import numpy as np
import matplotlib.pyplot as plt
from tensorflow.keras.datasets import mnist
from tensorflow import keras
import keras.backend as K
from tensorflow.keras.layers import Dense, Flatten, Reshape, Input, Lambda, BatchNormalization, Dropout
 
(x_train, y_train), (x_test, y_test) = mnist.load_data()
 
x_train = x_train / 255
x_test = x_test / 255

y_train = keras.utils.to_categorical(y_train, 10)

input_img = Input((28, 28))
x = Flatten()(input_img)
x = Dense(256, activation='relu')(x)
x = Dense(128, activation='relu')(x)
x = Dense(64, activation='relu')(x)
Classif = Dense(10, activation='softmax')(x)

model = keras.Model(input_img, Classif)

model.compile(optimizer='adam', loss='categorical_crossentropy')

model.fit(x_train, y_train, epochs=5, batch_size=30, shuffle=True)




import gradio as gr
import numpy as np

from huggingface_hub import from_pretrained_keras

model = from_pretrained_keras("ISYS/MyNewModel")

def greet(img):
    img = np.expand_dims(img, axis=0)
    return np.argmax(model.predict(img)[0])

iface = gr.Interface(fn=greet, inputs="sketchpad", outputs="text")
iface.launch()