Closed zhangke1997 closed 4 years ago
i have solved it
i have solved it
how did you solve it?
use tf 2.3.0 keras 2.4.3
use tf 2.3.0 keras 2.4.3
yes, i use this but meet a new problem which is WARNING:tensorflow:Your input ran out of data; interrupting training. did you meet this problem?(https://github.com/fizyr/keras-retinanet/issues/1449)
use tf 2.3.0 keras 2.4.3
yes, i use this but meet a new problem which is WARNING:tensorflow:Your input ran out of data; interrupting training. did you meet this problem?(#1449)
the map is low.
What do you mean the map is low?
This issue has been automatically marked as stale due to the lack of recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
last lines: File "/home/lyp/.local/lib/python3.5/site-packages/tensorflow/python/ops/variables.py", line 236, in
previous_getter = lambda kws: default_variable_creator_v2(None, kws)
File "/home/lyp/.local/lib/python3.5/site-packages/tensorflow/python/ops/variable_scope.py", line 2647, in default_variable_creator_v2
shape=shape)
File "/home/lyp/.local/lib/python3.5/site-packages/tensorflow/python/ops/variables.py", line 263, in call
return super(VariableMetaclass, cls).call(*args, **kwargs)
File "/home/lyp/.local/lib/python3.5/site-packages/tensorflow/python/ops/resource_variable_ops.py", line 1434, in init
distribute_strategy=distribute_strategy)
File "/home/lyp/.local/lib/python3.5/site-packages/tensorflow/python/ops/resource_variable_ops.py", line 1517, in _init_from_args
raise ValueError("Tensor-typed variable initializers must either be "
ValueError: Tensor-typed variable initializers must either be wrapped in an init_scope or callable (e.g.,
tf.Variable(lambda : tf.truncated_normal([10, 40]))
) when building functions. Please file a feature request if this restriction inconveniences you.anyone same?