IOError: Unable to open file (File signature not found)

最新推荐文章于 2025-06-12 10:48:18 发布

AI算法网奇

最新推荐文章于 2025-06-12 10:48:18 发布

阅读量1w

点赞数 1

CC 4.0 BY-SA版权

本文链接：https://blog.youkuaiyun.com/jacke121/article/details/79245317

本文介绍使用Keras加载模型的两种方法，并通过实例详细分析了加载预训练模型时出现的常见错误及其解决办法。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

keras加载模型有两种方式
1.model = load_model('model.h5')
2.
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same',
                 input_shape=(3, IMG_SIZE, IMG_SIZE),
                 activation='relu'))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Dropout(1))
model.add(Conv2D(64, (3, 3), padding='same',
                 activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Dropout(1))
model.add(Conv2D(128, (3, 3), padding='same',
                 activation='relu'))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Dropout(1))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
# model.add(Dropout(1))
model.add(Dense(NUM_CLASSES, activation='softmax'))
model.load_weights('model.h5')
adam = Adam(lr=1e-6)
model.compile(loss='mse', optimizer=adam)
又一次加载时报错了，IOError: Unable to open file (File signature not found)
h5py\_objects.pyx in h5py._objects.with_phil.wrapper (C:\aroot\work\h5py\_objects.c:2579)()

h5py\_objects.pyx in h5py._objects.with_phil.wrapper (C:\aroot\work\h5py\_objects.c:2538)()

h5py\h5f.pyx in h5py.h5f.open (C:\aroot\work\h5py\h5f.c:1813)()

OSError: Unable to open file (File signature not found)

原因：model.h5内容丢失了，大小为59k
重新训练一个正常的model.h5就可以了