我正在 Jupyter 上试验一些代码并一直卡在这里。如果我删除以“optimizer = ...”开头的行以及对该行的所有引用，事情实际上工作得很好。但是，如果我将这一行放在代码中，则会出现错误。
我没有在此处粘贴所有其他函数以使代码的大小保持在可读水平。我希望更有经验的人可以立即看到这里有什么问题。
请注意，输入层、2 个隐藏层和输出层中有 5、4、3 和 2 个单元。
代码：
tf.reset_default_graph()
num_units_in_layers = [5,4,3,2]
X = tf.placeholder(shape=[5, 3], dtype=tf.float32)
Y = tf.placeholder(shape=[2, 3], dtype=tf.float32)
parameters = initialize_layer_parameters(num_units_in_layers)
init = tf.global_variables_initializer()
my_sess = tf.Session()
my_sess.run(init)
ZL = forward_propagation_with_relu(X, num_units_in_layers, parameters, my_sess)
#my_sess.run(parameters) # Do I need to run this? Or is it obsolete?
cost = compute_cost(ZL, Y, my_sess, parameters, batch_size=3, lambd=0.05)
optimizer = tf.train.AdamOptimizer(learning_rate = 0.001).minimize(cost)
_ , minibatch_cost = my_sess.run([optimizer, cost],
feed_dict={X: minibatch_X,
Y: minibatch_Y})
print(minibatch_cost)
my_sess.close()
错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-321-135b9fc18268> in <module>()
16 cost = compute_cost(ZL, Y, my_sess, parameters, 3, 0.05)
17
---> 18 optimizer = tf.train.AdamOptimizer(learning_rate = 0.001).minimize(cost)
19 _ , minibatch_cost = my_sess.run([optimizer, cost],
20 feed_dict={X: minibatch_X,
~/.local/lib/python3.5/site-packages/tensorflow/python/training/optimizer.py in minimize(self, loss, global_step, var_list, gate_gradients, aggregation_method, colocate_gradients_with_ops, name, grad_loss)
362 "No gradients provided for any variable, check your graph for ops"
363 " that do not support gradients, between variables %s and loss %s." %
--> 364 ([str(v) for _, v in grads_and_vars], loss))
365
366 return self.apply_gradients(grads_and_vars, global_step=global_step,
ValueError: No gradients provided for any variable, check your graph for ops that do not support gradients, between variables ["<tf.Variable 'weights/W1:0' shape=(4, 5) dtype=float32_ref>", "<tf.Variable 'biases/b1:0' shape=(4, 1) dtype=float32_ref>", "<tf.Variable 'weights/W2:0' shape=(3, 4) dtype=float32_ref>", "<tf.Variable 'biases/b2:0' shape=(3, 1) dtype=float32_ref>", "<tf.Variable 'weights/W3:0' shape=(2, 3) dtype=float32_ref>", "<tf.Variable 'biases/b3:0' shape=(2, 1) dtype=float32_ref>"] and loss Tensor("Add_3:0", shape=(), dtype=float32).
请注意，如果我运行
print(tf.trainable_variables())
就在“优化器 = ...”行之前，我实际上在那里看到了我的可训练变量。
hts/W1:0' shape=(4, 5) dtype=float32_ref>, <tf.Variable 'biases/b1:0' shape=(4, 1) dtype=float32_ref>, <tf.Variable 'weights/W2:0' shape=(3, 4) dtype=float32_ref>, <tf.Variable 'biases/b2:0' shape=(3, 1) dtype=float32_ref>, <tf.Variable 'weights/W3:0' shape=(2, 3) dtype=float32_ref>, <tf.Variable 'biases/b3:0' shape=(2, 1) dtype=float32_ref>]
有人会知道可能是什么问题吗？
编辑和添加更多信息：如果您想看看我如何创建和初始化我的参数，这里是代码。也许这部分有什么问题，但我不明白是什么..
def get_nn_parameter(variable_scope, variable_name, dim1, dim2):
with tf.variable_scope(variable_scope, reuse=tf.AUTO_REUSE):
v = tf.get_variable(variable_name,
[dim1, dim2],
trainable=True,
initializer = tf.contrib.layers.xavier_initializer())
return v
def initialize_layer_parameters(num_units_in_layers):
parameters = {}
L = len(num_units_in_layers)
for i in range (1, L):
temp_weight = get_nn_parameter("weights",
"W"+str(i),
num_units_in_layers[i],
num_units_in_layers[i-1])
parameters.update({"W" + str(i) : temp_weight})
temp_bias = get_nn_parameter("biases",
"b"+str(i),
num_units_in_layers[i],
1)
parameters.update({"b" + str(i) : temp_bias})
return parameters
附录
我让它工作了。我没有写一个单独的答案，而是在这里添加我的代码的正确版本。
（大卫在下面的回答很有帮助。）
我只是删除了 my_sess 作为我的 compute_cost 函数的参数。（我以前无法让它工作，但似乎根本不需要它。）我还在我的主函数中重新排序了语句，以便以正确的顺序调用事物。
这是我的成本函数的工作版本以及我如何称呼它：
def compute_cost(ZL, Y, parameters, mb_size, lambd):
logits = tf.transpose(ZL)
labels = tf.transpose(Y)
cost_unregularized = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits = logits, labels = labels))
#Since the dict parameters includes both W and b, it needs to be divided with 2 to find L
L = len(parameters) // 2
list_sum_weights = []
for i in range (0, L):
list_sum_weights.append(tf.nn.l2_loss(parameters.get("W"+str(i+1))))
regularization_effect = tf.multiply((lambd / mb_size), tf.add_n(list_sum_weights))
cost = tf.add(cost_unregularized, regularization_effect)
return cost
这是我调用 compute_cost(..) 函数的主要函数：
tf.reset_default_graph()
num_units_in_layers = [5,4,3,2]
X = tf.placeholder(shape=[5, 3], dtype=tf.float32)
Y = tf.placeholder(shape=[2, 3], dtype=tf.float32)
parameters = initialize_layer_parameters(num_units_in_layers)
my_sess = tf.Session()
ZL = forward_propagation_with_relu(X, num_units_in_layers, parameters)
cost = compute_cost(ZL, Y, parameters, 3, 0.05)
optimizer = tf.train.AdamOptimizer(learning_rate = 0.001).minimize(cost)
init = tf.global_variables_initializer()
my_sess.run(init)
_ , minibatch_cost = my_sess.run([optimizer, cost],
feed_dict={X: [[-1.,4.,-7.],[2.,6.,2.],[3.,3.,9.],[8.,4.,4.],[5.,3.,5.]],
Y: [[0.6, 0., 0.3], [0.4, 0., 0.7]]})
print(minibatch_cost)
my_sess.close()