MNIST Multi Digit прогноз ⇐ Python

[Anonymous]

Я попытался тренировать модель на наборе данных MNIST. Он работает нормально для однозначного прогнозирования, и я получил точность 96,92% и на тестовых данных, но у меня есть все, но он не работает для многограда. Прогнозирование 3356.Enter изображение описание здесь < /p>
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
import tensorflow
from tensorflow import keras
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense
from PIL import Image
def apply_threshold(img, threshold=125):
img = np.where(img > threshold, 1, 0).astype(np.uint8)
return img

def image_background(img):
if img.mean() > 127:
img = 255 - img
return img

def padding_and_resize(img):
h, w = img.shape
if h < w:
new_img = np.zeros((int((w - h) / 2), w))
new_img = np.append(new_img, img, axis=0)
zeros = np.zeros(((w - h) - int((w - h) / 2), w))
new_img = np.append(new_img, zeros, axis=0)
img = new_img
elif h > w:
new_img = np.zeros((h, int((h - w) / 2)))
new_img = np.append(new_img, img, axis=1)
zeros = np.zeros((h, (h - w) - int((h - w) / 2)))
new_img = np.append(new_img, zeros, axis=1)
img = new_img

img = Image.fromarray(img.astype(np.uint8))
img = img.resize((28, 28))
img = np.array(img)
return img

def reshaping_and_standardizing(img):
return img.reshape(-1) / 255.0

def split_digits(img):
img_mean = img.mean()
new_img = []

for i in img:
if np.sum(i) != 0:
new_img.append(i)

new_img = np.array(new_img)
output_digits = []

moving_on_digit = False
start = 0
end = 0
for i in range(len(new_img[0])):
if np.sum(new_img[:, i]) != 0 and (not moving_on_digit):
moving_on_digit = True
start = i
elif np.sum(new_img[:, i]) == 0 and moving_on_digit:
moving_on_digit = False
end = i
output_digits.append(new_img[:, start:end + 1])

if moving_on_digit:
output_digits.append(new_img[:, start:len(new_img[0])])

return output_digits

def img_processor(img, threshold=None):
if threshold is None:
threshold = img.mean()
img = image_background(img)
img = apply_threshold(img, threshold=threshold)
img = padding_and_resize(img)
img = reshaping_and_standardizing(img)
return img

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()

x_train = pd.DataFrame(img_processor(img) for img in x_train)
x_test = pd.DataFrame(img_processor(img) for img in x_test)

y_train = pd.DataFrame(np.array([[0] * i + [1] + [0] * (9 - i)]).reshape(10) for i in y_train)

model = Sequential()
model.add(Dense(784, activation='relu', input_dim=784))
model.add(Dense(128, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(10, activation='softmax'))

model.summary()

model.compile(loss='categorical_crossentropy', optimizer='Adam')
model.fit(x_train, y_train, epochs=11)

y_predict = model.predict(x_test)

y_predict = np.argmax(y_predict, axis=1)

str(round(accuracy_score(y_test, y_predict) * 100, 2)) + "%"

# testing

from PIL import Image

# single digit testing
img = Image.open('/content/drive/MyDrive/datasets/image_set/Screenshot 2025-07-30 052716.png')
img = img.convert('L')
img = img.resize((28, 28))
img_array = np.array(img)
img_array = img_array.reshape(1, 784)
if img_array.mean() > 127:
img_array = 255 - img_array
img_array = img_array / 255.0
y_predict = model.predict(img_array)
np.argmax(y_predict, axis=1)

img = Image.open('/content/Screenshot 2025-07-31 175136.png').convert('L')
img = np.array(img)
img = image_background(img)
img = apply_threshold(img, threshold=img.mean())
images = split_digits(img)
digit = 0
for img in images:
img = padding_and_resize(img)
plt.imshow(img, cmap='gray')
plt.axis('off')
plt.show()
img = img.reshape(1, 784) / 255.0
prediction = model.predict(img).argmax(axis=1)[0]
digit *= 10
digit += prediction
print(digit)enter image description here


Подробнее здесь: https://stackoverflow.com/questions/797 ... prediction