我如何使用 keras 创建 3d 输入/3d 输出卷积模型? [英] how i can create 3d input / 3d output Convolution model with keras?

问题描述

我有一个小问题无法解决.

I have a bit question i couldnt solve.

我想将具有完全连接的 MLP 的 CNN 模型实现到我的具有 2589 个蛋白质的蛋白质数据库中.每个蛋白质有 1287 行 69 列作为输入和 1287 行和 8 列作为输出.实际上有 1287x1 的输出，但我对类标签使用了一种热编码，以便在我的模型中使用交叉熵损失.

I wanna implement CNN model with fully-connected MLP to my protein database which has 2589 proteins. Each protein has 1287 rows and 69 columns as input and and 1287 rows and 8 columns as output. Actually there was 1287x1 output, but i used one hot encoding for class labels to use crossentropy loss in my model.

我也想要

如果我们将图像视为图像，我有一个 3d 矩阵 ** X_train = (2589, 1287, 69) 用于输入** 和 y_train =(2589, 1287, 8) 输出，我的意思是输出也是矩阵.

if we consider as image i have an 3d matrix ** X_train = (2589, 1287, 69) for input** and y_train =(2589, 1287, 8) output, i mean output is also matrix.

在我的 keras 代码下面:

Below my codes of keras:

model = Sequential()
model.add(Conv2D(64, kernel_size=3, activation="relu", input_shape=(X_train.shape[1],X_train.shape[2])))
model.add(Conv2D(32, kernel_size=3, activation="relu"))
model.add(Flatten())
model.add(Dense((8), activation="softmax"))

但是我遇到了关于密集层的错误:

But I encountered with Error about Dense layer :

ValueError: Error when checking target: expected dense_1 to have 2 dimensions, but got array with shape (2589, 1287, 8)

好的，我知道 Dense 应该采用正整数单位(Keras 文档中的解释.).但是我如何实现矩阵输出到我的模型?

Ok, i understand that Dense should take positive integer unit (explanation in Keras docs. ). But how i can implement matrix output to my model ?

我试过了:

model.add(Dense((1287,8), activation="softmax"))

还有别的东西，但我找不到任何解决方案.

and something else but i couldnt find any solution.

非常感谢.

推荐答案

Conv2D 层需要 (batch_size, height, width, channels) 的输入形状.这意味着每个样本都是一个 3D 数组.

The Conv2D layer requires an input shape of (batch_size, height, width, channels). This means that each sample is a 3D array.

您的实际输入是 (2589, 1287, 8) 意味着每个样本的形状都是 (1289, 8) - 一个二维形状.因此，您应该使用 Conv1D 而不是 Conv2D.

Your actual input is (2589, 1287, 8) meaning that each sample is of shape (1289, 8) - a 2D shape. Because of this, you should be using Conv1D instead of Conv2D.

其次，您需要 (2589, 1287, 8) 的输出.由于每个样本都是 2D 形状，因此 Flatten() 输入是没有意义的 - Flatten() 会将每个样本的形状减少到 1D，并且您想要每个样本都是二维的.

Secondly you want an output of (2589, 1287, 8). Since each sample is of a 2D shape, it makes no sense to Flatten() the input - Flatten() would reduce the shape of each sample to 1D, and you want each sample to be 2D.

最后，根据 Conv 层的填充，形状可能会根据 kernel_size 改变.由于要保留 1287 的中间尺寸，请使用 padding='same' 保持大小不变​​.

Finally depending on the padding of your Conv layers,the shape may change based on the kernel_size. Since you want to preserve the middle dimension of 1287, use padding='same' to keep the size the same.

from keras.models import Sequential
from keras.layers import Conv1D, Flatten, Dense
import numpy as np

X_train = np.random.rand(2589, 1287, 69)
y_train = np.random.rand(2589, 1287, 8)


model = Sequential()
model.add(Conv1D(64, 
                 kernel_size=3, 
                 activation="relu", 
                 padding='same',
                 input_shape=(X_train.shape[1],X_train.shape[2])))
model.add(Conv1D(32, 
                 kernel_size=3, 
                 activation="relu",
                 padding='same'))
model.add(Dense((8), activation="softmax"))

model.summary()
model.compile(loss='categorical_crossentropy', optimizer='adam')
model.fit(X_train, y_train)

这篇关于我如何使用 keras 创建 3d 输入/3d 输出卷积模型?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！