Q&A
Keras初心者です。
CNNを理解するためにKerasでモデルを作り、cifar10のデータを元にモデルの認識精度を出力しようとしています。
以下のプログラムに対するエラーの原因がわからずに困っております。
もしご存知の方いらしましたら、ご教授またはご指摘頂けると幸いです。
以下プログラム
from keras.datasets import cifar10 from keras.preprocessing.image import ImageDataGenerator from keras.models import Sequential from keras.models import load_model from keras.layers.core import Dense, Dropout, Activation, Flatten from keras.layers.convolutional import Convolution3D, MaxPooling2D import keras.optimizers from keras.utils import np_utils #highparameter batch_size = 32 nb_classes = 10 nb_epoch = 80 data_augmentation = False # the data, shuffled and split between train and test sets (X_train, y_train), (X_test, y_test) = cifar10.load_data() print('X_train shape:', X_train.shape) print(X_train.shape[0], 'train samples') print(X_test.shape[0], 'test samples') # convert class vectors to binary class matrices Y_train = np_utils.to_categorical(y_train, nb_classes) Y_test = np_utils.to_categorical(y_test, nb_classes) model = Sequential() #input: number of frames/depth: 3 , number of channels: 1 , width: 128, height: 128 (3, 1, 128, 128) # 1st layer group model.add(Convolution3D(nb_filter=64,kernel_dim1=3, kernel_dim2=3,kernel_dim3=3, activation='relu', input_shape = X_train.shape[1:])) model.add(Convolution3D(nb_filter=64,kernel_dim1=3, kernel_dim2=3,kernel_dim3=3, activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) # 2st layer group model.add(Convolution3D(nb_filter=128,kernel_dim1=3, kernel_dim2=3,kernel_dim3=3, activation='relu')) model.add(Convolution3D(nb_filter=64,kernel_dim1=3, kernel_dim2=3,kernel_dim3=3, activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) # 3st layer group model.add(Convolution3D(nb_filter=256,kernel_dim1=3, kernel_dim2=3,kernel_dim3=3, activation='relu')) model.add(Convolution3D(nb_filter=256,kernel_dim1=3, kernel_dim2=3,kernel_dim3=3, activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Flatten()) model.add(Dense(1024),activation('relu')) model.add(Dense(512),activation('relu')) model.add(Dense(num_classes)) model.summary() model.compile(loss='categorical_crossentropy', optimizer=RMSprop(), metrics=['accuracy']) history = model.fit(x_train, y_train, batch_size=batch_size, epochs=nb_epochs, verbose=1, validation_data=(x_test, y_test)) score = model.evaluate(x_test, y_test, verbose=0) print('Test loss:', score[0]) print('Test accuracy:', score[1])
以下エラー
ValueError Traceback (most recent call last) <ipython-input-6-787c050ba750> in <module>() 33 kernel_dim2=3,kernel_dim3=3, 34 activation='relu', ---> 35 input_shape = X_train.shape[1:])) 36 model.add(Convolution3D(nb_filter=64,kernel_dim1=3, 37 kernel_dim2=3,kernel_dim3=3, /usr/local/lib/python2.7/dist-packages/keras/models.pyc in add(self, layer) 420 # and create the node connecting the current layer 421 # to the input layer we just created. --> 422 layer(x) 423 424 if len(layer.inbound_nodes) != 1: /usr/local/lib/python2.7/dist-packages/keras/engine/topology.pyc in __call__(self, inputs, **kwargs) 509 # Raise exceptions in case the input is not compatible 510 # with the input_spec specified in the layer constructor. --> 511 self.assert_input_compatibility(inputs) 512 513 # Collect input shapes to build layer. /usr/local/lib/python2.7/dist-packages/keras/engine/topology.pyc in assert_input_compatibility(self, inputs) 411 self.name + ': expected ndim=' + 412 str(spec.ndim) + ', found ndim=' + --> 413 str(K.ndim(x))) 414 if spec.max_ndim is not None: 415 ndim = K.ndim(x) ValueError: Input 0 is incompatible with layer conv3d_6: expected ndim=5, found ndim=4
回答1件
0
ベストアンサー
いろいろ直しました。まだ調整前だと思いますので、パラメータはそのままでは動かない部分以外はそのままです。
わからない部分がありましたら、適宜回答します
Python
1from keras.datasets import cifar10 2from keras.preprocessing.image import ImageDataGenerator 3from keras.models import Sequential 4from keras.models import load_model 5from keras.layers.core import Dense, Dropout, Activation, Flatten 6from keras.layers.convolutional import Convolution2D, MaxPooling2D 7import keras.optimizers 8from keras.utils import np_utils 9 10#highparameter 11batch_size = 32 12nb_classes = 10 13nb_epochs = 80 14data_augmentation = False 15 16 17# the data, shuffled and split between train and test sets 18(X_train, y_train), (X_test, y_test) = cifar10.load_data() 19print('X_train shape:', X_train.shape) 20print(X_train.shape[0], 'train samples') 21print(X_test.shape[0], 'test samples') 22 23# convert class vectors to binary class matrices 24Y_train = np_utils.to_categorical(y_train, nb_classes) 25Y_test = np_utils.to_categorical(y_test, nb_classes) 26 27 28model = Sequential() 29#input: number of frames/depth: 3 , number of channels: 1 , width: 128, height: 128 (3, 1, 128, 128) 30# 1st layer group 31model.add(Convolution2D(64, (3, 3), 32 activation='relu', 33 input_shape = X_train.shape[1:])) 34model.add(Convolution2D(64, (3,3), 35 activation='relu')) 36model.add(MaxPooling2D(pool_size=(2, 2))) 37# 2st layer group 38model.add(Convolution2D(128, (3, 3), 39 activation='relu')) 40model.add(Convolution2D(64,3, 41 activation='relu')) 42model.add(MaxPooling2D(pool_size=(2, 2))) 43# 3st layer group 44model.add(Convolution2D(256, (3, 3), 45 activation='relu')) 46model.add(Convolution2D(256, (3,3), 47 activation='relu')) 48model.add(MaxPooling2D(pool_size=(1, 1))) 49 50model.add(Flatten()) 51model.add(Dense(1024, activation='relu')) 52model.add(Dense(512 ,activation='relu')) 53model.add(Dense(nb_classes)) 54 55model.summary() 56 57model.compile(loss='categorical_crossentropy', 58 optimizer='RMSprop', 59 metrics=['accuracy']) 60 61history = model.fit(X_train, Y_train, 62 batch_size=batch_size, 63 epochs=nb_epochs, 64 verbose=1, 65 validation_data=(X_test, Y_test)) 66 67score = model.evaluate(X_test, Y_test, verbose=0) 68print('Test loss:', score[0]) 69print('Test accuracy:', score[1])
投稿2017/05/12 23:15
総合スコア1150
あなたの回答
tips
プレビュー
バッドをするには、ログインかつ
こちらの条件を満たす必要があります。