IDubrovsky
commited on
Commit
•
4746e24
1
Parent(s):
6e3296d
Add application file
Browse files- app.py +85 -0
- requirements.txt +4 -0
- xgb.ckpt +3 -0
app.py
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pickle
|
3 |
+
import pandas as pd
|
4 |
+
from colormap import rgb2hex
|
5 |
+
from PIL import Image
|
6 |
+
|
7 |
+
def predict(m_cloth, v_w, v_m, v_k, v_b, m_al, m_cu, m_fe, m_tan, time, pH):
|
8 |
+
xgb = pickle.load(open('xgb.ckpt', 'rb'))
|
9 |
+
v_sum = v_w + v_m + v_k + v_b
|
10 |
+
X = pd.DataFrame({'m_cloth': m_cloth, 'v_w': v_w / v_sum, 'v_m': v_m / v_sum, 'v_k': v_k / v_sum, 'v_b': v_b / v_sum, 'm_al': m_al, 'm_cu': m_cu, 'm_fe': m_fe, 'm_tan': m_tan, 'time': time, 'pH': pH}, index = [0])
|
11 |
+
y = xgb.predict(X)
|
12 |
+
r, g, b = y[0]
|
13 |
+
img = Image.new('RGB',(200,200),(int(r),int(g),int(b)))
|
14 |
+
hex_color = rgb2hex(int(r), int(g), int(b))
|
15 |
+
return hex_color, int(r), int(g), int(b), hex_color, img
|
16 |
+
|
17 |
+
with gr.Blocks() as demo:
|
18 |
+
with gr.Column():
|
19 |
+
gr.Markdown(
|
20 |
+
"""
|
21 |
+
# Predicting the conditions of dyeing of cotton fabric with natural dyes to obtain a given color
|
22 |
+
""")
|
23 |
+
with gr.Row():
|
24 |
+
with gr.Column(scale=4):
|
25 |
+
gr.Markdown(
|
26 |
+
"""
|
27 |
+
This service was created as part of the project **"Predicting the conditions of dyeing of cotton fabric with natural dyes to obtain a given color"** under the **Sirius.Leto** program. The purpose of this service is to determine in advance the result of dyeing the fabric with natural dyes, without conducting experiments. This is achieved by using the **Extreme Gradient Boosting Regressor** model, which allows to predict the color in **RGB** format based on the initial dyeing parameters.
|
28 |
+
|
29 |
+
To build this model, **240** fabric dyeing experiments were conducted at **ITMO University**. These experiments formed the dataset on which the models were built with **R<sup>2</sup> = 0.82** on the test set. Additionally, **8** experiments close but different from the experiments in the original dataset were performed, on which the algorithm was validated. The accuracy on the validation set was **R<sup>2</sup> = 0.88**.
|
30 |
+
|
31 |
+
Dataset, code and detailed slides: **TBA**.
|
32 |
+
|
33 |
+
Limitations of the algorithm's performance:
|
34 |
+
|
35 |
+
|
36 |
+
* Limited palette of colors for which high prediction accuracy is preserved (see *Figure 1*)
|
37 |
+
* Limited investigation of the influence of additional factors such as additives, pH, temperature (many of these parameters are less likely to determine the final color)
|
38 |
+
* As in many machine learning models, borderline values with less data are predicted worse (e.g. in the case of very dilute solutions)
|
39 |
+
|
40 |
+
Authors:
|
41 |
+
Ekaterina Veselyaeva \*,
|
42 |
+
Alisa Pigulevskaya \*,
|
43 |
+
Sofia Ryakhovskaya \*.
|
44 |
+
|
45 |
+
Supervisor:
|
46 |
+
Ivan Dubrovsky \*\*.
|
47 |
+
|
48 |
+
\* Lyceum № 226, St. Petersburg
|
49 |
+
|
50 |
+
\*\* Artificial Intelligence in Chemistry Center, ITMO University, St. Petersburg
|
51 |
+
""")
|
52 |
+
with gr.Column(scale=3):
|
53 |
+
gr.Image("https://drive.usercontent.google.com/u/1/uc?id=1Bokju7A-owxh3cc3C623YqmAqKSSrdtO&export=download", height = 500, width = 500)
|
54 |
+
gr.Markdown("""
|
55 |
+
*Figure 1. A palette of colors that the algorithm is able to predict with high accuracy (mostly the colors of the original dyes and their combinations).*
|
56 |
+
""")
|
57 |
+
with gr.Row():
|
58 |
+
with gr.Column(scale=4):
|
59 |
+
inp= [gr.Number(label = 'Weight of fabric, g', minimum = 0, maximum = 1000, value = 0.1),
|
60 |
+
gr.Number(label = 'Water volume, ml', minimum = 0, maximum = 1000, value = 5),
|
61 |
+
gr.Number(label = 'Volume of madder dye solution, ml', minimum = 0, maximum = 1000, value = 5),
|
62 |
+
gr.Number(label = 'Volume of turmeric dye solution, ml', minimum = 0, maximum = 1000, value = 5),
|
63 |
+
gr.Number(label = 'Volume of elderberry dye solution, ml', minimum = 0, maximum = 1000),
|
64 |
+
gr.Number(label = 'Weight of added aluminum salt, g', minimum = 0, maximum = 1000),
|
65 |
+
gr.Number(label = 'Weight of added copper salt, g', minimum = 0, maximum = 1000),
|
66 |
+
gr.Number(label = 'Weight of added iron salt, g', minimum = 0, maximum = 1000),
|
67 |
+
gr.Number(label = 'Weight of added tannin, g', minimum = 0, maximum = 1000),
|
68 |
+
gr.Number(label = 'Dyeing time, min', minimum = 0, maximum = 5000, value = 60),
|
69 |
+
gr.Number(label = 'pH', minimum = 0, maximum = 14, value = 6)]
|
70 |
+
with gr.Column(scale=3):
|
71 |
+
out = [gr.ColorPicker(label="Color"),
|
72 |
+
gr.Number(label = 'R', minimum = 0, maximum = 255),
|
73 |
+
gr.Number(label = 'G', minimum = 0, maximum = 255),
|
74 |
+
gr.Number(label = 'B', minimum = 0, maximum = 255),
|
75 |
+
gr.Textbox(label="Hexadecimal color"),
|
76 |
+
gr.Image(label="Color image", height = 500, width = 500)]
|
77 |
+
button = gr.Button()
|
78 |
+
button.click(fn=predict, inputs=inp, outputs=out)
|
79 |
+
demo.launch()
|
80 |
+
|
81 |
+
def greet(name):
|
82 |
+
return "Hello " + name + "!!"
|
83 |
+
|
84 |
+
iface = gr.Interface(fn=greet, inputs="text", outputs="text")
|
85 |
+
iface.launch()
|
requirements.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
colormap
|
2 |
+
pandas
|
3 |
+
xgboost
|
4 |
+
PIL
|
xgb.ckpt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8171793ff02c45d048efd553b92879dd2946bad67cc914f2c62a336658868c95
|
3 |
+
size 342046
|