pile(loss='binary_crossentropy', optimizer='rmsprop', metrics=)įile "C:/Users/w024029h/PycharmProjects/keras pretrained/2training image.py", line 29, inįile "C:\Users\w024029h\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\utils\np utils.py", line 34, in tocategorical Model.add(Dense(12, activation='softmax', name='prediction'))
ValueError: invalid literal for int() with base 10: I already change the label into intĪnd the code is: from keras.models import Sequential Terminal output: Using TensorFlow backend.įile "C:/Users/w024029h/PycharmProjects/keras_pretrained/2_training_image.py", line 29, in įile "C:\Users\w024029h\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\utils\np_utils.py", line 25, in to_categorical Plt.title('Training and validation loss') Plt.plot(epochs, val_loss, 'r', label='Validation loss') Plt.plot(epochs, loss, 'b', label='Training loss') Plt.title('Training and validation accuracy') Plt.plot(epochs, val_acc, 'r', label='Validation acc') Plt.plot(epochs, acc, 'b', label='Training acc') pile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=) # pile(loss='sparse_categorical_crossentropy', optimizer=optimizers.RMSprop(lr=2e-4), metrics=) Model.add(Dense(1, activation='relu', name='prediction'))
Model.add(Flatten(input_shape=x_train.shape)) How I can run the pile? Please help from keras.models import Sequentialįrom keras.layers import Dense, Dropout, Flatten
X_train.dat contains my images and y_train.dat contains my label however I when I try to train it with model.fit it keeps give me an error.