Tensorflow Fused-conv实现不支持分组卷积

Question

我对彩色图像(3个通道(进行了神经网络机器学习。它起作用了，但现在我想尝试用灰度来做，看看我是否可以提高准确性。这是代码：

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更改为具有1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

当编号通道与模型不同时，会出现此错误。也许是因为input_shape，你已经给出了一个三维形状张量。这可能对您有所帮助。：(

input_shape = (img_width, img_height, 1)

Answer 3

如果您正在处理彩色图像，请添加

color_mode='grayscale' in the ImageDataGenerator

它对我有用！