Tensorflow融合conv实现不支持分组卷积

Question

我做了一个神经网络机器学习彩色图像(3通道)。它起了作用，但现在我想试着用灰度来看我是否能提高精确度。以下是代码：

train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)
 
test_datagen = ImageDataGenerator(rescale=1. / 255)
 
train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary',
    shuffle=True)
 
validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    color_mode='grayscale',
    class_mode='binary',
    shuffle=True)
model = tf.keras.Sequential()
input_shape = (img_width, img_height, 1)
model.add(Conv2D(32, 2, input_shape=input_shape, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
 
model.add(Conv2D(32, 2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
 
model.add(Conv2D(64, 2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
 
model.add(Flatten())
model.add(Dense(128))
model.add(Dense(len(classes)))

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])
history = model.fit(train_generator,
         validation_data=validation_generator,
         epochs=EPOCHS)

您可以看到，我已经将input_shape更改为只有一个灰度通道。我收到一个错误：

Node: 'sequential_26/conv2d_68/Relu' Fused conv implementation does not support grouped convolutions for now. [[{{node sequential_26/conv2d_68/Relu}}]] [Op:__inference_train_function_48830]

知道怎么解决这个问题吗？

Answer 1

您的train_generator似乎没有colormode='grayscale'。尝试：

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary',
    colormode='grayscale',
    shuffle=True)

Answer 2

这个错误是在否定时产生的。通道与模型不同。也许由于input_shape，你已经给出了一个三维形状张量。这可能对你有帮助。)

input_shape = (img_width, img_height, 1)