hzhao1997 / HF-Avatar

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

关于octopus_weights.hdf5权重的问题

muximuxi opened this issue · comments

您好!
根据提示将octopus_weights.hdf5下载并放到weights文件夹下,使用sample_data, 并执行第一步python _infer_single.py后,报错:
ValueError: Layer #5 (named "conv2d_1"), weight <tf.Variable 'conv2d_1/kernel:0' shape=(3, 3, 8, 16) dtype=float32> has shape (3, 3, 8, 16), but the saved weight has shape (8, 3, 3, 3).
请问是哪里出问题了吗?

可以把octopus文件中,286行的by_name改成False试一试,