如何在现有模型中添加更多的层(例如。可教机器应用模型)？
如何在现有模型中添加更多的层(例如。可教机器应用模型)？
提问于 2020-11-05 08:55:48
我试图通过在输出层之前添加几个层来使用可教机器应用程序https://teachablemachine.withgoogle.com/中的google模型。当我重新训练模型时，总是返回以下错误：
ValueError:层dense_25的输入0与图层不兼容:输入形状的预期轴-1值为5，但接收到的输入为20,512。
我的方法是：
当重新训练模型时，它返回错误：
如果我重新训练模型，而不添加新的层，它的工作很好。有人能告诉我是怎么回事吗？
回答 1
Stack Overflow用户
回答已采纳
发布于 2020-11-07 19:25:41
更新应答
如果您想要在两个层之间为预先训练的模型添加层，它并不像使用add方法添加层那么简单。如果这样做会导致意想不到的行为。
错误分析：
如果您像下面这样编译模型(就像您指定的那样)：
model.layers[-1].add(Dense(512, activation ="relu"))
model.add(Dense(128, activation="relu"))
model.add(Dense(32))
model.add(Dense(5))示范摘要的产出：
Model: "sequential_12"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
sequential_9 (Sequential) (None, 1280) 410208
_________________________________________________________________
sequential_11 (Sequential) (None, 512) 131672
_________________________________________________________________
dense_12 (Dense) (None, 128) 768
_________________________________________________________________
dense_13 (Dense) (None, 32) 4128
_________________________________________________________________
dense_14 (Dense) (None, 5) 165
=================================================================
Total params: 546,941
Trainable params: 532,861
Non-trainable params: 14,080
_________________________________________________________________这里的一切看起来都很好，但仔细看一下：
for l in model.layers:
print("layer : ", l.name, ", expects input of shape : ",l.input_shape)产出：
layer : sequential_9 , expects input of shape : (None, 224, 224, 3)
layer : sequential_11 , expects input of shape : (None, 1280)
layer : dense_12 , expects input of shape : (None, 5) <-- **PROBLEM**
layer : dense_13 , expects input of shape : (None, 128)
layer : dense_14 , expects input of shape : (None, 32)PROBLEM在这里是dense_12期望输入的形状(无，5)，但是它应该期望输入形状为(None，512)，因为我们已经向sequential_11添加了密集(512)，可能的原因是添加了类似于上面指定的层可能不会更新很少的属性，比如sequential_11的输出形状，所以在向前传递时，sequential_11的输出和层dense_12的输入之间会出现不匹配(在您的例子中是dense_25)。
可能的工作是:
对于“在sequential_9和sequential_11之间添加层”的问题，您可以在sequential_9和sequential_11之间添加任意多个层，但始终确保最后添加的层的输出形状与sequential_11所期望的输入形状相匹配。在这种情况下，它是1280。
代码：
sequential_1 = model.layers[0] # re-using pre-trained model
sequential_2 = model.layers[1]
from tensorflow.keras.layers import Input
from tensorflow.keras.layers import Dense
from tensorflow.keras.models import Model
inp_sequential_1 = Input(sequential_1.layers[0].input_shape[1:])
out_sequential_1 = sequential_1(inp_sequential_1)
#adding layers in between sequential_9 and sequential_11
out_intermediate = Dense(512, activation="relu")(out_sequential_1)
out_intermediate = Dense(128, activation ="relu")(out_intermediate)
out_intermediate = Dense(32, activation ="relu")(out_intermediate)
# always make sure to include a layer with output shape matching input shape of sequential 11, in this case 1280
out_intermediate = Dense(1280, activation ="relu")(out_intermediate)
output = sequential_2(out_intermediate) # output of intermediate layers are given to sequential_11
final_model = Model(inputs=inp_sequential_1, outputs=output)示范摘要的产出：
Model: "functional_3"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_5 (InputLayer) [(None, 224, 224, 3)] 0
_________________________________________________________________
sequential_9 (Sequential) (None, 1280) 410208
_________________________________________________________________
dense_15 (Dense) (None, 512) 655872
_________________________________________________________________
dense_16 (Dense) (None, 128) 65664
_________________________________________________________________
dense_17 (Dense) (None, 32) 4128
_________________________________________________________________
dense_18 (Dense) (None, 1280) 42240
_________________________________________________________________
sequential_11 (Sequential) (None, 5) 128600
=================================================================
Total params: 1,306,712
Trainable params: 1,292,632
Non-trainable params: 14,080页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/64693961
复制相关文章
相似问题
腾讯云开发者
