在张量板上可视化特征图

如何解决在张量板上可视化特征图

我想可视化张量板上各层之间的地图特征和权重。 这是我的代码：

# Load the TensorBoard notebook extension
%load_ext tensorboard.notebook

callbacks = [
# Write TensorBoard logs to './logs' directory 
tf.keras.callbacks.TensorBoard(log_dir='./logs/tensorflow_exercise')
]

# network and training
EPOCHS = 20
BATCH_SIZE = 128
VERBOSE = 1
OPTIMIZER = tf.keras.optimizers.Adam()
VALIDATION_SPLIT=0.95
IMG_ROWS,IMG_COLS = 28,28 
# input image dimensions 
INPUT_SHAPE = (IMG_ROWS,IMG_COLS,1)
NB_CLASSES = 10 
# number of outputs = number of digits

def build(input_shape,classes):
    model = models.Sequential()
    #First stage
    model.add(tf.keras.layers.Convolution2D(20,(5,5),activation='relu',input_shape=input_shape))
    model.add(tf.keras.layers.MaxPool2D(pool_size=(2,2),strides=(2,2)))
    #Second stage
    model.add(tf.keras.layers.Convolution2D(50,activation='relu')) 
    model.add(tf.keras.layers.MaxPooling2D(pool_size=(2,2)))
    # Flatten => RELU layers
    model.add(tf.keras.layers.Flatten()) 
    model.add(tf.keras.layers.Dense(500,activation='relu'))
    # a softmax classifier
    model.add(tf.keras.layers.Dense(classes,activation="softmax")) 
    model.summary()
    return model


mnist = tf.keras.datasets.mnist
# data: shuffled and split between train and test sets
(X_train,y_train),(X_test,y_test) = datasets.mnist.load_data()
# reshape
X_train = X_train.reshape((60000,28,1)) 
X_test = X_test.reshape((10000,1))
# normalize


X_train,X_test = X_train / 255.0,X_test / 255.0


# cast
X_train = X_train.astype('float32') 
X_test = X_test.astype('float32')
# convert class vectors to binary class matrices
y_train = tf.keras.utils.to_categorical(y_train,NB_CLASSES)
y_test = tf.keras.utils.to_categorical(y_test,NB_CLASSES)
# initialize the optimizer and model
model = build(input_shape=INPUT_SHAPE,classes=NB_CLASSES) 
model.compile(loss="categorical_crossentropy",optimizer=OPTIMIZER,metrics=["accuracy"]) 
model.summary()
# use TensorBoard,princess Aurora! 
callbacks = [
      # Write TensorBoard logs to './logs' directory
        tf.keras.callbacks.TensorBoard(log_dir='./logs',histogram_freq=1) ]






log_dir = "logs/fit/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir,histogram_freq=1)


# fit
history = model.fit(X_train,y_train,batch_size=BATCH_SIZE,epochs=EPOCHS,verbose=VERBOSE,validation_split=VALIDATION_SPLIT,callbacks=callbacks)
score = model.evaluate(X_test,y_test,verbose=VERBOSE) 
print("\nTest score:",score[0])
print('Test accuracy:',score[1])

%tensorboard --logdir logs

我认为我必须使用tf.keras.callbacks.ModelCheckpoint，但这不起作用。 我在google中没有找到任何回应，我看到有keract，但是我想用tensorboard来实现。 我该怎么办？

非常感谢您