如何將新數字手寫體訓練成存在 keras model？

Question

我有一個現有的 model 訓練來識別手寫數字。 然后我有一個新的樣本數字來訓練更多的 model。 有沒有辦法做到這一點？

  import os
  import cv2 as cv
  import numpy as np
  import matplotlib.pyplot as plt
  import tensorflow as tf

  ### train model ###
  mnist = tf.keras.datasets.mnist
  (x_train, y_train), (x_test, y_test) = mnist.load_data()
  x_train = x_train/255
  x_test = x_test/255

  model = tf.keras.models.Sequential()
  model.add(tf.keras.layers.Flatten(input_shape=(28,28)))
  model.add(tf.keras.layers.Dense(units=128,activation=tf.nn.relu))
  model.add(tf.keras.layers.Dense(units=10,activation=tf.nn.softmax))

  model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"])

  model.fit(x_train, y_train, epochs=5)
  model.save('traineddata.model')

我的新樣本是這樣的 1 號：

Answer 1

您可以加載圖像，轉換為灰度，調整為(28,28)
並通過一個示例轉換為訓練數組，並將其與fit()一起使用

x_example = cv2.imread('image.png')
x_example = cv2.cvtColor(x_example, cv2.COLOR_BGR2GRAY)
x_example = cv2.resize(x_example, (28, 28))

y_example = 1

x_data = np.array( [ x_example ] )  # it has to be array with shape (1, 28, 28) instead of (28, 28)
y_data = np.array( [ y_example ] )  # it has to be array with shape (1, 1) instead of (1,)

model.fit(x_data, y_data, epochs=5)

但它不能很好地預測epochs=5 。
對於epochs=10 ，它為該圖像提供了正確的預測，但我沒有檢查它是否仍然為其他圖像提供正確的預測。

也許將圖像添加到x_train ， y_train並再次重新訓練會更好。

x_data = np.append(x_train, [x_example], axis=0)
y_data = np.append(y_train, y_example)

model.fit(x_data, y_data, epochs=5)

就像在現實生活中一樣——當你學習新元素時，你最好記住它而不是舊元素。 當您用新元素再次學習所有元素時，您會刷新所有信息並記住所有這些信息。

---

我用於測試的最小工作代碼。

import warnings

warnings.filterwarnings('ignore')  # hide/supress warnings

import os
import cv2
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf

### train model ###

def build():
    print('-'*50)
    print('# Building model ')
    print('-'*50)
    
    model = tf.keras.models.Sequential()
    model.add(tf.keras.layers.Flatten(input_shape=(28, 28)))
    model.add(tf.keras.layers.Dense(units=128, activation=tf.nn.relu))
    model.add(tf.keras.layers.Dense(units=10, activation=tf.nn.softmax))
    
    model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"])

    return model
    
def train(model, x_train, y_train, epochs=5):
    print('-'*50)
    print('# Training model')
    print('-'*50)
    
    model.fit(x_train, y_train, epochs=epochs)

def save(model):
    print('-'*50)
    print('# Saving model')
    print('-'*50)

    model.save('traineddata.model')

def load():
    print('-'*50)
    print('# Loading model')
    print('-'*50)
    
    return tf.keras.models.load_model('traineddata.model')

def test_one(model, x_example, y_example):
    print('-'*50)
    print('# Testing one element')
    print('-'*50)
    
    # create array with one or more images
    x_data = np.array( [ x_example ] )
    y_data = np.array( [ y_example ] )

    print('x_data shape:', x_data.shape)
    print('y_data shape:', y_data.shape)
    print(' expected:', y_data)

    # get list with one or more predictions
    y_results = model.predict(x_data)

    print('predicted:', y_results.argmax(axis=1))

def retrain_one(model, x_example, y_example, epochs=5):
    print('-'*50)
    print('# Retraining one element')
    print('-'*50)

    # create array with one or more images
    x_data = np.array( [ x_example ] )
    y_data = np.array( [ y_example ] )

    print('x_data shape:', x_data.shape)
    print('y_data shape:', y_data.shape)
    print('y_data:', y_data)

    model.fit(x_data, y_data, epochs=epochs)

def retrain_all(model, x_train, y_train, x_example, y_example, epochs=5):
    print('-'*50)
    print('# Retraining all elements')
    print('-'*50)

    # create array with all images
    x_data = np.append(x_train, [x_example], axis=0)
    y_data = np.append(y_train, y_example)

    print('x_data shape:', x_data.shape)
    print('y_data shape:', y_data.shape)
    print('y_data:', y_data)

    model.fit(x_data, y_data, epochs=epochs)

# --- main ---

# - load train/test images -

print('>>> Loading train/test data ...')
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

x_train = x_train/255
x_test = x_test/255

# - train + save or load -

if not os.path.exists('traineddata.model'):
    print('>>> Building model ...')
    model = build()

    print('>>> Training model ...')
    train(model, x_train, y_train)

    print('>>> Saving model ...')
    save(model)
else:
    print('>>> Loading model ...')
    model = load()

#print(' - test on single example - ')
#index = 0
#test_one(model, x_train[index], y_train[index])

print(' - image - ')

x_example = cv2.imread('image.png')
x_example = cv2.cvtColor(x_example, cv2.COLOR_BGR2GRAY)
x_example = cv2.resize(x_example, (28, 28))

y_example = 1

print('>>> Predicting without training')

test_one(model, x_example, y_example)

print('>>> Predicting with training one element (epochs=10)')

retrain_one(model, x_example, y_example, epochs=10)  # epochs=5 epochs=7
test_one(model, x_example, y_example)

print('>>> Predicting with retraining all elements')

retrain_all(model, x_train, y_train, x_example, y_example)
test_one(model, x_example, y_example)

#print('>>> Saving new model')
#model.save('traineddata.model')