如何在 Keras/tf2.0 自定义损失函数中收集与真实标签不对应的 y_pred 元素？
How do you gather the elements of y_pred that do not correspond to the true label in a Keras/tf2.0 custom loss function?
下面是我想做的 numpy 中的一个简单示例：
import numpy as np
y_true = np.array([0,0,1])
y_pred = np.array([0.1,0.2,0.7])
yc = (1-y_true).astype('bool')
desired = y_pred[yc]
>>> desired
>>> array([0.1, 0.2])
所以ground truth对应的预测是0.7，我想对一个包含y_pred所有元素的数组进行操作，除了ground truth元素
我不确定如何在 Keras 中完成这项工作。这是损失函数中问题的一个工作示例。现在 'desired' 没有完成任何事情，但这就是我需要处理的事情：
# using tensorflow 2.0.0 and keras 2.3.1
import tensorflow.keras.backend as K
import tensorflow as tf
from tensorflow.keras.layers import Input,Dense,Flatten
from tensorflow.keras.models import Model
from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# Normalize data.
x_train = x_train.astype('float32') / 255
x_test = x_test.astype('float32') / 255
# Convert class vectors to binary class matrices.
y_train = tf.keras.utils.to_categorical(y_train, 10)
y_test = tf.keras.utils.to_categorical(y_test, 10)
input_shape = x_train.shape[1:]
x_in = Input((input_shape))
x = Flatten()(x_in)
x = Dense(256,'relu')(x)
x = Dense(256,'relu')(x)
x = Dense(256,'relu')(x)
out = Dense(10,'softmax')(x)
def loss(y_true,y_pred):
yc = tf.math.logical_not(kb.cast(y_true, 'bool'))
desired = tf.boolean_mask(y_pred,yc,axis = 1) #Remove and it runs
CE = tf.keras.losses.categorical_crossentropy(
y_true,
y_pred)
L = CE
return L
model = Model(x_in,out)
model.compile('adam',loss = loss,metrics = ['accuracy'])
model.fit(x_train,y_train)
我最终遇到错误
ValueError: Shapes (10,) and (None, None) are incompatible
其中 10 是类别数。最终目的是实现这个：ComplementEntropy
在 Keras 中，我的问题似乎是第 26-28 行。
您可以从 Boolean_mask 中删除 axis=1，它将 运行。坦率地说，我不明白为什么你需要 axis=1 在这里。
def loss(y_true,y_pred):
yc = tf.math.logical_not(K.cast(y_true, 'bool'))
print(yc.shape)
desired = tf.boolean_mask(y_pred, yc) #Remove axis=1 and it runs
CE = tf.keras.losses.categorical_crossentropy(
y_true,
y_pred)
L = CE
return L
这可能就是发生的事情。你有 y_pred，这是一个二维张量 (N=2)。然后你有一个 2D 掩码 (K=2)。但是有这个条件K + axis <= N。如果你通过 axis=1 则失败。
使用 thushv89 的回答，这里是我如何根据参考论文在 LeNet 上实现 COT 的完整代码。一个技巧是我实际上并没有在两个目标之间来回翻转，而是只有一个随机权重翻转 s。
# using tensorflow 2.0.0 and keras 2.3.1
import tensorflow.keras.backend as kb
import tensorflow as tf
from tensorflow.keras.layers import Conv2D, Input, Dense,Flatten,AveragePooling2D,GlobalAveragePooling2D
from tensorflow.keras.models import Model
from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# Normalize data.
x_train = x_train.astype('float32') / 255
x_test = x_test.astype('float32') / 255
#exapnd dims to fit chn format
x_train = np.expand_dims(x_train,axis=3)
x_test = np.expand_dims(x_test,axis=3)
# Convert class vectors to binary class matrices.
y_train = tf.keras.utils.to_categorical(y_train, 10)
y_test = tf.keras.utils.to_categorical(y_test, 10)
input_shape = x_train.shape[1:]
x_in = Input((input_shape))
act = 'tanh'
x = Conv2D(32, (5, 5), activation=act, padding='same',strides = 1)(x_in)
x = AveragePooling2D((2, 2),strides = (2,2))(x)
x = Conv2D(16, (5, 5), activation=act)(x)
x = AveragePooling2D((2, 2),strides = (2,2))(x)
conv_out = Flatten()(x)
z = Dense(120,activation = act)(conv_out)#120
z = Dense(84,activation = act)(z)#84
last = Dense(10,activation = 'softmax')(z)
model = Model(x_in,last)
def loss(y_true,y_pred, axis=-1):
s = kb.round(tf.random.uniform( (1,), minval=0, maxval=1, dtype=tf.dtypes.float32))
s_ = 1 - s
y_pred = y_pred + 1e-8
yg = kb.max(y_pred,axis=1)
yc = tf.math.logical_not(kb.cast(y_true, 'bool'))
yp_c = tf.boolean_mask(y_pred, yc)
ygc_ = 1/(1-yg+1e-8)
ygc_ = kb.expand_dims(ygc_,axis=1)
Px = yp_c*ygc_ +1e-8
COT = kb.mean(Px*kb.log(Px),axis=1)
CE = -kb.mean(y_true*kb.log(y_pred),axis=1)
L = s*CE +s_*(1/(10-1))*COT
return L
model.compile(loss=loss,
optimizer='adam', metrics=['accuracy'])
model.fit(x_train,y_train,epochs=20,batch_size = 128,validation_data= (x_test,y_test))
pred = model.predict(x_test)
pred_label = np.argmax(pred,axis=1)
label = np.argmax(y_test,axis=1)
cor = (pred_label == label).sum()
acc = print('acc:',cor/label.shape[0])
下面是我想做的 numpy 中的一个简单示例：
import numpy as np
y_true = np.array([0,0,1])
y_pred = np.array([0.1,0.2,0.7])
yc = (1-y_true).astype('bool')
desired = y_pred[yc]
>>> desired
>>> array([0.1, 0.2])
所以ground truth对应的预测是0.7，我想对一个包含y_pred所有元素的数组进行操作，除了ground truth元素
我不确定如何在 Keras 中完成这项工作。这是损失函数中问题的一个工作示例。现在 'desired' 没有完成任何事情，但这就是我需要处理的事情：
# using tensorflow 2.0.0 and keras 2.3.1
import tensorflow.keras.backend as K
import tensorflow as tf
from tensorflow.keras.layers import Input,Dense,Flatten
from tensorflow.keras.models import Model
from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# Normalize data.
x_train = x_train.astype('float32') / 255
x_test = x_test.astype('float32') / 255
# Convert class vectors to binary class matrices.
y_train = tf.keras.utils.to_categorical(y_train, 10)
y_test = tf.keras.utils.to_categorical(y_test, 10)
input_shape = x_train.shape[1:]
x_in = Input((input_shape))
x = Flatten()(x_in)
x = Dense(256,'relu')(x)
x = Dense(256,'relu')(x)
x = Dense(256,'relu')(x)
out = Dense(10,'softmax')(x)
def loss(y_true,y_pred):
yc = tf.math.logical_not(kb.cast(y_true, 'bool'))
desired = tf.boolean_mask(y_pred,yc,axis = 1) #Remove and it runs
CE = tf.keras.losses.categorical_crossentropy(
y_true,
y_pred)
L = CE
return L
model = Model(x_in,out)
model.compile('adam',loss = loss,metrics = ['accuracy'])
model.fit(x_train,y_train)
我最终遇到错误
ValueError: Shapes (10,) and (None, None) are incompatible
其中 10 是类别数。最终目的是实现这个：ComplementEntropy 在 Keras 中，我的问题似乎是第 26-28 行。
您可以从 Boolean_mask 中删除 axis=1，它将 运行。坦率地说，我不明白为什么你需要 axis=1 在这里。
def loss(y_true,y_pred):
yc = tf.math.logical_not(K.cast(y_true, 'bool'))
print(yc.shape)
desired = tf.boolean_mask(y_pred, yc) #Remove axis=1 and it runs
CE = tf.keras.losses.categorical_crossentropy(
y_true,
y_pred)
L = CE
return L
这可能就是发生的事情。你有 y_pred，这是一个二维张量 (N=2)。然后你有一个 2D 掩码 (K=2)。但是有这个条件K + axis <= N。如果你通过 axis=1 则失败。
使用 thushv89 的回答，这里是我如何根据参考论文在 LeNet 上实现 COT 的完整代码。一个技巧是我实际上并没有在两个目标之间来回翻转，而是只有一个随机权重翻转 s。
# using tensorflow 2.0.0 and keras 2.3.1
import tensorflow.keras.backend as kb
import tensorflow as tf
from tensorflow.keras.layers import Conv2D, Input, Dense,Flatten,AveragePooling2D,GlobalAveragePooling2D
from tensorflow.keras.models import Model
from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# Normalize data.
x_train = x_train.astype('float32') / 255
x_test = x_test.astype('float32') / 255
#exapnd dims to fit chn format
x_train = np.expand_dims(x_train,axis=3)
x_test = np.expand_dims(x_test,axis=3)
# Convert class vectors to binary class matrices.
y_train = tf.keras.utils.to_categorical(y_train, 10)
y_test = tf.keras.utils.to_categorical(y_test, 10)
input_shape = x_train.shape[1:]
x_in = Input((input_shape))
act = 'tanh'
x = Conv2D(32, (5, 5), activation=act, padding='same',strides = 1)(x_in)
x = AveragePooling2D((2, 2),strides = (2,2))(x)
x = Conv2D(16, (5, 5), activation=act)(x)
x = AveragePooling2D((2, 2),strides = (2,2))(x)
conv_out = Flatten()(x)
z = Dense(120,activation = act)(conv_out)#120
z = Dense(84,activation = act)(z)#84
last = Dense(10,activation = 'softmax')(z)
model = Model(x_in,last)
def loss(y_true,y_pred, axis=-1):
s = kb.round(tf.random.uniform( (1,), minval=0, maxval=1, dtype=tf.dtypes.float32))
s_ = 1 - s
y_pred = y_pred + 1e-8
yg = kb.max(y_pred,axis=1)
yc = tf.math.logical_not(kb.cast(y_true, 'bool'))
yp_c = tf.boolean_mask(y_pred, yc)
ygc_ = 1/(1-yg+1e-8)
ygc_ = kb.expand_dims(ygc_,axis=1)
Px = yp_c*ygc_ +1e-8
COT = kb.mean(Px*kb.log(Px),axis=1)
CE = -kb.mean(y_true*kb.log(y_pred),axis=1)
L = s*CE +s_*(1/(10-1))*COT
return L
model.compile(loss=loss,
optimizer='adam', metrics=['accuracy'])
model.fit(x_train,y_train,epochs=20,batch_size = 128,validation_data= (x_test,y_test))
pred = model.predict(x_test)
pred_label = np.argmax(pred,axis=1)
label = np.argmax(y_test,axis=1)
cor = (pred_label == label).sum()
acc = print('acc:',cor/label.shape[0])