Python 如何预处理keras.VGG19的图像?
我试图在RGB图像上训练keras VGG-19模型,当尝试前馈时,出现以下错误:Python 如何预处理keras.VGG19的图像?,python,tensorflow,keras,tf.keras,Python,Tensorflow,Keras,Tf.keras,我试图在RGB图像上训练keras VGG-19模型,当尝试前馈时,出现以下错误: ValueError: Input 0 of layer block1_conv1 is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: [224, 224, 3] 当将图像重塑为224、224、3、1以包括批次dim,然后如代码所示向前馈送时,会发生以下错误: ValueError: Dimens
ValueError: Input 0 of layer block1_conv1 is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: [224, 224, 3]
当将图像重塑为224、224、3、1以包括批次dim,然后如代码所示向前馈送时,会发生以下错误:
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]
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"
)
培训职能:
@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)
我想知道输入应该如何格式化,以便keras VGG-19实现能够接受它?您必须取消一维排序,才能将形状转换为[1,224,224,3':
当将图像重塑为224、224、3、1以包括批次尺寸时,图像批次使用了错误的尺寸-这应该是x、224、224、3,其中x是批次中图像的数量
@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)
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)