在 TensorFlow < 2.0 中,我们经常使用 tf.name_scope
或者 tf.variable_scope
来定义层,特别是像 inception modules 这样的更复杂的设置。
利用这些操作符,我们能够方便地构建计算图,结果使得 TensorBoard 的图形视图更容易解释。
这对于调试复杂的架构非常方便。
不幸的是,在 TensorFlow >= 2.0 中,tf.keras
似乎忽略了 tf.name_scope
,并且 tf.variable_scope
已经消失了。因此,像这样的解决方案......
with tf.variable_scope("foo"):
with tf.variable_scope("bar"):
v = tf.get_variable("v", [1])
assert v.name == "foo/bar/v:0"
...不再可用。有任何替代品吗?
在TensorFlow >= 2.0中,我们如何对层和整个模型进行分组?如果我们不对层进行分组,tf.keras
会在图形视图中将所有内容串行地放置,从而使复杂模型变得混乱。
是否有tf.variable_scope
的替代方法?我到目前为止还没有找到任何替代品,但在TensorFlow < 2.0中重度使用了该方法。
编辑:我现在已经实现了一个TensorFlow 2.0的例子。 这是使用tf.keras
实现的简单GAN:
# Generator
G_inputs = tk.Input(shape=(100,), name=f"G_inputs")
x = tk.layers.Dense(7 * 7 * 16)(G_inputs)
x = tf.nn.leaky_relu(x)
x = tk.layers.Flatten()(x)
x = tk.layers.Reshape((7, 7, 16))(x)
x = tk.layers.Conv2DTranspose(32, (3, 3), padding="same")(x)
x = tk.layers.BatchNormalization()(x)
x = tf.nn.leaky_relu(x)
x = tf.image.resize(x, (14, 14))
x = tk.layers.Conv2DTranspose(32, (3, 3), padding="same")(x)
x = tk.layers.BatchNormalization()(x)
x = tf.nn.leaky_relu(x)
x = tf.image.resize(x, (28, 28))
x = tk.layers.Conv2DTranspose(32, (3, 3), padding="same")(x)
x = tk.layers.BatchNormalization()(x)
x = tf.nn.leaky_relu(x)
x = tk.layers.Conv2DTranspose(1, (3, 3), padding="same")(x)
x = tf.nn.sigmoid(x)
G_model = tk.Model(inputs=G_inputs,
outputs=x,
name="G")
G_model.summary()
# Discriminator
D_inputs = tk.Input(shape=(28, 28, 1), name=f"D_inputs")
x = tk.layers.Conv2D(32, (3, 3), padding="same")(D_inputs)
x = tf.nn.leaky_relu(x)
x = tk.layers.MaxPooling2D((2, 2))(x)
x = tk.layers.Conv2D(32, (3, 3), padding="same")(x)
x = tf.nn.leaky_relu(x)
x = tk.layers.MaxPooling2D((2, 2))(x)
x = tk.layers.Conv2D(64, (3, 3), padding="same")(x)
x = tf.nn.leaky_relu(x)
x = tk.layers.Flatten()(x)
x = tk.layers.Dense(128)(x)
x = tf.nn.sigmoid(x)
x = tk.layers.Dense(64)(x)
x = tf.nn.sigmoid(x)
x = tk.layers.Dense(1)(x)
x = tf.nn.sigmoid(x)
D_model = tk.Model(inputs=D_inputs,
outputs=x,
name="D")
D_model.compile(optimizer=tk.optimizers.Adam(learning_rate=1e-5, beta_1=0.5, name="Adam_D"),
loss="binary_crossentropy")
D_model.summary()
GAN = tk.Sequential()
GAN.add(G_model)
GAN.add(D_model)
GAN.compile(optimizer=tk.optimizers.Adam(learning_rate=1e-5, beta_1=0.5, name="Adam_GAN"),
loss="binary_crossentropy")
tb = tk.callbacks.TensorBoard(log_dir="./tb_tf2.0", write_graph=True)
# dummy data
noise = np.random.rand(100, 100).astype(np.float32)
target = np.ones(shape=(100, 1), dtype=np.float32)
GAN.fit(x=noise,
y=target,
callbacks=[tb])
这些模型在TensorBoard中的图表看起来像这样。层次结构非常混乱,而且右侧的“G”和“D”模型也很凌乱。“GAN”完全没有显示。训练操作“Adam”无法正确打开:从左到右绘制了太多层,并且箭头到处都是。这种方式很难检查GAN的正确性。
尽管同样的GAN使用TensorFlow 1.X实现涵盖了大量的“样板代码”......
# Generator
Z = tf.placeholder(tf.float32, shape=[None, 100], name="Z")
def model_G(inputs, reuse=False):
with tf.variable_scope("G", reuse=reuse):
x = tf.layers.dense(inputs, 7 * 7 * 16)
x = tf.nn.leaky_relu(x)
x = tf.reshape(x, (-1, 7, 7, 16))
x = tf.layers.conv2d_transpose(x, 32, (3, 3), padding="same")
x = tf.layers.batch_normalization(x)
x = tf.nn.leaky_relu(x)
x = tf.image.resize_images(x, (14, 14))
x = tf.layers.conv2d_transpose(x, 32, (3, 3), padding="same")
x = tf.layers.batch_normalization(x)
x = tf.nn.leaky_relu(x)
x = tf.image.resize_images(x, (28, 28))
x = tf.layers.conv2d_transpose(x, 32, (3, 3), padding="same")
x = tf.layers.batch_normalization(x)
x = tf.nn.leaky_relu(x)
x = tf.layers.conv2d_transpose(x, 1, (3, 3), padding="same")
G_logits = x
G_out = tf.nn.sigmoid(x)
return G_logits, G_out
# Discriminator
D_in = tf.placeholder(tf.float32, shape=[None, 28, 28, 1], name="D_in")
def model_D(inputs, reuse=False):
with tf.variable_scope("D", reuse=reuse):
with tf.variable_scope("conv"):
x = tf.layers.conv2d(inputs, 32, (3, 3), padding="same")
x = tf.nn.leaky_relu(x)
x = tf.layers.max_pooling2d(x, (2, 2), (2, 2))
x = tf.layers.conv2d(x, 32, (3, 3), padding="same")
x = tf.nn.leaky_relu(x)
x = tf.layers.max_pooling2d(x, (2, 2), (2, 2))
x = tf.layers.conv2d(x, 64, (3, 3), padding="same")
x = tf.nn.leaky_relu(x)
with tf.variable_scope("dense"):
x = tf.reshape(x, (-1, 7 * 7 * 64))
x = tf.layers.dense(x, 128)
x = tf.nn.sigmoid(x)
x = tf.layers.dense(x, 64)
x = tf.nn.sigmoid(x)
x = tf.layers.dense(x, 1)
D_logits = x
D_out = tf.nn.sigmoid(x)
return D_logits, D_out
# models
G_logits, G_out = model_G(Z)
D_logits, D_out = model_D(D_in)
GAN_logits, GAN_out = model_D(G_out, reuse=True)
# losses
target = tf.placeholder(tf.float32, shape=[None, 1], name="target")
d_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=D_logits, labels=target))
gan_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=GAN_logits, labels=target))
# train ops
train_d = tf.train.AdamOptimizer(learning_rate=1e-5, name="AdamD") \
.minimize(d_loss, var_list=tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="D"))
train_gan = tf.train.AdamOptimizer(learning_rate=1e-5, name="AdamGAN") \
.minimize(gan_loss, var_list=tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="G"))
# dummy data
dat_noise = np.random.rand(100, 100).astype(np.float32)
dat_target = np.ones(shape=(100, 1), dtype=np.float32)
sess = tf.Session()
tf_init = tf.global_variables_initializer()
sess.run(tf_init)
# merged = tf.summary.merge_all()
writer = tf.summary.FileWriter("./tb_tf1.0", sess.graph)
ret = sess.run([gan_loss, train_gan], feed_dict={Z: dat_noise, target: dat_target})
...最终得到的TensorBoard图看起来更加清晰。请注意右上角的“AdamD”和“AdamGAN”作用域是多么干净。您可以直接检查优化器是否附加到正确的作用域/梯度。
tf.keras.layers.Conv2D(..., name='conv_1')
即可。或者您可以更具体地说明一下? - Sharkyname ='modelX/scopeY/layerZ'
吗?使用tf.variable_scope
就容易得多了。 - daniel451tf.keras
在TF 1.X和TF 2.0中都进行了实现。请查看附加的图像,比较TF 2.0创建的图形与使用变量作用域从TF 1.X创建的图形。 - daniel451img_input = Input(shape=(224,224,3), name='Img_input') x = Conv2D(64, (3,3), activation='relu', name='Conv1')(img_input) x = Flatten(name='flatten')(x) z = Dense(1, activation='sigmoid', name='output')(x) model = Model(img_input, z, name='sample_model') model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) tb = TensorBoard('logs', write_graph=True) model.fit(random_input, random_output, callbacks=[tb], epochs=1, batch_size=8)
- enterML