Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import tensorflow as tf
|
3 |
+
from tensorflow.keras.preprocessing.image import load_img, img_to_array
|
4 |
+
import numpy as np
|
5 |
+
|
6 |
+
def preprocesa_img(img_path):
|
7 |
+
img = load_img(img_path, color_mode="grayscale", target_size=(28, 28))
|
8 |
+
img_array = img_to_array(img)
|
9 |
+
img_array = 255 - img_array
|
10 |
+
img_array = img_array.reshape(1, 784) / 255.0
|
11 |
+
return img_array
|
12 |
+
|
13 |
+
model = tf.keras.models.load_model("identificadordigitos.h5")
|
14 |
+
st.title("Clasificaci贸n de im谩genes de d铆gitos")
|
15 |
+
|
16 |
+
uploaded_file = st.file_uploader("Subir una imagen de un d铆gito", type=["jpg", "png"])
|
17 |
+
|
18 |
+
if uploaded_file is not None:
|
19 |
+
image_array = preprocesa_img(uploaded_file)
|
20 |
+
|
21 |
+
st.write("Imagen preprocesada:", image_array)
|
22 |
+
|
23 |
+
preliminar = model.predict(image_array)
|
24 |
+
|
25 |
+
st.write("Predicci贸n del modelo (vector de probabilidades):", preliminar)
|
26 |
+
prediccion = np.argmax(preliminar, axis=1)[0]
|
27 |
+
st.success(f"Predicci贸n: {prediccion}")
|