Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -4,19 +4,19 @@ from PIL import Image
|
|
4 |
import tensorflow as tf
|
5 |
from utils import preprocess_image
|
6 |
|
7 |
-
|
8 |
-
import streamlit as st
|
9 |
-
import tensorflow as tf
|
10 |
-
from PIL import Image
|
11 |
-
from utils import preprocess_image
|
12 |
|
13 |
# Initialize labels and model
|
14 |
labels = ['cardboard', 'glass', 'metal', 'paper', 'plastic', 'trash']
|
15 |
model = tf.keras.models.load_model('classify_model.h5')
|
16 |
|
17 |
-
#
|
18 |
-
|
19 |
-
|
|
|
|
|
|
|
|
|
20 |
|
21 |
# Customized Streamlit styles
|
22 |
st.markdown(
|
@@ -76,48 +76,34 @@ st.markdown(
|
|
76 |
unsafe_allow_html=True,
|
77 |
)
|
78 |
|
79 |
-
|
80 |
# Logo
|
81 |
st.image("https://ecoclimsolutions.files.wordpress.com/2024/01/rmcai-removebg.png?resize=48%2C48")
|
82 |
|
83 |
# Page title
|
84 |
st.title("EcoIdentify by EcoClim Solutions")
|
85 |
|
86 |
-
|
|
|
|
|
|
|
|
|
87 |
|
88 |
-
|
89 |
-
|
90 |
|
91 |
-
|
92 |
-
# Train the model with a new image and label
|
93 |
-
st.header("Train the model with a new image and label")
|
94 |
|
95 |
-
|
96 |
file = st.file_uploader('Select', type=['jpg', 'png', 'jpeg'])
|
97 |
if file:
|
98 |
-
|
99 |
-
image = preprocess_image(file)
|
100 |
-
st.image(image, width=256, caption='Uploaded Image')
|
101 |
-
|
102 |
-
# Label input
|
103 |
-
user_label = st.selectbox("Select the correct label", labels)
|
104 |
-
|
105 |
-
# Train button
|
106 |
-
if st.button('Train Model'):
|
107 |
-
accumulated_images.append(image[np.newaxis, ...])
|
108 |
-
label_index = labels.index(user_label)
|
109 |
-
label_one_hot = tf.one_hot(label_index, len(labels))
|
110 |
-
accumulated_labels.append(label_one_hot)
|
111 |
-
|
112 |
-
if len(accumulated_images) >= 5: # Example threshold
|
113 |
-
X_train = np.vstack(accumulated_images)
|
114 |
-
y_train = np.vstack(accumulated_labels)
|
115 |
-
model.fit(X_train, y_train, epochs=2, batch_size=1)
|
116 |
-
st.success(f'Model has been trained with the accumulated images and labels.')
|
117 |
-
# Clear accumulated data
|
118 |
-
accumulated_images.clear()
|
119 |
-
accumulated_labels.clear()
|
120 |
|
121 |
-
|
122 |
-
|
123 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
import tensorflow as tf
|
5 |
from utils import preprocess_image
|
6 |
|
7 |
+
|
|
|
|
|
|
|
|
|
8 |
|
9 |
# Initialize labels and model
|
10 |
labels = ['cardboard', 'glass', 'metal', 'paper', 'plastic', 'trash']
|
11 |
model = tf.keras.models.load_model('classify_model.h5')
|
12 |
|
13 |
+
# Customized Streamlit layout
|
14 |
+
st.set_page_config(
|
15 |
+
page_title="EcoIdentify by EcoClim Solutions",
|
16 |
+
page_icon="https://ecoclimsolutions.files.wordpress.com/2024/01/rmcai-removebg.png?resize=48%2C48",
|
17 |
+
layout="wide",
|
18 |
+
initial_sidebar_state="expanded",
|
19 |
+
)
|
20 |
|
21 |
# Customized Streamlit styles
|
22 |
st.markdown(
|
|
|
76 |
unsafe_allow_html=True,
|
77 |
)
|
78 |
|
|
|
79 |
# Logo
|
80 |
st.image("https://ecoclimsolutions.files.wordpress.com/2024/01/rmcai-removebg.png?resize=48%2C48")
|
81 |
|
82 |
# Page title
|
83 |
st.title("EcoIdentify by EcoClim Solutions")
|
84 |
|
85 |
+
# Subheader
|
86 |
+
st.header("Upload a waste image to find its category")
|
87 |
+
|
88 |
+
# Note
|
89 |
+
st.markdown("* Please note that our dataset is trained primarily with images that contain a white background. Therefore, images with white background would produce maximum accuracy *")
|
90 |
|
91 |
+
# Image upload section
|
92 |
+
opt = st.selectbox("How do you want to upload the image for classification?", ("Please Select", "Upload image from device"))
|
93 |
|
94 |
+
image = None
|
|
|
|
|
95 |
|
96 |
+
if opt == 'Upload image from device':
|
97 |
file = st.file_uploader('Select', type=['jpg', 'png', 'jpeg'])
|
98 |
if file:
|
99 |
+
image = preprocess_image(file)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
100 |
|
101 |
+
try:
|
102 |
+
if image is not None:
|
103 |
+
st.image(image, width=256, caption='Uploaded Image')
|
104 |
+
if st.button('Predict'):
|
105 |
+
prediction = model.predict(image[np.newaxis, ...])
|
106 |
+
st.success(f'Prediction: {labels[np.argmax(prediction[0], axis=-1)]}')
|
107 |
+
except Exception as e:
|
108 |
+
st.error(f"An error occurred: {e}. Please contact us EcoClim Solutions at EcoClimSolutions.wordpress.com.")
|
109 |
+
|