0
0 комментариев

доброго времени суток. Я не давно начал изучать Python и машинное обучение. Прошу не судить строго. во время тренировки ./train.py я столкнулся с этой ошибкой. 


2019-08-16 17:12:41.510175: W tensorflow/core/framework/allocator.cc:107] Allocation of 268435456 exceeds 10% of system memory.
2019-08-16 17:12:42.468182: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=—tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass —vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=—xla_hlo_profile.
Traceback (most recent call last):
File «./train.py», line 266, in
initial_weights=initial_weights)
File «./train.py», line 239, in train
do_batch()
File «./train.py», line 222, in do_batch
feed_dict={x: batch_xs, y_: batch_ys})
File «/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py», line 950, in run
run_metadata_ptr)
File «/usr/lib/python2.7/site-packages/tensorflow/python/client/session.py», line 1149, in _run
str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (50, 289) for Tensor u’Placeholder_1:0′, which has shape ‘(?, 253)’

репозитории брал от сюда: https://github.com/matthewearl/deep-anpr

полное описания проблемы: https://github.com/matthewearl/deep-anpr/issues/120

и google мне не помог(

Asked question
Добавить комментарий