|
import joblib |
|
import numpy as np |
|
import cv2 |
|
import gradio as gr |
|
from sklearn import svm |
|
|
|
|
|
project_classifier = joblib.load('model.pkl') |
|
scaler = joblib.load('scaler.pkl') |
|
|
|
def inference(img): |
|
labels = ["0", "1", "2", "3", "4", "5", "6", "7", "8", "9"] |
|
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) |
|
H, W = 28, 28 |
|
img = cv2.resize(img, (H, W)) |
|
ret, img = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY) |
|
img = img.astype("float32").flatten().reshape(1, -1) |
|
img = scaler.transform(img) |
|
pred = project_classifier.predict_proba(img).flatten() |
|
dictionary = dict(zip(labels, map(float, pred))) |
|
return dictionary |
|
|
|
|
|
nbr_top_classes = 3 |
|
iface = gr.Interface(fn=inference, |
|
inputs=gr.Image(), |
|
outputs=gr.Label(num_top_classes=nbr_top_classes), |
|
theme="darkdefault") |
|
|
|
iface.launch(share=True) |
|
|
