我的目标是调整满足以下标准的可能网络架构：
- 第 1 层可以具有此列表中任意数量的隐藏单元：[32, 64, 128, 256, 512]
然后，要为其余层探索的隐藏单元的数量应始终取决于在其上方层中所做的特定选择，特别是：
- 第 2 层可以具有与第 1 层相同或一半的单元。
- 第 3 层可以具有与第 2 层相同或一半的单元。
- 第 4 层可以具有与第 3 层相同或一半的单元。
正如我目前正在实施的那样，第 2、3 和 4 层的 hp.Choice 选项一旦首次建立就永远不会更新。
例如，假装在调谐器的第一遍，num_layers = 4这意味着将创建所有四个层。例如，如果第 1 层选择 256 个隐藏单元，则选项变为：
第 2 层 --> [128, 256]
第 3 层 --> [64, 128]
第 4 层 --> [32, 64]
第 2 层、第 3 层和第 4 层在随后的每次迭代中都停留在这些选择上，而不是更新以适应第 1 层的未来选择。
这意味着在未来的迭代中，当第 1 层中隐藏单元的数量发生变化时，第 2、3 和 4 层的选项不再满足探索选项的预期目标，其中每个后续层可以包含相同或一半的隐藏单元上一层。
def build_and_tune_model(hp, train_ds, normalize_features, ohe_features, max_tokens, passthrough_features):
all_inputs, encoded_features = get_all_preprocessing_layers(train_ds,
normalize_features=normalize_features,
ohe_features=ohe_features,
max_tokens=max_tokens,
passthrough=passthrough_features)
# Possible values for the number of hidden units in layer 1.
# Defining here because we will always have at least 1 layer.
layer_1_hidden_units = hp.Choice('layer1_hidden_units', values=[32, 64, 128, 256, 512])
# Possible number of layers to include
num_layers = hp.Choice('num_layers', values=[1, 2, 3, 4])
print("================= starting new round =====================")
print(f"Layer 1 hidden units = {hp.get('layer1_hidden_units')}")
print(f"Num layers is {hp.get('num_layers')}")
all_features = layers.concatenate(encoded_features)
x = layers.Dense(layer_1_hidden_units,
activation="relu")(all_features)
if hp.get('num_layers') >= 2:
with hp.conditional_scope("num_layers", [2, 3, 4]):
# Layer 2 hidden units can either be half the layer 1 hidden units or the same.
layer_2_hidden_units = hp.Choice('layer2_hidden_units', values=[(int(hp.get('layer1_hidden_units') / 2)),
hp.get('layer1_hidden_units')])
print("\n==========================================================")
print(f"In layer 2")
print(f"num_layers param = {hp.get('num_layers')}")
print(f"layer_1_hidden_units = {hp.get('layer1_hidden_units')}")
print(f"layer_2_hidden_units = {hp.get('layer2_hidden_units')}")
print("==============================================================\n")
x = layers.Dense(layer_2_hidden_units,
activation="relu")(x)
if hp.get('num_layers') >= 3:
with hp.conditional_scope("num_layers", [3, 4]):
# Layer 3 hidden units can either be half the layer 2 hidden units or the same.
layer_3_hidden_units = hp.Choice('layer3_hidden_units', values=[(int(hp.get('layer2_hidden_units') / 2)),
hp.get('layer2_hidden_units')])
print("\n==========================================================")
print(f"In layer 3")
print(f"num_layers param = {hp.get('num_layers')}")
print(f"layer_1_hidden_units = {hp.get('layer1_hidden_units')}")
print(f"layer_2_hidden_units = {hp.get('layer2_hidden_units')}")
print(f"layer_3_hidden_units = {hp.get('layer3_hidden_units')}")
print("==============================================================\n")
x = layers.Dense(layer_3_hidden_units,
activation="relu")(x)
if hp.get('num_layers') >= 4:
with hp.conditional_scope("num_layers", [4]):
# Layer 4 hidden units can either be half the layer 3 hidden units or the same.
# Extra stipulation applied here, layer 4 hidden units can never be less than 8.
layer_4_hidden_units = hp.Choice('layer4_hidden_units', values=[max(int(hp.get('layer3_hidden_units') / 2), 8),
hp.get('layer3_hidden_units')])
print("\n==========================================================")
print(f"In layer 4")
print(f"num_layers param = {hp.get('num_layers')}")
print(f"layer_1_hidden_units = {hp.get('layer1_hidden_units')}")
print(f"layer_2_hidden_units = {hp.get('layer2_hidden_units')}")
print(f"layer_3_hidden_units = {hp.get('layer3_hidden_units')}")
print(f"layer_4_hidden_units = {hp.get('layer4_hidden_units')}")
print("==============================================================\n")
x = layers.Dense(layer_4_hidden_units,
activation="relu")(x)
output = layers.Dense(1, activation='sigmoid')(x)
model = tf.keras.Model(all_inputs, output)
model.compile(optimizer=tf.keras.optimizers.Adam(),
metrics = ['accuracy'],
loss='binary_crossentropy')
print(">>>>>>>>>>>>>>>>>>>>>>>>>>>> End of round <<<<<<<<<<<<<<<<<<<<<<<<<<<<<")
return model
有谁知道告诉 Keras Tuner 探索每一层隐藏单元的所有可能选项的正确方法，其中要探索的区域满足标准，即第一层之后的每一层允许具有与前一层相同或一半的隐藏单元层，并且第一层可以有来自列表 [32, 64, 128, 256, 512] 的多个隐藏单元？