如何将从 ccn1 提取的特征传递给另一个 cnn2？
[英]How to pass features extracted from ccn1 to another cnn2?
问题描述
i made a cnn and from the third conv layer i extracted the features so that the shape is (600,12,12,128)
我制作了一个 cnn 并从第三个 conv 层提取了特征，使得形状为 (600,12,12,128)
600 = training images 12x12128 = for a single image 600 = 训练图像 12x12128 = 对于单个图像
Now i want to pass these to another cnn2 as an input But i want the input shape to be (600,12,12,1).现在我想将这些作为输入传递给另一个 cnn2 但我希望输入形状为 (600,12,12,1)。
How to change the shape?如何改变形状？
1 个解决方案
解决方案1
0 2020-12-24 14:46:19
Try with Lambda layer in order to slice the output tensor from cnn1:尝试使用Lambda 层，以便从 cnn1 中切出 output 张量：
model=models.Sequential()
model.add(cnn1)
model.add(Lambda(lambda x : x[:,:,i])) # with 0 <= i < 128
model.add(cnn2)
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.
相关问题
如何将从 cnn 密集层提取的特征传递给另一个 cnn？ - How to pass feature extracted from cnn dense layer to another cnn?
如何组合从两个 cnn 模型中提取的特征？ - How to combine features extracted from two cnn models?
如何将提取的特征传递给 keras 模型？ - How to pass extracted features to keras model?
如何存储 CNN 提取的特征以训练 SVM 分类器 - How to store CNN extracted features to train a SVM classifier
如何在使用 CNN 提取特征的同时使用 SVM 进行分类？ - How to use SVM to classify while the features are extracted using CNN?
在CNN提取的功能之上使用SVM-如何进行多类分类？ - Using SVM on top of CNN extracted features - How to do Multi-Class classification?
具有图像数据和预提取特征的 CNN 模型 - CNN model with both image data and pre-extracted features
如何可视化从 ResNet50 中提取的特征 - How to visualize features extracted from ResNet50
如何提取音频的 mfcc 特征并将其传递给 cnn 以训练 model？ - How can I extract mfcc features for audio and pass it to the cnn to train the model?
如何在LSTM中提供视频的特征提取帧？ - How to feed features extracted frames of videos in a LSTM?
相关标签