我创建了一个机器学习程序，该程序能够正确识别99.947％的手写十进制数字。我使用了MNIST数据集来训练模型，并且正在开发一个程序，该程序可以预测在图像中写入了哪些数字。该图像是使用PyGame创建的。
此代码在具有python 3.7.1的Linux系统上运行。
我的代码如下。我正在尝试创建一个教育游戏，而我的AI似乎无法正确处理数据：
import sys, os # For modifying files, making directories, etc.
import keras # Simplified TensorFlow library
import matplotlib.pyplot as plt # Image display from PyPlot
import numpy as np # NumPy for advanced math
import math # If needed
import random # For picking a random value within the MNIST data set
import pygame # For drawing canvas, etc
from pygame.locals import *
import time
from keras.models import Sequential # Enables sequential layers for AI learning
from keras.layers import Dense # Enables Dense layers
from keras.layers import Conv2D # Enables 2D Convoluted Neural Network layers
from keras.layers import MaxPooling2D # Enables Maximum Pooling layers
from keras.layers import Dropout # Enables Dropout layers
from keras.layers import Flatten # Enables Flatten layers
from keras.datasets import mnist # Imports MNIST for training artificial intelligence
from keras.callbacks import ModelCheckpoint # Imports ModelCheckpoint for saving progress
import cv2 # For loading images
model = Sequential() # Use sequential layers for AI training
# ML Configuration. Although this is included in a separate file, I included an option to train the AI within this file.
model.add(Conv2D(32, (3,3), activation='relu', input_shape = (28, 28, 1)))
model.add(Conv2D(64, (3,3), activation='relu'))
model.add(MaxPooling2D(pool_size = (2, 2)))
model.add(Flatten())
model.add(Dense(128, activation = 'relu'))
model.add(Dropout(rate = 0.3))
model.add(Dense(10, activation = 'softmax'))
load = True # Load previous best model fit?
save = True # Save best model fit?
if load:
print("Loading weights from previous model fit...\t", end="")
model.load_weights("./saves/main_MNIST.hdf5")
print("Done")
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(-1, 28, 28, 1)
x_test = x_train.reshape(-1, 28, 28, 1)
y_train = keras.utils.to_categorical(y_train, num_classes=10)
y_test = keras.utils.to_categorical(y_test, num_classes=10)
model.compile(loss = keras.losses.categorical_crossentropy, optimizer=keras.optimizers.Adadelta(), metrics=['accuracy'])
callbacks_list = []
if save:
filepath="./saves/main_MNIST.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='acc', verbose=1, save_best_only=True, mode='max')
callbacks_list = [checkpoint]
# Whether or not to retrain model within this file
if input("Retrain model? (Y/N)\t").lower() == "y":
history = model.fit(x_train, y_train, epochs=int(input("Input epochs number. Recommended value is 5.\t"), 10), batch_size=64, callbacks=callbacks_list)
# Initialize PyGame
pygame.init()
pygame.font.init()
myfont = pygame.font.SysFont('Open Sans', 30)
pygame.display.set_caption("NumSmart AI")
mouse = pygame.mouse
fpsclock = pygame.time.Clock()
# Width and height of window
width = 1024
height = 1024
window = pygame.display.set_mode((width, height))
canvas = window.copy()
# Color definitions
BLACK = pygame.Color(0,0,0)
WHITE = pygame.Color(255,255,255)
canvas.fill(BLACK)
def quitAndExit():
pygame.quit()
sys.exit()
def rgb2gray(rgb):
return np.dot(rgb[...,:3], [0.299, 0.587, 0.144])
while True:
title = myfont.render('NumSmart AI Game', False, (255, 255, 255))
add1 = random.randint(0, 10)
add2 = random.randint(0, 10)
dig2compl = False
prompt = myfont.render(("Add the following numbers: " + str(add1) + " + " + str(add2)), False, (255, 255, 255))
drawComplete = False
while not drawComplete:
left_pressed, middle_pressed, right_pressed = mouse.get_pressed()
for event in pygame.event.get():
if event.type == QUIT:
quitAndExit()
elif left_pressed:
pygame.draw.circle(canvas, WHITE, (pygame.mouse.get_pos()), 20)
elif middle_pressed:
canvas.fill(BLACK)
elif right_pressed:
pygame.draw.circle(canvas, BLACK, (pygame.mouse.get_pos()), 10)
elif event.type == pygame.KEYDOWN:
if event.key == pygame.K_q:
quitAndExit()
if event.key == pygame.K_c:
drawComplete = True
canvas.fill(BLACK)
if (add1 + add2 >= 10) and (not dig2compl):
drawComplete = False
dig2compl = True
# PROBLEM AREA BEGINS HERE
img = cv2.imread("./IMG/img.jpeg")
img = cv2.resize(img, dsize=(28, 28), interpolation=cv2.INTER_CUBIC)
plt.imshow(img)
plt.axis("off")
plt.show()
img = np.asarray(img)
img = rgb2gray(img)
img = img.reshape((-1, 28, 28, 1))
out = model.predict(img)
print(out)
print("AI Read: " + str(np.argmax(out)))
# PROBLEM AREA ENDS HERE
window.blit(canvas, (0, 0))
window.blit(prompt, (250, 0))
window.blit(title, (0, 0))
pygame.display.update()
pygame.image.save(canvas, "./IMG/img.jpeg")
如您所见，如果您绘制数字，则AI的猜测很可能是不准确的。
相对于上述文件，这是ML文件，需要将其放置在./saves/main_MNIST.hdf5中：
http://www.mediafire.com/file/1haza5nmxwxs24f/main_MNIST.hdf5/file
谢谢！