Traceback (most recent call last): File "D:/Coding/python/machine_learn/image_classify3.py", line 141, in <module> model = ResNet50_model(0.2, 7, 'adam') File "D:/Coding/python/machine_learn/image_classify3.py", line 59, in ResNet50_model base_model = ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3)) File "D:\SF_A\Anaconda\envs\ml\lib\site-packages\tensorflow\python\keras\applications\resnet.py", line 471, in ResNet50 return ResNet(stack_fn, False, True, 'resnet50', include_top, weights, File "D:\SF_A\Anaconda\envs\ml\lib\site-packages\tensorflow\python\keras\applications\resnet.py", line 219, in ResNet model.load_weights(weights_path) File "D:\SF_A\Anaconda\envs\ml\lib\site-packages\tensorflow\python\keras\engine\training.py", line 2234, in load_weights hdf5_format.load_weights_from_hdf5_group(f, self.layers) File "D:\SF_A\Anaconda\envs\ml\lib\site-packages\tensorflow\python\keras\saving\hdf5_format.py", line 662, in load_weights_from_hdf5_group original_keras_version = f.attrs['keras_version'].decode('utf8') AttributeError: 'str' object has no attribute 'decode'

这个错误是因为在代码中使用了Python 3的`.decode()`方法，但是在运行时使用了Python 2的HDF5文件。在Python 2中，字符串类型是bytes类型，所以可以使用`.decode()`方法将其转换为Unicode字符串类型。但是在Python 3中，字符串类型默认是Unicode字符串类型，因此没有`.decode()`方法。

要解决这个错误，你可以尝试升级你的HDF5库，或者在读取HDF5文件时指定`encoding`参数。例如：

import h5py

with h5py.File('your_file.h5', 'r', encoding='utf-8') as f:
    # 读取HDF5文件的代码

如果你仍然遇到问题，可以尝试将代码转换为Python 2或者Python 3版本的代码，以便与使用的HDF5库兼容。