如何预处理 keras 的图像.VGG19?

Question

我正在尝试在RGB图像上训练keras VGG-19模型，当尝试转发时会出现此错误：

ValueError: Input 0 of layer block1_conv1 is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: [224, 224, 3]

将图像整形为 (224， 224， 3， 1( 以包含批量 dim，然后按代码所示向前馈送时，会发生此错误：

ValueError: Dimensions must be equal, but are 1 and 3 for '{{node BiasAdd}} = BiasAdd[T=DT_FLOAT, data_format="NHWC"](strided_slice, Const)' with input shapes: [64,224,224,1], [3]

for idx in tqdm(range(train_data.get_ds_size() // batch_size)):
# train step
batch = train_data.get_train_batch()
for sample, label in zip(batch[0], batch[1]):
sample = tf.reshape(sample, [*sample.shape, 1])
label = tf.reshape(label, [*label.shape, 1])
train_step(idx, sample, label)

vgg初始化为：

vgg = tf.keras.applications.VGG19(
include_top=True,
weights=None,
input_tensor=None,
input_shape=[224, 224, 3],
pooling=None,
classes=1000,
classifier_activation="softmax"
)

训练功能：

@tf.function
def train_step(idx, sample, label):
with tf.GradientTape() as tape:
# preprocess for vgg-19
sample = tf.image.resize(sample, (224, 224))
sample = tf.keras.applications.vgg19.preprocess_input(sample * 255)
predictions = vgg(sample, training=True)
# mean squared error in prediction
loss = tf.keras.losses.MSE(label, predictions)
# apply gradients
gradients = tape.gradient(loss, vgg.trainable_variables)
optimizer.apply_gradients(zip(gradients, vgg.trainable_variables))
# update metrics
train_loss(loss)
train_accuracy(vgg, predictions)

我想知道应该如何格式化输入，以便 keras VGG-19 实现接受它？

Answer 1

您必须解压缩一个维度才能将形状变成[1, 224, 224, 3'：

for idx in tqdm(range(train_data.get_ds_size() // batch_size)):
# train step
batch = train_data.get_train_batch()
for sample, label in zip(batch[0], batch[1]):
sample = tf.reshape(sample, [1, *sample.shape])  # added the 1 here
label = tf.reshape(label, [*label.shape, 1])
train_step(idx, sample, label)

Answer 2

您对图像批次使用了错误的尺寸，"当将图像整形为 (224， 224， 3， 1( 以包含批量 dim" -- 这应该是 (x， 224， 224， 3(，其中x是批中图像的数量。