前提・実現したいこと
Kerasでcifer10のディープラーニングを試したいです。
fit時にエラーが発生しました。
参考ページ
AidemyのCNN画像認識
https://aidemy.net/courses/5100/exercises/BJdU__iTHf
発生している問題・エラーメッセージ
fit = model.fit(X_train, y_train,
batch_size=128, epochs=10, verbose=1, )
ValueError: Error when checking target: expected activation_6 to have shape (None, 10) but got array with shape (50000, 1)
該当のソースコード
python
1#データロード、作成 2(X_train, y_train), (X_test, y_test) = cifar10.load_data() 3X_train = X_train.astype(np.float32) / 255.0 4X_test = X_test.astype(np.float32) / 255.0 5 6print(X_train.shape, y_train.shape, X_test.shape, y_test.shape) 7#(50000, 32, 32, 3) (50000, 1) (10000, 32, 32, 3) (10000, 1) 8 9#モデル定義 10model = Sequential() 11model.add(Conv2D(32, (3, 3), padding='same', 12 input_shape=X_train.shape[1:])) 13model.add(Activation('relu')) 14model.add(Conv2D(32, (3, 3))) 15model.add(Activation('relu')) 16model.add(MaxPool2D(pool_size=(2, 2))) 17model.add(Dropout(0.25)) 18 19model.add(Conv2D(64, (3, 3), padding='same')) 20model.add(Activation('relu')) 21model.add(Conv2D(64, (3, 3))) 22model.add(Activation('relu')) 23model.add(MaxPool2D(pool_size=(2, 2))) 24model.add(Dropout(0.25)) 25 26model.add(Flatten()) 27model.add(Dense(512)) 28model.add(Activation('relu')) 29model.add(Dropout(0.5)) 30model.add(Dense(10)) 31model.add(Activation('softmax')) 32 33#モデルコンパイル 34model.compile(optimizer='rmsprop', 35 loss='categorical_crossentropy', 36 metrics=['accuracy']) 37 38# 学習 39fit = model.fit(X_train, y_train, 40 batch_size=128, 41 epochs=10, 42 verbose=1, 43 ) 44
想定されている入力の行列と入ってくる行列の形式が違う?とか、入力と出力で形式がおかしいみたいなそんな感じのエラーなのかなとは思うのですが、どう直せば良いものかわかりません。。。
補足情報(FW/ツールのバージョンなど)
bleach (1.5.0)
certifi (2018.1.18)
chardet (3.0.4)
cycler (0.10.0)
decorator (4.2.1)
entrypoints (0.2.3)
enum34 (1.1.6)
graphviz (0.8)
h5py (2.7.0)
html5lib (0.9999999)
idna (2.6)
ipykernel (4.8.0)
ipython (6.2.1)
ipython-genutils (0.2.0)
ipywidgets (7.0.0)
jedi (0.11.1)
Jinja2 (2.10)
jsonschema (2.6.0)
jupyter-client (5.2.2)
jupyter-core (4.4.0)
jupyterlab (0.29.0)
jupyterlab-launcher (0.5.5)
Markdown (2.6.11)
MarkupSafe (1.0)
matplotlib (2.1.0)
mecab-python3 (0.7)
mistune (0.8.3)
nbconvert (5.3.1)
nbformat (4.4.0)
nltk (3.2.5)
notebook (5.2.0)
numpy (1.14.0)
opencv-python (3.3.0.10)
pandas (0.21.0)
pandocfilters (1.4.2)
parso (0.1.1)
pexpect (4.3.1)
pickleshare (0.7.4)
Pillow (5.0.0)
pip (9.0.1)
plotly (2.2.0)
prompt-toolkit (1.0.15)
protobuf (3.5.1)
ptyprocess (0.5.2)
pydotplus (2.0.0)
Pygments (2.2.0)
pyparsing (2.2.0)
python-dateutil (2.6.1)
pytz (2017.3)
pyzmq (16.0.4)
requests (2.18.4)
scikit-learn (0.19.0)
scipy (1.0.0)
setuptools (28.8.0)
simplegeneric (0.8.1)
six (1.11.0)
tensorflow (1.4.0)
tensorflow-tensorboard (0.4.0rc3)
terminado (0.8.1)
testpath (0.3.1)
tornado (4.5.3)
traitlets (4.3.2)
urllib3 (1.22)
wcwidth (0.1.7)
Werkzeug (0.14.1)
wheel (0.30.0)
widgetsnbextension (3.0.8)
keras '2.0.8-tf' #追記
追記:モデルサマリー
Layer (type) Output Shape Param
conv2d_1 (Conv2D) (None, 32, 32, 32) 896
activation_1 (Activation) (None, 32, 32, 32) 0
conv2d_2 (Conv2D) (None, 30, 30, 32) 9248
activation_2 (Activation) (None, 30, 30, 32) 0
max_pooling2d_1 (MaxPooling2 (None, 15, 15, 32) 0
dropout_1 (Dropout) (None, 15, 15, 32) 0
conv2d_3 (Conv2D) (None, 15, 15, 64) 18496
activation_3 (Activation) (None, 15, 15, 64) 0
conv2d_4 (Conv2D) (None, 13, 13, 64) 36928
activation_4 (Activation) (None, 13, 13, 64) 0
max_pooling2d_2 (MaxPooling2 (None, 6, 6, 64) 0
dropout_2 (Dropout) (None, 6, 6, 64) 0
flatten_1 (Flatten) (None, 2304) 0
dense_1 (Dense) (None, 512) 1180160
activation_5 (Activation) (None, 512) 0
dropout_3 (Dropout) (None, 512) 0
dense_2 (Dense) (None, 10) 5130
activation_6 (Activation) (None, 10) 0
Total params: 1,250,858
Trainable params: 1,250,858
Non-trainable params: 0
回答1件
あなたの回答
tips
プレビュー