keras中的组卷积

Question

我创建了一个简单的神经网络来了解组卷积如何减少参数数量。但是当我在第二个卷积层中使用 groups 参数时，我得到了一个未实现的错误。但是，当不使用 groups 参数时，一切正常。为什么在使用 groups 参数时会抛出未实现的错误？这是否意味着在 keras api 中不可用组卷积？

import tensorflow
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D,Reshape,MaxPooling2D
from tensorflow.keras.utils import to_categorical
import numpy as np

num_classes = 10

a = np.random.randint(low=0,high=255,size=(100,28,28,1))

b = np.random.randint(low=0,high=10,size=(100,7,7))

a = a.astype('float32')

a = a/255


X_train, Y_train = a[:80], b[:80]

X_test, Y_test = a[80:], b[80:]

num_classes=10

Y_train = to_categorical(Y_train, num_classes)
Y_test = to_categorical(Y_test, num_classes)

# Create the model
model = Sequential()
model.add(Conv2D(8, kernel_size=(3,3),input_shape=(28,28,1),padding='same'))
model.add(Conv2D(8, kernel_size=(3,3),groups=4,input_shape=(28,28,1),padding='same'))
# model.add(Dense(10, input_shape=input_shape, activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))
model.add(MaxPooling2D())
model.add(MaxPooling2D())
# model.add(Reshape(target_shape=(10,)))
         
model.summary()

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X_train, Y_train, epochs=10, batch_size=250, verbose=1, validation_split=0.2)

# model.save_weights("model.h5")


# # Test the model after training
# test_results = model.evaluate(X_test, Y_test, verbose=1)
# print(f'Test results - Loss: {test_results[0]} - Accuracy: {test_results[1]}%')

错误

UnimplementedError:  Fused conv implementation does not support grouped convolutions for now.
     [[node sequential_38/conv2d_37/BiasAdd (defined at <ipython-input-42-e7c1c931a421>:50) ]] [Op:__inference_train_function_8596]

Function call stack:
train_function

Answer 1

Here 是您的代码的 colab 文件。根据文档

A positive integer specifying the number of groups in which the input is split along the channel axis. Each group is convolved separately with filters / groups filters. The output is the concatenation of all the groups results along the channel axis. Input channels and filters must both be divisible by groups.

在您的代码中，我没有发现与此冲突。它应该工作。否则，它可能会出现其他问题。

keras中的组卷积

Group convolution in keras

convolution

keras

tensorflow