[英]Single loss with Multiple output model in TF.Keras
我使用tensorflow的數據集,這樣y
是一個包含6 個張量的字典,我都在單個損失 function 中使用它,它看起來像這樣:
def CustomLoss():
def custom_loss(y_true, y_pred):
a = tf.keras.losses.binary_crossentropy(y_true['a_0'], y_pred[0]) * y_true['a_1']
b = tf.square(y_true['b_0'] - y_pred[1]) * y_true['b_1']
c = tf.abs(y_true['c_0'] - y_pred[2]) * y_true['c_1']
return a + b + c
return custom_loss
我有一個 model 有3個不同形狀的輸出。 當我編譯 model 並調用fit
方法時,我得到Value Error
model.compile(optimizer=optimizer, loss=CustomLoss())
model.fit(dataset, epochs=10)
ValueError: Found unexpected keys that do not correspond to any
Model output: dict_keys(['a_0', 'a_1', 'b_0', 'b_1', 'c_0', 'c_1']).
Expected: ['output_0', 'output_1', 'output_2']
其中output_0, 'output_1', 'output_2'
是 output 層的名稱。
我認為通過數據集中的鍵命名 output 層應該可以解決問題,但問題是我在數據集中有6 個張量,只有3 個輸出。 我知道我可以將損失 function 分配給每個 output 使用單個數據集地面實況張量,但我需要再次將至少兩個張量作為 GT 傳遞。
到目前為止,我使用了自定義訓練循環,但我更願意使用fit
方法。 我正在使用tensorflow 2.3.1
編輯:
示例 model:
inputs = x = tf.keras.layers.Input((256, 256, 3))
x = tf.keras.applications.ResNet50(include_top=False, weights=None)(x)
x1 = tf.keras.layers.Flatten()(x)
x1 = tf.keras.layers.Dense(2, name='output_1')(x1)
x2 = tf.keras.layers.Conv2D(256, 1, name='output_2')(x)
x3 = tf.keras.layers.Flatten()(x)
x3 = tf.keras.layers.Dense(64, name='output_3')(x3)
model = tf.keras.Model(inputs=inputs, outputs=[x1, x2, x3])
自定義訓練循環:
avg_loss = tf.keras.metrics.Mean('loss', dtype=tf.float32)
for epoch in range(1, epochs+1):
for batch, (images, labels) in enumerate(train_dataset):
with tf.GradientTape() as tape:
outputs = model(images, training=False)
reg_loss = tf.reduce_sum(model.losses)
pred_loss = loss(labels, outputs)
total_loss = tf.reduce_sum(pred_loss) + reg_loss
grads = tape.gradient(total_loss, model.trainable_variables)
optimizer.apply_gradients(zip(grads, model.trainable_variables))
avg_loss.update_state(total_loss)
print(f'Epoch {epoch}/{epochs} - Loss: {avg_loss.result().numpy()}')
avg_loss.reset_states()
最小的可重現代碼:
import tensorflow as tf
def CustomLoss():
def custom_loss(y_true, y_pred):
a = tf.keras.losses.binary_crossentropy(y_true['a_0'], y_pred[0]) * y_true['a_1']
b = tf.square(y_true['b_0'] - y_pred[1]) * y_true['b_1']
b = tf.reduce_sum(b, axis=(1, 2, 3))
c = tf.abs(y_true['c_0'] - y_pred[2]) * y_true['c_1']
c = tf.reduce_sum(c, axis=1)
return a + b + c
return custom_loss
dataset = tf.data.Dataset.from_tensors((
tf.random.uniform((256, 256, 3)),
{'a_0': [0., 1.], 'a_1': [1.], 'b_0': tf.random.uniform((8, 8, 256)), 'b_1': [1.], 'c_0': tf.random.uniform((64,)), 'c_1': [1.]}
))
dataset = dataset.batch(1)
inputs = x = tf.keras.layers.Input((256, 256, 3))
x = tf.keras.applications.ResNet50(include_top=False, weights=None)(x)
x1 = tf.keras.layers.Flatten()(x)
x1 = tf.keras.layers.Dense(2, name='output_1')(x1)
x2 = tf.keras.layers.Conv2D(256, 1, name='output_2')(x)
x3 = tf.keras.layers.Flatten()(x)
x3 = tf.keras.layers.Dense(64, name='output_3')(x3)
model = tf.keras.Model(inputs=inputs, outputs=[x1, x2, x3])
optimizer = tf.keras.optimizers.Adam(1e-3)
model.compile(optimizer=optimizer, loss=CustomLoss())
model.fit(dataset, epochs=1)
這是您的情況的一種方法。 我們仍將使用自定義訓練循環,但也會通過自定義此方法來利用方便的.fit
方法。 請查看文檔以獲取更多詳細信息:自定義 fit() 中發生的情況
這是一個簡單的演示,擴展您的可重現代碼。
import tensorflow as tf
# data set
dataset = tf.data.Dataset.from_tensors((
tf.random.uniform((256, 256, 3)),
{'a_0': [0., 1.], 'a_1': [1.], 'b_0': tf.random.uniform((8, 8, 256)),
'b_1': [1.], 'c_0': tf.random.uniform((64,)), 'c_1': [1.]}
))
dataset = dataset.batch(1)
# custom loss
def loss(y_true, y_pred):
a = tf.keras.losses.binary_crossentropy(y_true['a_0'], y_pred[0]) * y_true['a_1']
b = tf.square(y_true['b_0'] - y_pred[1]) * y_true['b_1']
b = tf.reduce_sum(b, axis=(1, 2, 3))
c = tf.abs(y_true['c_0'] - y_pred[2]) * y_true['c_1']
c = tf.reduce_sum(c, axis=1)
return a + b + c
定制 Model
這基本上是覆蓋將在每批數據上重復運行的train_step
。
avg_loss = tf.keras.metrics.Mean('loss', dtype=tf.float32)
class custom_fit(tf.keras.Model):
def train_step(self, data):
images, labels = data
with tf.GradientTape() as tape:
outputs = self(images, training=True) # forward pass
reg_loss = tf.reduce_sum(self.losses)
pred_loss = loss(labels, outputs)
total_loss = tf.reduce_sum(pred_loss) + reg_loss
gradients = tape.gradient(total_loss, self.trainable_variables)
self.optimizer.apply_gradients(zip(gradients, self.trainable_variables))
avg_loss.update_state(total_loss)
return {"loss": avg_loss.result()}
@property
def metrics(self):
# We list our `Metric` objects here so that `reset_states()` can be
# called automatically at the start of each epoch
# or at the start of `evaluate()`.
# If you don't implement this property, you have to call
# `reset_states()` yourself at the time of your choosing.
return [avg_loss]
構建 Model
# model
inputs = x = tf.keras.layers.Input((256, 256, 3))
x = tf.keras.applications.ResNet50(include_top=False, weights=None)(x)
x1 = tf.keras.layers.Flatten()(x)
x1 = tf.keras.layers.Dense(2, name='output_1')(x1)
x2 = tf.keras.layers.Conv2D(256, 1, name='output_2')(x)
x3 = tf.keras.layers.Flatten()(x)
x3 = tf.keras.layers.Dense(64, name='output_3')(x3)
# simply pass input and outps to the custom model
custom_model = custom_fit(inputs=[inputs],
outputs=[x1, x2, x3])
編譯和擬合
custom_model.compile(optimizer='adam')
custom_model.fit(dataset, epochs=5, verbose=2)
Epoch 1/5
1/1 - 6s - loss: 73784.0078
Epoch 2/5
1/1 - 1s - loss: 64882.8984
Epoch 3/5
1/1 - 1s - loss: 54760.2500
Epoch 4/5
1/1 - 1s - loss: 47696.7031
Epoch 5/5
1/1 - 1s - loss: 40574.6328
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.