尝试加载我训练有素的Keras模型以进行进一步推断时
self.model = tf.keras.models.load_model(filepath=weight_url, custom_objects={
'dice_coef': dice_coef,
'iou_coef': iou_coef,
'bce_dice_coef': bce_dice_coef,
})
我收到以下错误。这三个函数与我用来训练模型的函数相同，权重URL正确。错误消息什么都没告诉我。
file "/home/long/Desktop/bachelor-thesis/unet/pipeline.py", line 344, in <module>
binary.inference_blood_cell_unet()
File "/home/long/Desktop/bachelor-thesis/unet/pipeline.py", line 305, in inference_blood_cell_unet
self.blood_cell_unet = UNet(weight_url=self.blood_cell_final_name, class_weights=self.blut_koerperchen_classweights, num_classes=2)
File "/home/long/Desktop/bachelor-thesis/unet/model.py", line 39, in __init__
'bce_dice_coef': bce_dice_coef,
File "/home/long/Desktop/bachelor-thesis/venv/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/save.py", line 146, in load_model
return hdf5_format.load_model_from_hdf5(filepath, custom_objects, compile)
File "/home/long/Desktop/bachelor-thesis/venv/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/hdf5_format.py", line 193, in load_model_from_hdf5
model._make_train_function()
File "/home/long/Desktop/bachelor-thesis/venv/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 2116, in _make_train_function
params=self._collected_trainable_weights, loss=self.total_loss)
File "/home/long/Desktop/bachelor-thesis/venv/lib/python3.7/site-packages/tensorflow_core/python/keras/optimizer_v2/optimizer_v2.py", line 500, in get_updates
grads = self.get_gradients(loss, params)
File "/home/long/Desktop/bachelor-thesis/venv/lib/python3.7/site-packages/tensorflow_core/python/keras/optimizer_v2/optimizer_v2.py", line 391, in get_gradients
grads = gradients.gradients(loss, params)
File "/home/long/Desktop/bachelor-thesis/venv/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_impl.py", line 158, in gradients
unconnected_gradients)
File "/home/long/Desktop/bachelor-thesis/venv/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py", line 550, in _GradientsHelper
gradient_uid)
File "/home/long/Desktop/bachelor-thesis/venv/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py", line 166, in _DefaultGradYs
with _maybe_colocate_with(y.op, gradient_uid, colocate_gradients_with_ops):
AttributeError: 'NoneType' object has no attribute 'op'
以下是我的代码如何构建模型：
import tensorflow as tf
from tensorflow.keras.callbacks import ModelCheckpoint
from tensorflow.keras.layers import Input, Conv2D, BatchNormalization, LeakyReLU, Dropout, MaxPooling2D, Conv2DTranspose
from tensorflow.keras.layers import concatenate
from tensorflow.keras.optimizers import Adam
from unet.metrics import dice_coef, iou_coef, cce_dice_coef, weighted_loss, bce_dice_coef
fil_coef = 4
class UNet(UNetBase, DataHandlingBase):
def __init__(self,
class_weights,
weight_url=None,
width=256,
height=256,
channel=3,
learning_rate=0.0005,
num_classes=2,
alpha=0.01,
dropout_rate=0.25):
super().__init__(weight_url, width, height, channel, learning_rate, num_classes, alpha, dropout_rate)
self.class_weights = class_weights
if self.num_classes > 2:
self.loss_function = weighted_loss(cce_dice_coef, weights_list=self.class_weights)
elif self.num_classes == 2:
self.loss_function = bce_dice_coef
else:
raise Exception("Invalid num class: ", self.num_classes)
if weight_url:
self.model = tf.keras.models.load_model(filepath=weight_url, custom_objects={
'dice_coef': dice_coef,
'iou_coef': iou_coef,
'bce_dice_coef': bce_dice_coef,
'loss_function': self.loss_function
})
else:
model_input = Input((self.height, self.width, self.channel))
c1 = Conv2D(filters=16 * fil_coef, kernel_size=(3, 3), padding='same')(model_input)
c1 = BatchNormalization()(c1)
c1 = LeakyReLU(self.alpha)(c1)
c1 = Dropout(self.dropout_rate)(c1)
c1 = Conv2D(filters=16 * fil_coef, kernel_size=(3, 3), padding='same')(c1)
...
c9 = BatchNormalization()(c9)
c9 = LeakyReLU(self.alpha)(c9)
c9 = Dropout(self.dropout_rate)(c9)
if self.num_classes == 2:
output = Conv2D(1, kernel_size=(1, 1), activation='sigmoid')(c9)
else:
output = Conv2D(self.num_classes, kernel_size=(1, 1), activation='softmax')(c9)
self.model = tf.keras.Model(inputs=[model_input], outputs=[output])
self.reinitialize()
def reinitialize(self):
if self.num_classes > 2:
self.model.compile(optimizer=Adam(lr=self.learning_rate),
loss=self.loss_function,
metrics=[dice_coef, iou_coef])
else:
self.model.compile(optimizer=Adam(lr=self.learning_rate),
loss=self.loss_function,
metrics=[dice_coef, iou_coef],
class_weight=self.class_weights)
def fit(self, X, Y, x=None, y=None,
batch_size=params["batch_size"],
epochs=params["epochs"],
validation_split=params["validation_split"],
checkpoint_path="temp/models/model-{epoch:02d}-{val_loss:.2f}.h5",
patience=params["patience"],
min_delta=params["min_delta"]):
checkpoint = ModelCheckpoint(checkpoint_path,
verbose=0,
save_best_only=False,
monitor='val_loss',
mode='auto')
if x is None and y is None:
history = self.model.fit(X, Y,
validation_split=validation_split,
batch_size=batch_size,
epochs=epochs,
shuffle=True,
callbacks=[checkpoint])
return history
elif x is not None and y is not None:
history = self.model.fit(X, Y,
verbose=0,
steps_per_epoch=X.shape[0] // batch_size,
validation_data=[x, y],
validation_steps=x.shape[0] // batch_size,
batch_size=batch_size,
epochs=epochs,
shuffle=True)
return history
def save_weights(self, url):
self.model.save(url)
def predict(self, X):
return self.model.predict(X)
def summary(self):
log.info(f"Learning rate {self.learning_rate} Alpha {self.alpha} Dropout Rate {self.dropout_rate}")
self.model.summary()
以下是我的损失函数的编码方式：
import tensorflow as tf
import tensorflow.keras.backend as K
def weighted_loss(original_loss_function, weights_list):
"""
Author: https://stackoverflow.com/questions/51793737/custom-loss-function-for-u-net-in-keras-using-class-weights-class-weight-not
"""
def loss_function(true, pred):
axis = -1 # if channels last
# axis= 1 #if channels first
# argmax returns the index of the element with the greatest value
# done in the class axis, it returns the class index
class_selectors = tf.cast(K.argmax(true, axis=axis), tf.int32)
# if your loss is sparse, use only true as classSelectors
# considering weights are ordered by class, for each class
# true(1) if the class index is equal to the weight index
class_selectors = [K.equal(i, class_selectors) for i in range(len(weights_list))]
# casting boolean to float for calculations
# each tensor in the list contains 1 where ground true class is equal to its index
# if you sum all these, you will get a tensor full of ones.
class_selectors = [K.cast(x, K.floatx()) for x in class_selectors]
# for each of the selections above, multiply their respective weight
weights = [sel * w for sel, w in zip(class_selectors, weights_list)]
# sums all the selections
# result is a tensor with the respective weight for each element in predictions
weight_multiplier = weights[0]
for i in range(1, len(weights)):
weight_multiplier = weight_multiplier + weights[i]
# make sure your originalLossFunc only collapses the class axis
# you need the other axes intact to multiply the weights tensor
loss = original_loss_function(true, pred)
loss = loss * weight_multiplier
return loss
return loss_function
@tf.function
def cce_iou_coef(y_true, y_pred, smooth=1, cat_weight=1, iou_weight=1):
return cat_weight * K.categorical_crossentropy(y_true, y_pred) + iou_weight * log_iou_coef(y_true, y_pred, smooth)
@tf.function
def cce_dice_coef(y_true, y_pred, smooth=1, cat_weight=1, dice_weight=1):
return cat_weight * K.categorical_crossentropy(y_true, y_pred) + dice_weight * log_dice_coef(y_true, y_pred, smooth)
@tf.function
def bce_iou_coef(y_true, y_pred, smooth=1, cat_weight=1, iou_weight=1):
return cat_weight * K.binary_crossentropy(y_true, y_pred) + iou_weight * log_iou_coef(y_true, y_pred, smooth)
@tf.function
def bce_dice_coef(y_true, y_pred, smooth=1, cat_weight=1, dice_weight=1):
return cat_weight * K.binary_crossentropy(y_true, y_pred) + dice_weight * log_dice_coef(y_true, y_pred, smooth)
@tf.function
def log_iou_coef(y_true, y_pred, smooth=1):
return - K.log(iou_coef(y_true, y_pred, smooth))
@tf.function
def log_dice_coef(y_true, y_pred, smooth=1):
return -K.log(dice_coef(y_true, y_pred, smooth))
@tf.function
def iou_coef(y_true, y_pred, smooth=1):
intersection = K.sum(K.abs(y_true * y_pred), axis=-1)
union = K.sum(y_true, axis=-1) + K.sum(y_pred, axis=-1) - intersection
iou = K.mean((intersection + smooth) / (union + smooth), axis=0)
return iou
@tf.function
def dice_coef(y_true, y_pred, smooth=1):
intersection = K.sum(y_true * y_pred, axis=-1)
union = K.sum(y_true, axis=-1) + K.sum(y_pred, axis=-1)
dice = K.mean((2. * intersection + smooth) / (union + smooth), axis=0)
return dice
在我训练了二进制模型，将其保存并再次加载以进行推断之后，发生了错误。如您所见，为推理而导入的损失函数在训练阶段是相同的。所以我不太明白为什么会出现错误。而且我也不明白该错误意味着什么。
答案 0 :(得分：3)
您可以在load_model调用中尝试使用compile = False参数。这将删除与优化器和损失函数有关的所有元数据，并且由于您具有重新初始化的函数，并且如果您不需要从上次停止的地方对其进行训练，那么我猜这将不是问题。
正如您所说的，它可以与compile = False一起使用，我认为问题可能出在您的自定义函数（用于损耗/优化器等）中，我无法指出问题的确切原因，可以尝试tf。而不是tf.keras.backend。如果需要的话。