我正在尝试使用 keras 微调模型,根据以下描述:https://keras.io/applications/#inceptionv3
然而,在训练过程中,我发现当使用相同的输入(同时所有相关层都被卡住)时,网络的输出在训练后不会保持不变,这是我不想要的。
我构建了以下玩具示例来对此进行调查:
import keras.applications.resnet50 as resnet50
from keras.layers import Dense, Flatten, Input
from keras.models import Model
from keras.utils import to_categorical
from keras import optimizers
from keras.preprocessing.image import ImageDataGenerator
import numpy as np
# data
i = np.random.rand(1,224,224,3)
X = np.random.rand(32,224,224,3)
y = to_categorical(np.random.randint(751, size=32), num_classes=751)
# model
base_model = resnet50.ResNet50(weights='imagenet', include_top=False, input_tensor=Input(shape=(224,224,3)))
layer = base_model.output
layer = Flatten(name='myflatten')(layer)
layer = Dense(751, activation='softmax', name='fc751')(layer)
model = Model(inputs=base_model.input, outputs=layer)
# freeze all layers
for layer in model.layers:
layer.trainable = False
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')
# features and predictions before training
feat0 = base_model.predict(i)
pred0 = model.predict(i)
weights0 = model.layers[-1].get_weights()
# before training output is consistent
feat00 = base_model.predict(i)
pred00 = model.predict(i)
print(np.allclose(feat0, feat00)) # True
print(np.allclose(pred0, pred00)) # True
# train
model.fit(X, y, batch_size=2, epochs=3, shuffle=False)
# features and predictions after training
feat1 = base_model.predict(i)
pred1 = model.predict(i)
weights1 = model.layers[-1].get_weights()
# these are not the same
print(np.allclose(feat0, feat1)) # False
# Optionally: printing shows they are in fact very different
# print(feat0)
# print(feat1)
# these are not the same
print(np.allclose(pred0, pred1)) # False
# Optionally: printing shows they are in fact very different
# print(pred0)
# print(pred1)
# these are the same and loss does not change during training
# so layers were actually frozen
print(np.allclose(weights0[0], weights1[0])) # True
# Check again if all layers were in fact untrainable
for layer in model.layers:
assert layer.trainable == False # All succeed
# Being overly cautious also checking base_model
for layer in base_model.layers:
assert layer.trainable == False # All succeed
由于我卡住了所有层,所以我完全希望预测和特征都相等,但令人惊讶的是它们并非如此。
所以我可能犯了某种错误,但我想不出是什么..任何建议将不胜感激!
请您参考如下方法:
所以问题似乎是该模型使用了批量归一化层,这些层确实会根据训练期间看到的数据更新它们的内部状态(即它们的权重)。当他们的可训练标志被设置为 False 时,甚至会发生这种情况。随着权重的更新,输出也会发生变化。您可以使用问题中的代码并更改以下代码行来检查这一点:
这个weights0 = model.layers[-1].get_weights()
到 weights0 = model.layers[2].get_weights()
和这个 weights1 = model.layers[-1].get_weights()
到 weights1 = model.layers[2].get_weights()
或任何其他批量归一化层的索引。
因为接下来的断言将不再成立:
print(np.allclose(weights0, weights1)) # 现在这是 False
据我所知,目前还没有解决方案..
另见我的 issue在 Keras 的 Github 页面上。
