Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from transformers import pipeline
|
3 |
+
import requests
|
4 |
+
from io import BytesIO
|
5 |
+
from PIL import Image
|
6 |
+
|
7 |
+
# Define models and their validation accuracies
|
8 |
+
model_options = {
|
9 |
+
"Model Name": {
|
10 |
+
"path": "model_name.h5",
|
11 |
+
"accuracy": 50
|
12 |
+
},
|
13 |
+
"Old Model": {
|
14 |
+
"path": "oldModel.h5",
|
15 |
+
"accuracy": 76
|
16 |
+
}
|
17 |
+
}
|
18 |
+
|
19 |
+
# Load the model from Hugging Face repo
|
20 |
+
def load_model(model_path):
|
21 |
+
# Here you would use the Hugging Face `transformers` library to load your model.
|
22 |
+
# However, since these are `.h5` models (likely Keras models), use the appropriate loader.
|
23 |
+
# This example assumes you have a custom loader function for Keras models.
|
24 |
+
from tensorflow.keras.models import load_model
|
25 |
+
return load_model(model_path)
|
26 |
+
|
27 |
+
def main():
|
28 |
+
st.title("Pneumonia Detection App")
|
29 |
+
|
30 |
+
model_name = st.selectbox("Select a model", list(model_options.keys()))
|
31 |
+
model_path = model_options[model_name]["path"]
|
32 |
+
model_accuracy = model_options[model_name]["accuracy"]
|
33 |
+
|
34 |
+
# Load the selected model
|
35 |
+
model = load_model(model_path)
|
36 |
+
|
37 |
+
st.write(f"Model: {model_name}")
|
38 |
+
st.write(f"Validation Accuracy: {model_accuracy}%")
|
39 |
+
|
40 |
+
uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
|
41 |
+
|
42 |
+
if uploaded_file is not None:
|
43 |
+
image = Image.open(uploaded_file)
|
44 |
+
st.image(image, caption="Uploaded Image", use_column_width=True)
|
45 |
+
|
46 |
+
# Perform prediction using the model
|
47 |
+
# This part depends on how your model expects input.
|
48 |
+
# Here, you would preprocess the image and perform prediction.
|
49 |
+
# For example:
|
50 |
+
# img_array = preprocess_image(image)
|
51 |
+
# prediction = model.predict(img_array)
|
52 |
+
# st.write("Prediction:", prediction)
|
53 |
+
|
54 |
+
# Example placeholder for prediction output
|
55 |
+
st.write("Prediction: [Placeholder for actual prediction]")
|
56 |
+
|
57 |
+
if __name__ == "__main__":
|
58 |
+
main()
|