width, height = image.size
for box in boxes:
ymin, xmin, ymax, xmax = box
draw.rectangle([
xmin * width,
ymin * height,
xmax * width,
ymax * height
], outline="red", width=3)
return image
# Streamlit UI
st.title("Bildanalyse mit Gemini")
col1, col2 = st.columns(2)
with col1:
uploaded_file = st.file_uploader("Bild hochladen", type=["jpg", "png", "jpeg"])
object_name = st.text_input("Objekt zur Erkennung", placeholder="z.B. 'Auto', 'Person'")
if uploaded_file and object_name:
image = Image.open(uploaded_file)
st.image(image, caption="Hochgeladenes Bild", use_container_width=True)
if st.button("Analysieren"):
with st.spinner("Analysiere Bild..."):
try:
# Bildvorbereitung
image_bytes = io.BytesIO()
image.save(image_bytes, format=image.format)
image_part = types.Part.from_bytes(
data=image_bytes.getvalue(),
mime_type=f"image/{image.format.lower()}"
)
# API-Client
client = genai.Client(api_key=os.getenv("KEY"))
# Bildbeschreibung
desc_response = client.models.generate_content(
model="gemini-2.0-flash-exp",
contents=["Beschreibe dieses Bild detailliert.", image_part]
)
# Objekterkennung
detection_prompt = (
f"Gib alle Bounding Boxes für {object_name} im Format "
"[ymin, xmin, ymax, xmax] als Liste. Nur die Liste zurückgeben!"
)
box_response = client.models.generate_content(
model="gemini-1.0-pro-vision",
contents=[detection_prompt, image_part]
)
# Verarbeitung
boxes = parse_list_boxes(box_response.text)
annotated_image = image.copy()
if boxes:
annotated_image = draw_bounding_boxes(annotated_image, boxes)
result_text = f"{len(boxes)} {object_name} erkannt"
else:
result_text = "Keine Objekte gefunden"
# Ergebnisse anzeigen
with col2:
st.write("## Beschreibung:")
st.write(desc_response.text)
st.write("## Objekterkennung:")
st.write(result_text)
st.image(annotated_image, caption="Erkannte Objekte", use_column_width=True)
except Exception as e:
st.error(f"Fehler: {str(e)}") |