tensorflow中负维度大小错误

Question

所以我有2个图像，img1和img2都有shape=(20,20)，其中我expand_dims到(1,20,20)1是批量大小并将它们提供给网络，但我得到以下错误:

ValueError: Negative dimension size caused by subtracting 3 from 1 for '{{node conv2d/Conv2D}} = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], explicit_paddings=[], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true](Placeholder, conv2d/Conv2D/ReadVariableOp)' with input shapes: [?,1,20,20], [3,3,20,32]. ```

def mean_squared_error(y_true, y_pred):
return tf.keras.metrics.mean_squared_error(y_true, y_pred)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=(1,20,20)))
model.add(Conv2D(1, kernel_size=(3, 3),
activation='relu'))

model.compile(optimizer='adam', loss=mean_squared_error, metrics=[mean_squared_error, 'accuracy'])

# Train

model.fit(img1, img2)

Answer 1

卷积层减少了输入的维度，但是IIUC，您试图将mse应用于模型的输出和img2。所以试试这样写:

import tensorflow as tf
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(32, kernel_size=(2, 2),
activation='relu',
input_shape=(20, 20, 1)))
model.add(tf.keras.layers.Conv2DTranspose(1, kernel_size=(2, 2),
activation='relu'))
model.compile(optimizer='adam', loss='mse', metrics=['mae'])
# Train
img1 = tf.random.normal((1, 20, 20))
img2 = tf.random.normal((1, 20, 20))
model.fit(img1, img2)