我正在嘗試在 keras 網站上實作 UNET：
使用類似 U-Net 的架構進行影像分割
只有一個變化。使用骰子損失而不是“sparse_categorical_crossentropy”。但是，每次我嘗試某些東西時，都會遇到不同的錯誤。我正在使用 Tensorflow 2.7 在 google colab 上編碼。
例如，我嘗試使用
def DiceLoss(targets, inputs, smooth=1e-6):
#flatten label and prediction tensors
inputs = K.flatten(inputs)
targets = K.flatten(targets)
intersection = K.sum(K.dot(targets, inputs))
dice = (2*intersection smooth) / (K.sum(targets) K.sum(inputs) smooth)
return 1 - dice
我得到的錯誤：
ValueError: Shape must be rank 2 but is rank 1 for '{{node DiceLoss99/MatMul}} = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false](DiceLoss99/Reshape_1, DiceLoss99/Reshape)' 輸入形狀： [?], [?]。
問題出在這一行：
intersection = K.sum(K.dot(targets, inputs))
我也試過這個庫：
!pip install git https://github.com/qubvel/segmentation_models
# define optomizer
n_classes=3
LR = 0.0001
optim = keras.optimizers.Adam(LR)
dice_loss_sm = sm.losses.DiceLoss(class_weights=K.ones_like(n_classes))
但是，我收到以下錯誤：
型別錯誤：“Mul”操作的輸入“y”的型別為 int32，與引數“x”的 float32 型別不匹配。
其余代碼與 keras.io 中的相同。但為了完整起見，我在下面列出了：
from tensorflow.keras import layers
def get_model(img_size, num_classes):
inputs = keras.Input(shape=img_size (3,))
### [First half of the network: downsampling inputs] ###
# Entry block
x = layers.Conv2D(32, 3, strides=2, padding="same")(inputs)
x = layers.BatchNormalization()(x)
x = layers.Activation("relu")(x)
previous_block_activation = x # Set aside residual
# Blocks 1, 2, 3 are identical apart from the feature depth.
for filters in [64, 128, 256]:
x = layers.Activation("relu")(x)
x = layers.SeparableConv2D(filters, 3, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.Activation("relu")(x)
x = layers.SeparableConv2D(filters, 3, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.MaxPooling2D(3, strides=2, padding="same")(x)
# Project residual
residual = layers.Conv2D(filters, 1, strides=2, padding="same")(
previous_block_activation
)
x = layers.add([x, residual]) # Add back residual
previous_block_activation = x # Set aside next residual
### [Second half of the network: upsampling inputs] ###
for filters in [256, 128, 64, 32]:
x = layers.Activation("relu")(x)
x = layers.Conv2DTranspose(filters, 3, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.Activation("relu")(x)
x = layers.Conv2DTranspose(filters, 3, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.UpSampling2D(2)(x)
# Project residual
residual = layers.UpSampling2D(2)(previous_block_activation)
residual = layers.Conv2D(filters, 1, padding="same")(residual)
x = layers.add([x, residual]) # Add back residual
previous_block_activation = x # Set aside next residual
# Add a per-pixel classification layer
outputs = layers.Conv2D(num_classes, 3, activation="softmax", padding="same")(x)
# Define the model
model = keras.Model(inputs, outputs)
return model
# Free up RAM in case the model definition cells were run multiple times
keras.backend.clear_session()
# Build model
model = get_model(img_size, num_classes)
model.summary()
# Configure the model for training.
# We use the "sparse" version of categorical_crossentropy
# because our target data is integers.
# notice I changed the lose the dice loss instead of sparse_categorical_crossentropy
model.compile(optimizer="rmsprop", loss="sparse_categorical_crossentropy")
callbacks = [
keras.callbacks.ModelCheckpoint("oxford_segmentation.h5", save_best_only=True)
]
# Train the model, doing validation at the end of each epoch.
epochs = 15
model.fit(train_gen, epochs=epochs, validation_data=val_gen, callbacks=callbacks)
uj5u.com熱心網友回復：
您將一維向量傳遞給K.dot，而 ValueError 則表示K.dot需要二維陣列。
您可以將其替換為逐元素乘法，即 intersection = K.sum(targets *inputs)
轉載請註明出處，本文鏈接：https://www.uj5u.com/ruanti/401999.html