以下代码有问题 以下行 new_model = load_model('124446.model',custom_objects = None,compile = True) 这是代码:
import tensorflow as tf
from tensorflow.keras.models import load_model
mnist = tf.keras.datasets.mnist
(x_train,y_train), (x_test,y_test) = mnist.load_data()
x_train = tf.keras.utils.normalize(x_train,axis=1)
x_test = tf.keras.utils.normalize(x_test,axis=1)
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(128,activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(128,activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(10,activation=tf.nn.softmax))
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train,y_train,epochs=3)
tf.keras.models.save_model(model,'124446.model')
val_loss, val_acc = model.evaluate(x_test,y_test)
print(val_loss, val_acc)
new_model = load_model('124446.model', custom_objects=None, compile=True)
prediction = new_model.predict([x_test])
print(prediction)
错误是:
回溯(最近通话最近):文件 “ C:/用户/TanveerIslam/PycharmProjects/DeepLearningPractice/1.py”, 第32行,在 new_model = load_model('124446.model',custom_objects = None,compile = True)文件 “ C:\ Users \ TanveerIslam \ PycharmProjects \ DeepLearningPractice \ venv \ lib \ site-packages \ tensorflow \ python \ keras \ engine \ saving.py”, 在load_model中的第262行 sample_weight_mode = sample_weight_mode)文件“ C:\ Users \ TanveerIslam \ PycharmProjects \ DeepLearningPractice \ venv \ lib \ site-packages \ tensorflow \ python \ training \ checkpointable \ base.py”, _method_wrapper中的第426行 方法(自身,* args,** kwargs)文件“ C:\ Users \ TanveerIslam \ PycharmProjects \ DeepLearningPractice \ venv \ lib \ site-packages \ tensorflow \ python \ keras \ engine \ training.py”, 525行,正在编译 指标,self.output_names)
AttributeError:“顺序”对象没有属性“ output_names”
任何人都可以给我提供解决方案。
注意:我使用pycharm作为IDE。
答案 0 :(得分:1)
我可以通过在 load_model()
中设置 compile = False 来加载模型答案 1 :(得分:0)
如果此程序在Windows上运行,则问题在于Windows当前不支持toco-https://github.com/tensorflow/tensorflow/issues/20975
答案 2 :(得分:0)
正如@Shinva所说,将load_model函数的“ compile”属性设置为“ False”。 然后在加载模型后,分别进行编译。
from tensorflow.keras.models import save_model, load_model
save_model(model,'124446.model')
然后再次加载模型:
saved_model = load_model('124446.model', compile=False)
saved_model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
saved_model.predict([x_test])
更新:由于某些未知原因,我开始遇到与问题陈述相同的错误。尝试找到其他解决方案后,似乎直接使用“ keras”库而不是“ tensorflow.keras”可以正常工作。
我的设置是在“ Windows 10”上使用python:'3.6.7',tensorflow:'1.11.0'和keras:'2.2.4'
据我所知,可以通过三种不同的方式保存和恢复模型。只要您直接使用keras制作模型即可。
选项1:
import json
from keras.models import model_from_json, load_model
# Save Weights + Architecture
model.save_weights('model_weights.h5')
with open('model_architecture.json', 'w') as f:
f.write(model.to_json())
# Load Weights + Architecture
with open('model_architecture.json', 'r') as f:
new_model = model_from_json(f.read())
new_model.load_weights('model_weights.h5')
选项2:
from keras.models import save_model, load_model
# Creates a HDF5 file 'my_model.h5'
save_model(model, 'my_model.h5') # model, [path + "/"] name of model
# Deletes the existing model
del model
# Returns a compiled model identical to the previous one
new_model = load_model('my_model.h5')
选项3
# using model's methods
model.save("my_model.h5")
# deletes the existing model
del model
# load the saved model back
new_model = load_model('my_model.h5')
选项1要求编译才能使用。
选项2和3的语法几乎相似。
使用的代码:
1. Saving & Loading Keras Models
2. https://keras.io/getting-started/faq/#how-can-i-save-a-keras-model
答案 3 :(得分:0)
import tensorflow as tf
tf.keras.models.save_model(
model,
"epic_num_reader.model",
overwrite=True,
include_optimizer=True
)
new_model = tf.keras.models.load_model('epic_num_reader.model', custom_objects=None, compile=False)
predictions = new_model.predict(x_test)
print(predictions)
import numpy as np
print(np.argmax(predictions[0]))
plt.imshow(x_test[0],cmap=plt.cm.binary)
plt.show()