我正在尝试从此处https://github.com/tensorflow/docs/blob/master/site/en/tutorials/generative/deepdream.ipynb
修改代码以便我可以运行任何任意的优化器，而不仅仅是像在其代码的梯度上升部分中那样实现梯度下降。
这是相关代码的原始版本：
class DeepDream(tf.Module):
def __init__(self, model):
self.model = model
@tf.function(
input_signature=(
tf.TensorSpec(shape=[None,None,3], dtype=tf.float32),
tf.TensorSpec(shape=[], dtype=tf.int32),
tf.TensorSpec(shape=[], dtype=tf.float32),)
)
def __call__(self, img, steps, step_size):
print("Tracing")
loss = tf.constant(0.0)
for n in tf.range(steps):
with tf.GradientTape() as tape:
# This needs gradients relative to `img`
# `GradientTape` only watches `tf.Variable`s by default
tape.watch(img)
loss = calc_loss(img, self.model)
# Calculate the gradient of the loss with respect to the pixels of the input image.
gradients = tape.gradient(loss, img)
# Normalize the gradients.
gradients /= tf.math.reduce_std(gradients) + 1e-8
# In gradient ascent, the "loss" is maximized so that the input image increasingly "excites" the layers.
# You can update the image by directly adding the gradients (because they're the same shape!)
img = img + gradients*step_size
img = tf.clip_by_value(img, -1, 1)
return loss, img
我尝试将其更改为此：
class DeepDream(tf.Module):
def __init__(self, model):
self.model = model
@tf.function(
input_signature=(
tf.TensorSpec(shape=[None,None,3], dtype=tf.float32),
tf.TensorSpec(shape=[], dtype=tf.int32),
tf.TensorSpec(shape=[], dtype=tf.float32),)
)
def __call__(self, img, steps, step_size):
print("Tracing")
opt=tf.optimizers.SGD(step_size)
loss = tf.constant(0.0)
for n in tf.range(steps):
with tf.GradientTape() as tape:
# This needs gradients relative to `img`
# `GradientTape` only watches `tf.Variable`s by default
tape.watch(img)
loss = calc_loss(img, self.model)
# Calculate the gradient of the loss with respect to the pixels of the input image.
gradients = tape.gradient(loss, img)
# Normalize the gradients.
gradients /= tf.math.reduce_std(gradients) + 1e-8
# In gradient ascent, the "loss" is maximized so that the input image increasingly "excites" the layers.
# You can update the image by directly adding the gradients (because they're the same shape!)
# img = img + gradients*step_size
opt.apply_gradients(zip([gradients],[img]))
img = tf.clip_by_value(img, -1, 1)
return loss, img
进行此更改时，出现以下错误：
NotImplementedError ：（“尝试更新张量”，）
我知道img需要一个tf.Variable实例。但是，我尝试了多种方法来执行此操作，例如，将img初始化为函数外部的tf.Variable，但似乎无济于事。
执行此操作的正确方法是什么？