Galaxy-yyyyy

用自己的数据和预训练模型重新训练train_softmax.py出错

4

TypeError: Cannot create initializer for non-floating point type.

数据集制作

1

请问如果用自己的数据训练大佬写的程序，数据集怎么制作了，1，不用再另外制作label，文件夹就是标签，有多少个文件夹就有多少类别；2，需要另外制作标签；

'tensorflow.python.framework.errors_impl.InvalidArgumentError'>, assertion failed: [Unable to decode bytes as JPEG, PNG, GIF, or BMP]

File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper File "h5py/h5f.pyx", line 108, in h5py.h5f.create OSError: Unable to create file (unable to open file: name = '/media/zhang/Data/face/Face-Occlusion-Detect/model/',...