tensorflow.python.framework.errors_impl.NotFoundError: 2 root error(s) found.
(0) Not found: Resource localhost/FC_embedding/N10tensorflow3VarE does not exist.
[[node strided_slice/_assign (defined at /home/admin1/anaconda3/envs/max/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
[[ReadVariableOp_1/_191]]
(1) Not found: Resource localhost/FC_embedding/N10tensorflow3VarE does not exist.
[[node strided_slice/_assign (defined at /home/admin1/anaconda3/envs/max/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
keras无法使用Tensorboar投影仪看到任何嵌入层
•
问答
我尝试使用Keras.callbacks.tensorboard可视化分类程序。该方法具有类似embeddings_freq \ embeddings_layer_names \ embeddings_data的参数。我将最后一个FC层分配给embedding_layer_names。而且它不起作用。
引发错误：
qazzaqqaz4444 回答：keras无法使用Tensorboar投影仪看到任何嵌入层
暂时没有好的解决方案，如果你有好的解决方案，请发邮件至：iooj@foxmail.com