我用张量流实现了神经网络模型。
但是代码无法正常工作。
环境：
OS：Linux
CPU：x86_64（Intel CPU）
框架：张量流（版本2，Python3）
以下是代码
import tensorflow as tf
tf.random.set_seed(seed=1234)
class DenseLayer(object):
def __init__(self, input_dimention, output_dimention):
self.list = []
self.w = tf.Variable(tf.random.normal([input_dimention, output_dimention], dtype=tf.float64))
self.b = tf.Variable(tf.random.normal([1,], dtype=tf.float64))
self.list.append(self.w)
self.list.append(self.b)
def dense_layer(self, inputs, no_activation):
mean, var = tf.nn.moments(inputs, [0, 1])
inputs = tf.nn.batch_normalization(inputs, mean, var, 0, 1, 0.00001)
z = tf.matmul(inputs, self.w) + self.b
if no_activation==False:
return tf.nn.relu(inputs)
return z
class Model(object):
def __init__(self):
self.var_list = []
self.alpha = 0.01
self.lamb = 0.1
self.epochs = 1
#モデルの定義と初期化を行う
def define_model(self):
self.dense_layer1 = DenseLayer(28*28, 100)
self.push_parameter(self.dense_layer1)
self.dense_layer2 = DenseLayer(28*28, 10)
self.push_parameter(self.dense_layer2)
def push_parameter(self, layer):
for param in layer.list:
self.var_list.append(param)
return
def run(self, inputs):
inputs = self.flattend(inputs, 28,28,1)
dense_layer1 = self.dense_layer1.dense_layer(inputs, False)
dense_layer2 = self.dense_layer2.dense_layer(dense_layer1, True)
return dense_layer2
def loss(self, outputs, targets):
predicted_y = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = outputs, labels = targets))
return predicted_y
def grad(self, x, target_y):
with tf.GradientTape() as tape:
tape.watch(self.var_list)
loss_value = self.loss(self.run(x), target_y)
return tape.gradient(loss_value, self.var_list)
def flattend(self, inputs, x, y, z):
inputs = tf.cast(inputs, tf.float64)
return tf.reshape(inputs, [-1, x*y*z])
def optimizer(self):
opt = tf.keras.optimizers.SGD(learning_rate=self.alpha)
return opt
def model_train(self):
mnist = tf.keras.datasets.mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
train_images = train_images/255.0
test_images = test_images/255.0
train_labels = make_onehot_labels(train_labels)
test_labels = make_onehot_labels(test_labels)
ds_train_x = tf.data.Dataset.from_tensor_slices(train_images)
ds_train_y = tf.data.Dataset.from_tensor_slices(train_labels)
train_dataset = tf.data.Dataset.zip((ds_train_x, ds_train_y)).shuffle(buffer_size=10).repeat().batch(100)
train_images = tf.convert_to_tensor(train_images)
train_labels = tf.convert_to_tensor(train_labels)
test_images = tf.convert_to_tensor(test_images)
test_labels = tf.convert_to_tensor(test_labels)
self.define_model()
opt = self.optimizer()
print(self.var_list)
for epoch in range(self.epochs):
for (batch, (images, labels)) in enumerate(train_dataset):
if batch ==600:
break
grads = self.grad(images, labels)
opt.apply_gradients(zip(grads, self.var_list))
def make_onehot_labels(labels):
depth = 10
one_hot_labels = tf.one_hot(labels, depth)
return one_hot_labels
以下是执行代码时的错误。
此问题与渐变有关。
请告诉我为什么发生此问题。
Gradients do not exist for variables ['Variable:0', 'Variable:0'] when minimizing the loss.