Witam,
pisze klasyfikator obrazow z biblioteki CIFAR-10, chce wykorzystac tylko 2 z 10 klasow z tej biblioteki. Dziele dane na dwie klasy i podczas uczenia wyrzuca mi błąd: ValueError: Data cardinality is ambiguous; x sizes: 32, 32 , 32 ... y sizes: 10, 10, 10 ... Make sure all arrays contain the same number of samples. Gdy ucze na danych nie podzielony na 2 klasy model uczy sie prawidłowo.
from keras.datasets import cifar10
from matplotlib import pyplot as plt
from keras.utils import to_categorical
from sklearn.model_selection import train_test_split
data = cifar10.load_data()
X=data[0][0].astype('float32') / 255.0
y=to_categorical(data[0][1])
X_new = []
y_new = []
# Biore tylko dane z klasy 1 i 2
for x_change,y_change in zip (X, y):
if y_change[0] == 1 or y_change[1] == 1:
X_new.append(x_change)
y_new.append(y_change)
X_train, X_test, y_train, y_test = train_test_split(X_new, y_new, test_size=0.3)
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Dense
from keras.layers import Flatten
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
history = model.fit(X_train, y_train, epochs=30, batch_size=64, validation_data=(X_test, y_test))