节点'training/Adam/gradients/gradients/conv5_block3_3_bn/cond_grad/StatelessIf'

如何解决节点'training/Adam/gradients/gradients/conv5_block3_3_bn/cond_grad/StatelessIf'

img_height,img_width = 32,32
base_model = ResNet50(weights = 'imagenet',include_top = False,input_shape =(img_height,img_width,3))
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dropout(0.7)(x)
predictions = Dense(num_classes,activation = 'softmax')(x)
model = Model(inputs = base_model.input,outputs = predictions)
model.compile(optimizer = Adam(),lr = 0.0001,loss = 'categorical_crossentropy',metrics = ['accuracy']) 
model.fit(X_train,y_train,epochs = 20,batch_size = 128)

我正在尝试使用 Resnet 在 CIFAR-10 数据集上执行 image_classification 任务。我正在使用带有 TensorFlow 2.5.0 版的 colab CPU。

我在“model.fit”行中收到此错误：

InvalidArgumentError：节点“training/Adam/gradients/gradients/conv5_block3_3_bn/cond_grad/StatelessIf”：连接到具有 3 个输出的源节点 conv5_block3_3_bn/cond 的无效输出 3。尝试使用 tf.compat.v1.experimental.output_all_intermediates(True)。

解决方法

我可以使用 TF2.5 在 colab 上执行代码而不会出现任何问题

import tensorflow as tf
print(tf.__version__)
from tensorflow.keras.applications import ResNet50
from tensorflow.keras import Input,Model
from tensorflow.keras.layers import GlobalAveragePooling2D,Dropout,Dense
from tensorflow.keras.optimizers import Adam
(X_train,y_train),(X_test,y_test) = tf.keras.datasets.cifar10.load_data()

X_train = X_train.astype("float32") / 255.0
X_test = X_test.astype("float32") / 255.0
y_train = tf.keras.utils.to_categorical(y_train,10)
y_test = tf.keras.utils.to_categorical(y_test,10)
  
num_classes = 10
img_height,img_width = 32,32
base_model = ResNet50(weights = 'imagenet',include_top = False,input_shape =(img_height,img_width,3))
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dropout(0.7)(x)
predictions = Dense(num_classes,activation = 'softmax')(x)
model = Model(inputs = base_model.input,outputs = predictions)
model.compile(optimizer = Adam(),loss = 'categorical_crossentropy',metrics = ['accuracy']) 
model.fit(X_train,y_train,epochs = 5,batch_size = 128)

输出：

2.5.0
Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz
170500096/170498071 [==============================] - 6s 0us/step
Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5
94773248/94765736 [==============================] - 2s 0us/step
Epoch 1/5
391/391 [==============================] - 72s 72ms/step - loss: 2.1970 - accuracy: 0.3832
Epoch 2/5
391/391 [==============================] - 27s 69ms/step - loss: 1.5985 - accuracy: 0.5207
Epoch 3/5
391/391 [==============================] - 28s 71ms/step - loss: 1.4202 - accuracy: 0.5837
Epoch 4/5
391/391 [==============================] - 27s 69ms/step - loss: 1.1143 - accuracy: 0.6464
Epoch 5/5
391/391 [==============================] - 27s 70ms/step - loss: 0.9299 - accuracy: 0.6993
<tensorflow.python.keras.callbacks.History at 0x7f7c8c112350>