Question

我是一个初学者，开始学习在Keras后端Tensorflow中进行编码。我正在使用python 2.7

我在喀拉拉邦有模特，训练后我想检查一下体重。

已编辑

# fix random seed for reproducibility (split training and validation set)
seed = 7
np.random.seed(seed)

# load data
(X_train, y_train), (X_test, y_test) = mnist.load_data()

# reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28).astype('float32')

# normalize inputs from 0-255 to 0-1
X_train = X_train / 255
X_test = X_test / 255

# one hot encode outputs (label encoding)
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]

def tempsigmoid(x, temp=0.5):
    return K.sigmoid(x/temp)


def baseline_model():
    # create model
    model = Sequential()
    model.add(Conv2D(32, (5, 5), input_shape=(1, 28, 28), activation='relu'))
    #model.add(Dense, input_shape = (1,28,28), Activation='relu')
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(100, activation='relu'))
    model.add(Dense(num_classes, activation=tempsigmoid))

    # Compile model
    model.compile(loss='mae', optimizer=SGD(lr=0.1), metrics=['accuracy'])
    return model

    # build the model
model = baseline_model()

earlystopper = EarlyStopping(monitor='val_loss', min_delta=0.1, patience=0, verbose=2, mode='auto')

# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=5, batch_size=200, verbose=2, callbacks=[earlystopper])

# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("CNN Error: %.2f%%" % (100-scores[1]*100))
# print("Metrics(Test loss & Test Accuracy): ")
print(scores)

weight = model.get_weights()
print(weight)

我得到图片中数组中的权重。如何将砝码数组保存到csv文件中？

weight array

我尝试使用model.save_weight（），并且有一个h5格式的输出文件，但是当我想用numpy打开它时，它只显示其中的一小部分。当我可以将其保存为csv格式时，我很想知道，我将完全显示数据。

我曾尝试使用numpy python将h5转换为csv，如图所示

# to save weight after output
model.save_weights('Result/w_output.h5')

Tried to display full array with numpy

Answer 1

我假设您希望每个数字列表都位于其自己的行中。如果是这种情况，则需要按照以下形状权重= [[data1，data2，data3 ...]，[data11，data12，data13 ...] ...]重新设置权重。 functions for reforming list

然后，您只需要将其写入/添加到csv文件即可。您可以使用pandas或csv库。

Answer 2

通过使用此编码，我已成功将数组的权重保存为csv

weight = model.get_weights()
np.savetxt('weight.csv' , weight , fmt='%s', delimiter=',')

如何将数组形式的model.get_weight保存到csv？

2 个答案: