尝试在 UNET 中使用 Dice Loss
Trying to use Dice Loss with UNET
我正在尝试在 keras 网站上实施 UNET：
Image segmentation with a U-Net-like architecture
只有一个变化。使用骰子损失而不是“sparse_categorical_crossentropy”。但是，每次尝试时，都会出现不同的错误。我正在使用 Tensorflow 2.7 在 google colab 上编码。
例如，我尝试使用
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
我得到的错误：
ValueError：形状必须是等级 2 但对于 '{{node DiceLoss99/MatMul}} = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false](DiceLoss99/Reshape_1, DiceLoss99/Reshape)' 输入形状：[?], [?].
问题出在这一行：
intersection = K.sum(K.dot(targets, inputs))
我也试过这个库：
!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，我收到以下错误：
TypeError: 'Mul' Op 的输入 'y' 的 int32 类型与参数 'x'.[=55 的 float32 类型不匹配=]
其余代码与keras.io中的相同。但我在下面列出了完整性：
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)
编辑
在 segmentation_models 尝试丢失库时的详细错误消息：
这段代码的问题：
backend = kwargs['backend']
Args:
gt: ground truth 4D keras tensor (B, H, W, C) or (B, C, H, W)
pr: prediction 4D keras tensor (B, H, W, C) or (B, C, H, W)
class_weights: 1. or list of class weights, len(weights) = C
class_indexes: Optional integer or list of integers, classes to consider, if ``None`` all classes are used.
beta: f-score coefficient
smooth: value to avoid division by zero
per_image: if ``True``, metric is calculated as mean over images in batch (B),
else over whole batch
threshold: value to round predictions (use ``>`` comparison), if ``None`` prediction will not be round
Returns:
F-score in range [0, 1]
"""
Args:
gt: ground truth 4D keras tensor (B, H, W, C) or (B, C, H, W)
pr: prediction 4D keras tensor (B, H, W, C) or (B, C, H, W)
class_weights: 1. or list of class weights, len(weights) = C
class_indexes: Optional integer or list of integers, classes to consider, if ``None`` all classes are used.
beta: f-score coefficient
smooth: value to avoid division by zero
per_image: if ``True``, metric is calculated as mean over images in batch (B),
else over whole batch
threshold: value to round predictions (use ``>`` comparison), if ``None`` prediction will not be round
Returns:
F-score in range [0, 1]
"""
Args:
gt: ground truth 4D keras tensor (B, H, W, C) or (B, C, H, W)
pr: prediction 4D keras tensor (B, H, W, C) or (B, C, H, W)
class_weights: 1. or list of class weights, len(weights) = C
class_indexes: Optional integer or list of integers, classes to consider, if ``None`` all classes are used.
beta: f-score coefficient
smooth: value to avoid division by zero
per_image: if ``True``, metric is calculated as mean over images in batch (B),
else over whole batch
threshold: value to round predictions (use ``>`` comparison), if ``None`` prediction will not be round
Returns:
F-score in range [0, 1]
"""
gt, pr = gather_channels(gt, pr, indexes=class_indexes, **kwargs)
pr = round_if_needed(pr, threshold, **kwargs)
axes = get_reduce_axes(per_image, **kwargs)
# calculate score
tp = backend.sum(gt * pr, axis=axes) # the issue here
fp = backend.sum(pr, axis=axes) - tp
fn = backend.sum(gt, axis=axes) - tp
score = ((1 + beta ** 2) * tp + smooth) \
/ ((1 + beta ** 2) * tp + beta ** 2 * fn + fp + smooth)
score = average(score, per_image, class_weights, **kwargs)
return score
gt、pr 和 axis 的代码在这里：
def get_reduce_axes(per_image, **kwargs):
backend = kwargs['backend']
axes = [1, 2] if backend.image_data_format() == 'channels_last' else [2, 3]
if not per_image:
axes.insert(0, 0)
return axes
def gather_channels(*xs, indexes=None, **kwargs):
"""Slice tensors along channels axis by given indexes"""
if indexes is None:
return xs
elif isinstance(indexes, (int)):
indexes = [indexes]
xs = [_gather_channels(x, indexes=indexes, **kwargs) for x in xs]
return xs
def round_if_needed(x, threshold, **kwargs):
backend = kwargs['backend']
if threshold is not None:
x = backend.greater(x, threshold)
x = backend.cast(x, backend.floatx())
return x
您将一维向量传递给 K.dot，而 ValueError 表示 K.dot 需要二维数组。
您可以将其替换为逐元素乘法，即 intersection = K.sum(targets *inputs)
我正在尝试在 keras 网站上实施 UNET：
Image segmentation with a U-Net-like architecture
只有一个变化。使用骰子损失而不是“sparse_categorical_crossentropy”。但是，每次尝试时，都会出现不同的错误。我正在使用 Tensorflow 2.7 在 google colab 上编码。
例如，我尝试使用
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
我得到的错误：
ValueError：形状必须是等级 2 但对于 '{{node DiceLoss99/MatMul}} = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false](DiceLoss99/Reshape_1, DiceLoss99/Reshape)' 输入形状：[?], [?].
问题出在这一行：
intersection = K.sum(K.dot(targets, inputs))
我也试过这个库：
!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，我收到以下错误：
TypeError: 'Mul' Op 的输入 'y' 的 int32 类型与参数 'x'.[=55 的 float32 类型不匹配=]
其余代码与keras.io中的相同。但我在下面列出了完整性：
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)
编辑
在 segmentation_models 尝试丢失库时的详细错误消息：
这段代码的问题：
backend = kwargs['backend']
Args:
gt: ground truth 4D keras tensor (B, H, W, C) or (B, C, H, W)
pr: prediction 4D keras tensor (B, H, W, C) or (B, C, H, W)
class_weights: 1. or list of class weights, len(weights) = C
class_indexes: Optional integer or list of integers, classes to consider, if ``None`` all classes are used.
beta: f-score coefficient
smooth: value to avoid division by zero
per_image: if ``True``, metric is calculated as mean over images in batch (B),
else over whole batch
threshold: value to round predictions (use ``>`` comparison), if ``None`` prediction will not be round
Returns:
F-score in range [0, 1]
"""
Args:
gt: ground truth 4D keras tensor (B, H, W, C) or (B, C, H, W)
pr: prediction 4D keras tensor (B, H, W, C) or (B, C, H, W)
class_weights: 1. or list of class weights, len(weights) = C
class_indexes: Optional integer or list of integers, classes to consider, if ``None`` all classes are used.
beta: f-score coefficient
smooth: value to avoid division by zero
per_image: if ``True``, metric is calculated as mean over images in batch (B),
else over whole batch
threshold: value to round predictions (use ``>`` comparison), if ``None`` prediction will not be round
Returns:
F-score in range [0, 1]
"""
Args:
gt: ground truth 4D keras tensor (B, H, W, C) or (B, C, H, W)
pr: prediction 4D keras tensor (B, H, W, C) or (B, C, H, W)
class_weights: 1. or list of class weights, len(weights) = C
class_indexes: Optional integer or list of integers, classes to consider, if ``None`` all classes are used.
beta: f-score coefficient
smooth: value to avoid division by zero
per_image: if ``True``, metric is calculated as mean over images in batch (B),
else over whole batch
threshold: value to round predictions (use ``>`` comparison), if ``None`` prediction will not be round
Returns:
F-score in range [0, 1]
"""
gt, pr = gather_channels(gt, pr, indexes=class_indexes, **kwargs)
pr = round_if_needed(pr, threshold, **kwargs)
axes = get_reduce_axes(per_image, **kwargs)
# calculate score
tp = backend.sum(gt * pr, axis=axes) # the issue here
fp = backend.sum(pr, axis=axes) - tp
fn = backend.sum(gt, axis=axes) - tp
score = ((1 + beta ** 2) * tp + smooth) \
/ ((1 + beta ** 2) * tp + beta ** 2 * fn + fp + smooth)
score = average(score, per_image, class_weights, **kwargs)
return score
gt、pr 和 axis 的代码在这里：
def get_reduce_axes(per_image, **kwargs):
backend = kwargs['backend']
axes = [1, 2] if backend.image_data_format() == 'channels_last' else [2, 3]
if not per_image:
axes.insert(0, 0)
return axes
def gather_channels(*xs, indexes=None, **kwargs):
"""Slice tensors along channels axis by given indexes"""
if indexes is None:
return xs
elif isinstance(indexes, (int)):
indexes = [indexes]
xs = [_gather_channels(x, indexes=indexes, **kwargs) for x in xs]
return xs
def round_if_needed(x, threshold, **kwargs):
backend = kwargs['backend']
if threshold is not None:
x = backend.greater(x, threshold)
x = backend.cast(x, backend.floatx())
return x
您将一维向量传递给 K.dot，而 ValueError 表示 K.dot 需要二维数组。
您可以将其替换为逐元素乘法，即 intersection = K.sum(targets *inputs)