【发布时间】：2020-03-20 15:04:23
【问题描述】：
在引入 Tensorflow 2.0 后，scipy 接口 (tf.contrib.opt.ScipyOptimizerInterface) 已被删除。但是，我仍然想使用 scipy 优化器 scipy.optimize.minimize(method='L-BFGS-B') 来训练神经网络（keras model sequence ）。为了让优化器工作，它需要一个函数 fun(x0) 作为输入，其中 x0 是一个形状 (n,) 的数组。因此，第一步是“展平”权重矩阵以获得具有所需形状的向量。为此，我修改了https://pychao.com/2019/11/02/optimize-tensorflow-keras-models-with-l-bfgs-from-tensorflow-probability/提供的代码。这提供了一个函数工厂来创建这样的函数fun(x0)。但是，代码似乎不起作用，损失函数并没有减少。如果有人能帮我解决这个问题，我将不胜感激。
这是我正在使用的代码：
func = function_factory(model, loss_function, x_u_train, u_train)
# convert initial model parameters to a 1D tf.Tensor
init_params = tf.dynamic_stitch(func.idx, model.trainable_variables)
init_params = tf.cast(init_params, dtype=tf.float32)
# train the model with L-BFGS solver
results = scipy.optimize.minimize(fun=func, x0=init_params, method='L-BFGS-B')
def loss_function(x_u_train, u_train, network):
u_pred = tf.cast(network(x_u_train), dtype=tf.float32)
loss_value = tf.reduce_mean(tf.square(u_train - u_pred))
return tf.cast(loss_value, dtype=tf.float32)
def function_factory(model, loss_f, x_u_train, u_train):
"""A factory to create a function required by tfp.optimizer.lbfgs_minimize.
Args:
model [in]: an instance of `tf.keras.Model` or its subclasses.
loss [in]: a function with signature loss_value = loss(pred_y, true_y).
train_x [in]: the input part of training data.
train_y [in]: the output part of training data.
Returns:
A function that has a signature of:
loss_value, gradients = f(model_parameters).
"""
# obtain the shapes of all trainable parameters in the model
shapes = tf.shape_n(model.trainable_variables)
n_tensors = len(shapes)
# we'll use tf.dynamic_stitch and tf.dynamic_partition later, so we need to
# prepare required information first
count = 0
idx = [] # stitch indices
part = [] # partition indices
for i, shape in enumerate(shapes):
n = np.product(shape)
idx.append(tf.reshape(tf.range(count, count+n, dtype=tf.int32), shape))
part.extend([i]*n)
count += n
part = tf.constant(part)
def assign_new_model_parameters(params_1d):
"""A function updating the model's parameters with a 1D tf.Tensor.
Args:
params_1d [in]: a 1D tf.Tensor representing the model's trainable parameters.
"""
params = tf.dynamic_partition(params_1d, part, n_tensors)
for i, (shape, param) in enumerate(zip(shapes, params)):
model.trainable_variables[i].assign(tf.cast(tf.reshape(param, shape), dtype=tf.float32))
# now create a function that will be returned by this factory
def f(params_1d):
"""
This function is created by function_factory.
Args:
params_1d [in]: a 1D tf.Tensor.
Returns:
A scalar loss.
"""
# update the parameters in the model
assign_new_model_parameters(params_1d)
# calculate the loss
loss_value = loss_f(x_u_train, u_train, model)
# print out iteration & loss
f.iter.assign_add(1)
tf.print("Iter:", f.iter, "loss:", loss_value)
return loss_value
# store these information as members so we can use them outside the scope
f.iter = tf.Variable(0)
f.idx = idx
f.part = part
f.shapes = shapes
f.assign_new_model_parameters = assign_new_model_parameters
return f
这里 model 是一个对象 tf.keras.Sequential。
提前感谢您的帮助！
【问题讨论】：
标签： python tensorflow keras neural-network scipy-optimize