yu-wu / decoupled-novel-object-captioner Goto Github PK

Hello! Thank you for your fascinating work.
When I was preparing the data, I found that the googledrive link https://drive.google.com/open?id=1zit11UTSTQl00ynsyhSlF0NtggHSQmwI is invalid. The file stores the pre-extracted detection features. I think the url is out of date. Could you please update it? Thanks!

当我运行 python extract_detection_feature.py后出现如下错误：

tensorflow是1.4.1的gpu版本
该如何解决？

I am getting the following exception while reading data, I guess the getting occurred before putting finishing.

Traceback (most recent call last):
  File "/home/vimos/git/multimodal/DNOC/run.py", line 148, in <module>
    tf.compat.v1.app.run()
  File "/home/vimos/anaconda3/envs/rcqa/lib/python3.7/site-packages/tensorflow/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/home/vimos/anaconda3/envs/rcqa/lib/python3.7/site-packages/absl/app.py", line 300, in run
    _run_main(main, args)
  File "/home/vimos/anaconda3/envs/rcqa/lib/python3.7/site-packages/absl/app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "/home/vimos/git/multimodal/DNOC/run.py", line 142, in main
    train()
  File "/home/vimos/git/multimodal/DNOC/run.py", line 80, in train
    batch = data_loader.next()
  File "/home/vimos/git/multimodal/DNOC/utils/dataloader.py", line 101, in next
    batch = self._feed_queue.get(timeout=10)
  File "/home/vimos/anaconda3/envs/rcqa/lib/python3.7/multiprocessing/queues.py", line 105, in get
    raise Empty
_queue.Empty

Hi,
I am using Tensorflow 1.14 with python 3.6, on windows 10. I managed to complete all the steps of preparing data after some path modifications (windows....), however I am having problems with run.py while training. It is related to multiprocessing and Pickling, but I am unable to figure out exactly what.

Here are all the warnings and errors, can you please have a look.

`(py36tf) E:\Decoupled-Novel-Object-Captioner-master>python run.py --stage train
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
WARNING:tensorflow:From run.py:56: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.

WARNING:tensorflow:From run.py:148: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.

Traceback (most recent call last):
File "run.py", line 148, in
tf.app.run()
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\absl\app.py", line 299, in run
_run_main(main, args)
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\absl\app.py", line 250, in _run_main
sys.exit(main(argv))
File "run.py", line 142, in main
train()
File "run.py", line 63, in train
data_loader.start()
File "E:\Decoupled-Novel-Object-Captioner-master\utils\dataloader.py", line 48, in start
t.start()
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\multiprocessing\popen_spawn_win32.py", line 65, in init
reduction.dump(process_obj, to_child)
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: can't pickle _thread.lock objects
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorflow\python\framework\dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])

(py36tf) E:\Decoupled-Novel-Object-Captioner-master>C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
WARNING:tensorflow:From E:\Decoupled-Novel-Object-Captioner-master\run.py:56: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.

Traceback (most recent call last):
File "", line 1, in
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "C:\Users\22161668\AppData\Local\Continuum\anaconda3\envs\py36tf\lib\multiprocessing\spawn.py", line 115, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input`