Python - Keras, got array with (32, 1)

Question

seed_value= 777

import os
os.environ['PYTHONHASHSEED']=str(seed_value)

import random
random.seed(seed_value)

import numpy as np
np.random.seed(seed_value)

import tensorflow as tf
tf.set_random_seed(seed_value)

from keras import backend as K
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
K.set_session(sess)


from tensorflow.python.keras.utils.np_utils import to_categorical
from sklearn.model_selection import train_test_split
import pandas as pd 

train = pd.read_csv("C:/Users/Mateusz/dane/train.csv")
test= pd.read_csv("C:/Users/Mateusz/dane/test.csv")
print("Train size:{}\nTest size:{}".format(train.shape, test.shape))

x_train = train.drop(['label'], axis=1).values.astype('float32')
y_train = train['label'].values.astype('int32')
x_test = test.values.astype('float32')
x_train = x_train.reshape(x_train.shape[0], 28, 28) / 255.0
x_test = x_test.reshape(x_test.shape[0], 28, 28) / 255.0

x_train, x_val, y_train, y_val = train_test_split(x_train, y_train, test_size = 0.01, random_state=77)

print(x_train.shape)
print(y_train.shape)
print(x_test.shape)
print(x_val.shape)
print(y_val.shape)




x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
x_val = x_val.reshape(x_val.shape[0], 28, 28, 1)



import keras
from keras.optimizers import Adadelta
from keras.layers import Dense, Dropout, Conv2D, MaxPooling2D, Flatten, BatchNormalization
from keras.models import Sequential

model = Sequential()
model.add(Conv2D(filters=16, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(BatchNormalization())
model.add(Conv2D(filters=16, kernel_size=(3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(filters=32, kernel_size=(3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(Conv2D(filters=32, kernel_size=(3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.25))
model.add(Dense(units=256, activation='relu'))
model.add(Dropout(0.25))
model.add(Dense(units=128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(units=10, activation='softmax'))
model.summary()


model.compile(optimizer='adadelta',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])



from keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(rescale=1./255.)
valid_datagen = ImageDataGenerator(rescale=1./255.)

train_generator = train_datagen.fit(x_train)

valid_generator = valid_datagen.fit(x_val)



from keras.callbacks import ModelCheckpoint

checkpoint = ModelCheckpoint("best_weights.hdf5",
                             monitor='val_acc',
                             save_best_only=True, 
                             mode='max')
model.fit_generator(train_datagen.flow(x_train, y_train, batch_size=32),
                    steps_per_epoch=100,
                    epochs=15,
                    callbacks=[checkpoint],
                    validation_data=valid_datagen.flow(x_val, y_val),
                    validation_steps=50)

Error:

Error when checking target: expected dense_23 to have 4 dimensions, but got array with shape (32, 1)

Comments

To jest Twój kod? Czy skopiowany?

Problem leży chyba w wymiarowości, z tego co się orientuję trzeba używać np. metody model.add(Flatten()) by zmniejszyć wymiarowość i dostosować ją do oczekiwanej wielkości:

https://stackoverflow.com/questions/43237124/role-of-flatten-in-keras

https://keras.io/getting-started/sequential-model-guide/

---

Dzięki, zapomniałem o Flatten(),