我一直在尝试使用Keras和本教程后已预先训练好的权重VGG16构建卷积神经网络（CNN）：https://github.com/heuritech/convnets-keras。
当我运行以下代码时：
from keras.optimizers import SGD
from convnetskeras.convnets import preprocess_image_batch, convnet
im = preprocess_image_batch(['examples/dog.jpg'],img_size=(256,256), crop_size=(224,224), color_mode="bgr")
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
## For the VGG16, use this command
model = convnet('vgg_16',weights_path="weights/vgg16_weights.h5", heatmap=False)
model.compile(optimizer=sgd, loss='mse')
out = model.predict(im)
声明模型时出现以下错误，因为它使用了h5py包：
Traceback (most recent call last):
File "Convnets_Setup01.py", line 13, in <module>
model = convnet('vgg_16',weights_path="weights/vgg16_weights.h5",heatmap=False)
File "/home/inigo/convnets_keras/convnetskeras/convnets.py", line 65, in convnet
convnet = convnet_init(weights_path, heatmap=False)
File "/home/inigo/convnets_keras/convnetskeras/convnets.py", line 147, in VGG_16
model.load_weights(weights_path)
File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.0-py2.7.egg/keras/engine/topology.py", line 2494, in load_weights
f = h5py.File(filepath, mode='r')
File "/usr/lib/python2.7/dist-packages/h5py/_hl/files.py", line 207, in __init__
fid = make_fid(name, mode, userblock_size, fapl)
File "/usr/lib/python2.7/dist-packages/h5py/_hl/files.py", line 79, in make_fid
fid = h5f.open(name, h5f.ACC_RDONLY, fapl=fapl)
File "h5f.pyx", line 71, in h5py.h5f.open (h5py/h5f.c:1806)
IOError: unable to open file (File accessibilty: Unable to open file)
我在Ubuntu 14.04上使用Keras 1.1.0和后端Theano 0.9.0.dev3，Python-2.7。我安装的h5py版本是2.2.1
我已尝试重新安装h5py软件包，以防第一个软件包损坏。我也尝试手动创建h5f.c文件夹，但无法将任何其他文件夹添加到h5py目录（usr / lib / python2.7 / dist-packages / h5py）
有谁知道为什么会发生这种情况？