Closed wang-tf closed 7 years ago
Then I copy a file form ssd-tensorflow/nets/custom_layers.py
While, I have new problems:
INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.InvalidArgumentError'>, Name: <unknown>, Feature: label/length (data type: int64) is required but could not be found.
[[Node: input/ParseSingleExample/ParseExample/ParseExample = ParseExample[Ndense=3, Nsparse=1, Tdense=[DT_STRING, DT_STRING, DT_INT64], dense_shapes=[[], [], [1]], sparse_types=[DT_INT64], _device="/job:localhost/replica:0/task:0/cpu:0"](input/ParseSingleExample/ExpandDims, input/ParseSingleExample/ParseExample/ParseExample/names, input/ParseSingleExample/ParseExample/ParseExample/sparse_keys_0, input/ParseSingleExample/ParseExample/ParseExample/dense_keys_0, input/ParseSingleExample/ParseExample/ParseExample/dense_keys_1, input/ParseSingleExample/ParseExample/ParseExample/dense_keys_2, input/ParseSingleExample/ParseExample/Reshape, input/ParseSingleExample/ParseExample/Reshape_1, input/ParseSingleExample/ParseExample/Const)]]
Caused by op u'input/ParseSingleExample/ParseExample/ParseExample', defined at:
File "train_mjsyth.py", line 105, in <module>
tf.app.run()
File "/usr/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train_mjsyth.py", line 44, in main
num_epochs=num_epochs)
File "/disk/data0/users/tengfei5/test/crnn-tensorflow/dataset/read_utils.py", line 34, in inputs
img, label, length = read_and_decode(filename, num_epochs)
File "/disk/data0/users/tengfei5/test/crnn-tensorflow/dataset/read_utils.py", line 16, in read_and_decode
'label/length': tf.FixedLenFeature([1], tf.int64)
File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/parsing_ops.py", line 739, in parse_single_example
dense_types, dense_defaults, dense_shapes, name)
File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/parsing_ops.py", line 813, in _parse_single_example_raw
name=name)
File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/parsing_ops.py", line 688, in _parse_example_raw
name=name)
File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/gen_parsing_ops.py", line 178, in _parse_example
dense_shapes=dense_shapes, name=name)
File "/usr/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/usr/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Name: <unknown>, Feature: label/length (data type: int64) is required but could not be found.
[[Node: input/ParseSingleExample/ParseExample/ParseExample = ParseExample[Ndense=3, Nsparse=1, Tdense=[DT_STRING, DT_STRING, DT_INT64], dense_shapes=[[], [], [1]], sparse_types=[DT_INT64], _device="/job:localhost/replica:0/task:0/cpu:0"](input/ParseSingleExample/ExpandDims, input/ParseSingleExample/ParseExample/ParseExample/names, input/ParseSingleExample/ParseExample/ParseExample/sparse_keys_0, input/ParseSingleExample/ParseExample/ParseExample/dense_keys_0, input/ParseSingleExample/ParseExample/ParseExample/dense_keys_1, input/ParseSingleExample/ParseExample/ParseExample/dense_keys_2, input/ParseSingleExample/ParseExample/Reshape, input/ParseSingleExample/ParseExample/Reshape_1, input/ParseSingleExample/ParseExample/Const)]]
2017-07-14 12:24:11.369512: W tensorflow/core/framework/op_kernel.cc:1152] Out of range: RandomShuffleQueue '_2_input/shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 32, current size 0)
[[Node: input/shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/shuffle_batch/random_shuffle_queue, input/shuffle_batch/n)]]
2017-07-14 12:24:11.369599: W tensorflow/core/framework/op_kernel.cc:1152] Out of range: RandomShuffleQueue '_2_input/shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 32, current size 0)
[[Node: input/shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/shuffle_batch/random_shuffle_queue, input/shuffle_batch/n)]]
2017-07-14 12:24:11.369624: W tensorflow/core/framework/op_kernel.cc:1152] Out of range: RandomShuffleQueue '_2_input/shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 32, current size 0)
[[Node: input/shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/shuffle_batch/random_shuffle_queue, input/shuffle_batch/n)]]
2017-07-14 12:24:11.369940: W tensorflow/core/framework/op_kernel.cc:1152] Out of range: RandomShuffleQueue '_2_input/shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 32, current size 0)
[[Node: input/shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/shuffle_batch/random_shuffle_queue, input/shuffle_batch/n)]]
2017-07-14 12:24:11.370040: W tensorflow/core/framework/op_kernel.cc:1152] Out of range: RandomShuffleQueue '_2_input/shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 32, current size 0)
[[Node: input/shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/shuffle_batch/random_shuffle_queue, input/shuffle_batch/n)]]
2017-07-14 12:24:11.370094: W tensorflow/core/framework/op_kernel.cc:1152] Out of range: RandomShuffleQueue '_2_input/shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 32, current size 0)
[[Node: input/shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/shuffle_batch/random_shuffle_queue, input/shuffle_batch/n)]]
2017-07-14 12:24:11.370144: W tensorflow/core/framework/op_kernel.cc:1152] Out of range: RandomShuffleQueue '_2_input/shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 32, current size 0)
[[Node: input/shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/shuffle_batch/random_shuffle_queue, input/shuffle_batch/n)]]
2017-07-14 12:24:11.370257: W tensorflow/core/framework/op_kernel.cc:1152] Out of range: RandomShuffleQueue '_2_input/shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 32, current size 0)
[[Node: input/shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/shuffle_batch/random_shuffle_queue, input/shuffle_batch/n)]]
2017-07-14 12:24:11.370335: W tensorflow/core/framework/op_kernel.cc:1152] Out of range: RandomShuffleQueue '_2_input/shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 32, current size 0)
[[Node: input/shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/shuffle_batch/random_shuffle_queue, input/shuffle_batch/n)]]
Traceback (most recent call last):
File "train_mjsyth.py", line 105, in <module>
tf.app.run()
File "/usr/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train_mjsyth.py", line 96, in main
print('Done training for %d epochs, %d steps.' % (num_epochs, step))
TypeError: %d format: a number is required, not Variable
How can I fix it ? Thanks
@wang-tf have you solved this question?
@wang-tf @zoe218 find all in https://github.com/AimeeKing/my_practice_on_textbox
@novioleo@wang-tf @zoe218 can you run train_mjsyth.py , when i run it ,error reported.
Yes, I can run it now. This problem is fixed if I use num_epochs = None
. So actually it's not a problem. It just represent the train finished.
@wang-tf if set num_epochs = None ,The program has been stuck, no result....What's the matter? thank you
全部都是中国人,你们都贴图吧。好交流点。
@songwendong num_epochs作者在定义的时候是for循环里面的,可能有点问题,你debug一下试试~
@songwendong InvalidArgumentError (see above for traceback): assertion failed: [Expected shape for Tensor RCNN_net/sequence_length:0 is ] [1] [ but saw shape: ] [2] 你数据shape不对~你debug看下?
@songwendong 那你要不要试试原版程序?https://github.com/weinman/cnn_lstm_ctc_ocr
@novioleo 多谢多谢
就在github吧。平时不用其他的。
When I was trying
train_mjsyth.py
, it shows that:Is there any file I didn't include ?