魚大-程式筆記

安裝 tensorflow 等相關套件

先在cmd安裝這下面這兩行
conda install tensorflow
conda install tensorflow-gpu

安裝完後import tensorflow執行程式看看能不能執行

若不能執行則在cmd下以下兩行指令，移除剛剛所安裝的東西
conda uninstall tensorflow
conda uninstall tensorflow-gpu

接著在cmd再下這兩行指令(通常結束這一步就可以正常使用了)
conda install -c anaconda tensorflow
conda install -c anaconda tensorflow-gpu

若不行，則參考https://github.com/conda-forge/anaconda-client-feedstock
conda config --add channels conda-forge
conda install anaconda-client

檢查tensorflow可以正常使用

安裝其他相關套件

在cmd下指令
conda install theano
conda install -c conda-forge keras

安裝好後一樣 import theano; import keras; 檢查是否可以正常執行程式(通常是可以)
或者執行下面這一段程式，看看執行結果是否約為1

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import RMSprop

batch_size = 128
num_classes = 10
epochs = 2

# the data, shuffled and split between train and test sets
(x_train_image, y_train), (x_test, y_test) = mnist.load_data()

x_train = x_train_image.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Dense(512, activation='relu', input_shape=(784,)))
model.add(Dropout(0.2))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))

model.summary()

model.compile(loss='categorical_crossentropy',
              optimizer=RMSprop(),
              metrics=['accuracy'])

history = model.fit(x_train, y_train,
                    batch_size=batch_size,
                    epochs=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])

執行結果