训练后,我保存了两个 Keras 整个模型和唯一的权重使用
model.save_weights(MODEL_WEIGHTS) and model.save(MODEL_NAME)
模型和权重保存成功,没有错误。我可以简单地使用 model.load_weights 成功加载权重,它们很好,但是当我尝试通过 load_model 加载保存模型时,我收到错误。
File "C:/Users/Rizwan/model_testing/model_performance.py", line 46, in <module>
Model2 = load_model('nasnet_RS2.h5',custom_objects={'euc_dist_keras': euc_dist_keras})
File "C:\Users\Rizwan\AppData\Roaming\Python\Python36\site-packages\keras\engine\saving.py", line 419, in load_model
model = _deserialize_model(f, custom_objects, compile)
File "C:\Users\Rizwan\AppData\Roaming\Python\Python36\site-packages\keras\engine\saving.py", line 321, in _deserialize_model
optimizer_weights_group['weight_names']]
File "C:\Users\Rizwan\AppData\Roaming\Python\Python36\site-packages\keras\engine\saving.py", line 320, in <listcomp>
n.decode('utf8') for n in
AttributeError: 'str' object has no attribute 'decode'
我从未收到此错误,我曾经成功加载任何模型。我正在使用带有 tensorflow 后端的 Keras 2.2.4。蟒蛇 3.6。我的培训代码是:
from keras_preprocessing.image import ImageDataGenerator
from keras import backend as K
from keras.models import load_model
from keras.callbacks import ReduceLROnPlateau, TensorBoard,
ModelCheckpoint,EarlyStopping
import pandas as pd
MODEL_NAME = "nasnet_RS2.h5"
MODEL_WEIGHTS = "nasnet_RS2_weights.h5"
def euc_dist_keras(y_true, y_pred):
return K.sqrt(K.sum(K.square(y_true - y_pred), axis=-1, keepdims=True))
def main():
# Here, we initialize the "NASNetMobile" model type and customize the final
#feature regressor layer.
# NASNet is a neural network architecture developed by Google.
# This architecture is specialized for transfer learning, and was discovered via Neural Architecture Search.
# NASNetMobile is a smaller version of NASNet.
model = NASNetMobile()
model = Model(model.input, Dense(1, activation='linear', kernel_initializer='normal')(model.layers[-2].output))
# model = load_model('current_best.hdf5', custom_objects={'euc_dist_keras': euc_dist_keras})
# This model will use the "Adam" optimizer.
model.compile("adam", euc_dist_keras)
lr_callback = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=5, min_lr=0.003)
# This callback will log model stats to Tensorboard.
tb_callback = TensorBoard()
# This callback will checkpoint the best model at every epoch.
mc_callback = ModelCheckpoint(filepath='current_best_mem3.h5', verbose=1, save_best_only=True)
es_callback=EarlyStopping(monitor='val_loss', min_delta=0, patience=4, verbose=0, mode='auto', baseline=None, restore_best_weights=True)
# This is the train DataSequence.
# These are the callbacks.
#callbacks = [lr_callback, tb_callback,mc_callback]
callbacks = [lr_callback, tb_callback,es_callback]
train_pd = pd.read_csv("./train3.txt", delimiter=" ", names=["id", "label"], index_col=None)
test_pd = pd.read_csv("./val3.txt", delimiter=" ", names=["id", "label"], index_col=None)
# train_pd = pd.read_csv("./train2.txt",delimiter=" ",header=None,index_col=None)
# test_pd = pd.read_csv("./val2.txt",delimiter=" ",header=None,index_col=None)
#model.summary()
batch_size=32
datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = datagen.flow_from_dataframe(dataframe=train_pd,
directory="./images", x_col="id", y_col="label",
has_ext=True,
class_mode="other", target_size=(224, 224),
batch_size=batch_size)
valid_generator = datagen.flow_from_dataframe(dataframe=test_pd, directory="./images", x_col="id", y_col="label",
has_ext=True, class_mode="other", target_size=(224, 224),
batch_size=batch_size)
STEP_SIZE_TRAIN = train_generator.n // train_generator.batch_size
STEP_SIZE_VALID = valid_generator.n // valid_generator.batch_size
model.fit_generator(generator=train_generator,
steps_per_epoch=STEP_SIZE_TRAIN,
validation_data=valid_generator,
validation_steps=STEP_SIZE_VALID,
callbacks=callbacks,
epochs=20)
# we save the model.
model.save_weights(MODEL_WEIGHTS)
model.save(MODEL_NAME)
if __name__ == '__main__':
# freeze_support() here if program needs to be frozen
main()
对我来说,解决方案是降级 h5py
包(在我的情况下为 2.10.0),显然只将 Keras 和 Tensorflow 恢复到正确的版本是不够的。
我使用以下命令降级了我的 h5py 包,
pip install 'h5py==2.10.0' --force-reinstall
重新启动了我的 ipython 内核,它工作了。
conda install 'h5py==2.10.0'
有效。
对我来说,h5py 的版本优于我之前的版本。
通过设置为 2.10.0
来修复它。
使用以下命令降级 h5py 包以解决问题,
pip install h5py==2.10.0 --force-reinstall
我遇到了同样的问题,解决了将 compile=False
放入 load_model
的问题:
model_ = load_model('path to your model.h5',custom_objects={'Scale': Scale()}, compile=False)
sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.9, nesterov=True)
model_.compile(loss='categorical_crossentropy',optimizer='sgd',metrics=['accuracy'])
custom_objects={'Scale': Scale()}
?
compile = False
给了我这个错误,File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/saving.py", line 229, in load_model model_config = json.loads(model_config.decode('utf-8')) AttributeError: 'str' object has no attribute 'decode'
使用 TF 格式文件而不是 h5py 保存:save_format='tf'。就我而言:
model.save_weights("NMT_model_weight.tf",save_format='tf')
TypeError: save_weights() got an unexpected keyword argument 'save_format'
这可能是由于从不同版本的 keras 保存的模型。从 keras 2.2.6 加载由 tensorflow.keras 生成的模型(我认为类似于 keras 2.1.6 for tf 1.12)时,我遇到了同样的问题。
您可以使用 model.load_weights
加载权重并从您要使用的 keras 版本中重新保存完整的模型。
model.load_weights
我可以做到这一点,但我想知道为什么我不能加载整个模型架构
对我有用的解决方案是:
pip3 uninstall keras
pip3 uninstall tensorflow
pip3 install --upgrade pip3
pip3 install tensorflow
pip3 install keras
在我的环境中使用 tensorflow==2.4.1、h5py==2.1.0 和 python 3.8 后,我仍然遇到此错误。修复它的原因是将 python 版本降级到 3.6.9
不定期副业成功案例分享
We will have people working on making TF work with h5py >= 3 in the future, but this will only land in TF 2.5 or later.
出现此问题是因为 TensorFlow 无法与 h5py v3 和更高版本一起使用。 2.10.0 是最新版本-2.xy