加载预训练模型后与可变输入尺寸相关的错误
Posted
技术标签:
【中文标题】加载预训练模型后与可变输入尺寸相关的错误【英文标题】:Error related to variable Input dimensions after loading pretrained model 【发布时间】:2021-12-18 01:29:32 【问题描述】:我的模型有以下代码:
model = keras.Sequential()
model.add(L.InputLayer(batch_input_shape= (None, 768)))
model.add(L.Dense(input_shape = (None,768), activation='relu', units = 256))
model.add(L.Dense(input_shape = (None,256), activation='relu', units = 128))
model.add(L.Dense(input_shape=(None,128), activation='relu', units = 301))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy', precision, recall, f1])
有了model.summury()这样的结果:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, 256) 196864
_________________________________________________________________
dense_2 (Dense) (None, 128) 32896
_________________________________________________________________
dense_3 (Dense) (None, 301) 38829
=================================================================
Total params: 268,589
Trainable params: 268,589
Non-trainable params: 0
_______________________________________
我已经用这段代码保存了预训练模型:
model.save('./tag_prediction_model.h5')
并加载了这个:
dependincies =
'precision': precision,
'recall': recall,
'f1': f1
model1 = load_model('./tag_prediction_model.h5', custom_objects=dependincies)
但是当我从文件中加载它时,dimensoins 发生了这个错误。我检查了加载的模型摘要并看到了这个:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, None, 256) 196864
_________________________________________________________________
dense_2 (Dense) (None, None, 128) 32896
_________________________________________________________________
dense_3 (Dense) (None, None, 301) 38829
=================================================================
Total params: 268,589
Trainable params: 268,589
Non-trainable params: 0
_________________________________________________________________
我该如何解决这个问题?我正在使用 tensorflow 1.15 和 keras 2.3.1
【问题讨论】:
【参考方案1】:我找到了解释in this post:
删除 InputLayer 并在第一层使用 input_shape ... 似乎模型 使用 InputLayer 未正确序列化为 HDF5。
通过如下所示更改您的模型,它应该可以工作:
model = keras.Sequential()
model.add(L.Dense(input_shape= (768,), activation='relu', units = 256))
model.add(L.Dense(activation='relu', units = 128))
model.add(L.Dense(activation='relu', units = 301))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()
注意输入的形状是 (768,) 而不是 (None, 768)。
【讨论】:
以上是关于加载预训练模型后与可变输入尺寸相关的错误的主要内容,如果未能解决你的问题,请参考以下文章