I have written the following code:
tf.contrib.slim.learning.train(
...
...
session_wrapper=tensorflow.python.debug.LocalCLIDebugWrapperSession,
...)
While running the code, it reported:
......
......
2018-02-14 01:03:25.229477: I tensorflow/core/debug/debug_graph_utils.cc:229] For debugging, tfdbg is changing the parallel_iterations attribute of the Enter/RefEnter node "lstm/lstm_1/while/Enter_2" on device "/job:localhost/replica:0/task:0/device:CPU:0" from 32 to 1. (This does not affect subsequent non-debug runs.)
Traceback (most recent call last):
File "train_getimageid_ngch.py", line 147, in <module>
tf.app.run()
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train_getimageid_ngch.py", line 143, in main
saver=saver)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/contrib/slim/python/slim/learning.py", line 775, in train
sv.stop(threads, close_summary_writer=True)
File "/usr/lib/python2.7/contextlib.py", line 35, in __exit__
self.gen.throw(type, value, traceback)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 964, in managed_session
self.stop(close_summary_writer=close_summary_writer)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 792, in stop
stop_grace_period_secs=self._stop_grace_secs)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/training/coordinator.py", line 389, in join
six.reraise(*self._exc_info_to_raise)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/training/coordinator.py", line 296, in stop_on_exception
yield
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/training/coordinator.py", line 494, in run
self.run_loop()
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 1068, in run_loop
global_step=self._sv.global_step)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1549, in save
global_step = training_util.global_step(sess, global_step)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/training/training_util.py", line 67, in global_step
return int(sess.run(global_step_tensor))
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/debug/wrappers/framework.py", line 543, in run
run_end_resp = self.on_run_end(run_end_req)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/debug/wrappers/local_cli_wrapper.py", line 321, in on_run_end
self._dump_root, partition_graphs=partition_graphs)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/debug/lib/debug_data.py", line 495, in __init__
self._load_all_device_dumps(partition_graphs, validate)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/debug/lib/debug_data.py", line 517, in _load_all_device_dumps
self._load_partition_graphs(partition_graphs, validate)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/debug/lib/debug_data.py", line 798, in _load_partition_graphs
self._validate_dump_with_graphs(debug_graph.device_name)
File "/home/ngaimanchow/tensorflow_virtualenv/local/lib/python2.7/site-packages/tensorflow/python/debug/lib/debug_data.py", line 843, in _validate_dump_with_graphs
"device %s." % (datum.node_name, device_name))
ValueError: Node name 'TFRecordReaderV2' is not found in partition graphs of device /job:localhost/replica:0/task:0/device:CPU:0.
Even it can start the tf debugger, when tried to print the value of a tensor, i.e. the pt command, it reported the error:
Error occured during handling of command: "print_tensor"
exceptions.KeyError /device:CPU:0
Is it possible for tf_debug to truly support slim? How can it be worked out? If not, is there any other way to debug or print the values of tensors when using tf.contrib.slim.learning.train?
Related
(tensorflow) C:\tensorflow\workspace\training_demo>python model_main_tf2.py --model_dir=C:/tensorflow/workspace/models/my_ssd_resnet50_v1_fpn --pipeline_config_path=C:/tensorflow/workspace/models/my_ssd_resnet50_v1_fpn/pipeline.config
From C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\model_lib_v2.py:522: StrategyBase.experimental_distribute_datasets_from_function (from tensorflow.python.distribute.distribute_lib) is deprecated and will be removed in a future version.
Instructions for updating:
rename to distribute_datasets_from_function
Traceback (most recent call last):
File "model_main_tf2.py", line 113, in <module>
tf.compat.v1.app.run()
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\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\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\absl\app.py", line 300, in run
_run_main(main, args)
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\absl\app.py", line 251, in _run_main
sys.exit(main(argv))
File "model_main_tf2.py", line 104, in main
model_lib_v2.train_loop(
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\model_lib_v2.py", line 522, in train_loop
train_input = strategy.experimental_distribute_datasets_from_function(
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\util\deprecation.py", line 340, in new_func
return func(*args, **kwargs)
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\distribute\distribute_lib.py", line 1143, in experimental_distribute_datasets_from_function
return self.distribute_datasets_from_function(dataset_fn, options)
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\distribute\distribute_lib.py", line 1134, in distribute_datasets_from_function
return self._extended._distribute_datasets_from_function( # pylint: disable=protected-access
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\distribute\mirrored_strategy.py", line 545, in _distribute_datasets_from_function
return input_lib.get_distributed_datasets_from_function(
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\distribute\input_lib.py", line 161, in get_distributed_datasets_from_function
return DistributedDatasetsFromFunction(dataset_fn, input_workers,
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\distribute\input_lib.py", line 1272, in __init__
_create_datasets_from_function_with_input_context(
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\distribute\input_lib.py", line 1936, in _create_datasets_from_function_with_input_context
dataset = dataset_fn(ctx)
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\model_lib_v2.py", line 513, in train_dataset_fn
train_input = inputs.train_input(
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\inputs.py", line 870, in train_input
dataset = INPUT_BUILDER_UTIL_MAP['dataset_build'](
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\builders\dataset_builder.py", line 195, in build
decoder = decoder_builder.build(input_reader_config)
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\builders\decoder_builder.py", line 52, in build
decoder = tf_example_decoder.TfExampleDecoder(
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\data_decoders\tf_example_decoder.py", line 391, in __init__
_ClassTensorHandler(
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\data_decoders\tf_example_decoder.py", line 88, in __init__
name_to_id = label_map_util.get_label_map_dict(
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\utils\label_map_util.py", line 201, in get_label_map_dict
label_map = load_labelmap(label_map_path_or_proto)
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\object_detection\utils\label_map_util.py", line 168, in load_labelmap
label_map_string = fid.read()
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 117, in read
self._preread_check()
File "C:\Users\bigbootytx\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 79, in _preread_check
self._read_buf = _pywrap_file_io.BufferedInputStream(
tensorflow.python.framework.errors_impl.InvalidArgumentError: NewRandomAccessFile failed to Create/Open: C: ensorflow\workspacennotations\labelmap.pbtxt : The filename, directory name, or volume label syntax is incorrect.
; no protocol option
So im getting this weird issue where its changing the path of the file its looking for on its own.
C: ensorflow\workspacennotations\labelmap.pbtxt
should be
C:tensorflow\workspace\annotations\labelmap.pbtxt
Been stuck on this issue for quite a while now, tried several things including changing to forward slashes and stuff. Any idea what to do here? I followed this guide: https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html
\t in your path automatically replaces by tab. For prevent this on Windows, you need use double backslash (\\) as path delimiter: C:\\tensorflow\\...
Please help me through this..
Traceback (most recent call last):
File "object_detection\legacy\train.py", line 186, in
tf.app.run()
File "C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\platform\app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\absl\app.py", line 303, in run
_run_main(main, args)
File "C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\absl\app.py", line 251, in _run_main
sys.exit(main(argv))
File "C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\util\deprecation.py", line 324, in new_func
return func(*args, **kwargs)
File "object_detection\legacy\train.py", line 110, in main
overwrite=True)
File "C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\lib\io\file_io.py", line 469, in copy
copy_v2(oldpath, newpath, overwrite)
File "C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\lib\io\file_io.py", line 486, in copy_v2
compat.as_bytes(src), compat.as_bytes(dst), overwrite)
tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: : The system cannot find the path specified.
; No such process
I am currently trying to figure out how to use netmiko to automate some of my routine work.Such as getting configuration backup, creating vlans etc.I've managed to use it on Aruba and Huawei Switches without problem.But on alcatel switch I'm facing this issue:
Unknown exception: module 'cryptography.utils' has no attribute 'bit_length'
Traceback (most recent call last):
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\transport.py", line 2075, in run
self.kex_engine.parse_next(ptype, m)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\kex_gex.py", line 101, in parse_next
return self._parse_kexdh_gex_reply(m)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\kex_gex.py", line 281, in _parse_kexdh_gex_reply
self.transport._verify_key(host_key, sig)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\transport.py", line 1886, in _verify_key
if not key.verify_ssh_sig(self.H, Message(sig)):
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\dsskey.py", line 148, in verify_ssh_sig
key = dsa.DSAPublicNumbers(
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\cryptography\hazmat\primitives\asymmetric\dsa.py", line 212, in public_key
return backend.load_dsa_public_numbers(self)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\cryptography\hazmat\backends\openssl\backend.py", line 871, in load_dsa_public_numbers
dsa._check_dsa_parameters(numbers.parameter_numbers)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\netmiko\tplink\tplink_jetstream.py", line 145, in _override_check_dsa_parameters
if crypto_utils.bit_length(parameters.q) not in [160, 256]:
AttributeError: module 'cryptography.utils' has no attribute 'bit_length'
Traceback (most recent call last):
File "C:\Users\melih.celik\Desktop\New_Backup\Yedek\Coding\Rand stuff\ssh_deneme(toplu).py", line 75, in
config_backup(cihaz_secim,ip_address,username,password)
File "C:\Users\melih.celik\Desktop\New_Backup\Yedek\Coding\Rand stuff\ssh_deneme(toplu).py", line 12, in config_backup
net_connect=ConnectHandler(**switch) #Baglanti kuruldu.
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\netmiko\ssh_dispatcher.py", line 312, in ConnectHandler
return ConnectionClass(*args, **kwargs)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\netmiko\base_connection.py", line 346, in init
self._open()
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\netmiko\base_connection.py", line 351, in _open
self.establish_connection()
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\netmiko\base_connection.py", line 920, in establish_connection
self.remote_conn_pre.connect(**ssh_connect_params)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\client.py", line 406, in connect
t.start_client(timeout=timeout)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\transport.py", line 660, in start_client
raise e
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\transport.py", line 2075, in run
self.kex_engine.parse_next(ptype, m)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\kex_gex.py", line 101, in parse_next
return self._parse_kexdh_gex_reply(m)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\kex_gex.py", line 281, in _parse_kexdh_gex_reply
self.transport._verify_key(host_key, sig)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\transport.py", line 1886, in _verify_key
if not key.verify_ssh_sig(self.H, Message(sig)):
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\paramiko\dsskey.py", line 148, in verify_ssh_sig
key = dsa.DSAPublicNumbers(
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\cryptography\hazmat\primitives\asymmetric\dsa.py", line 212, in public_key
return backend.load_dsa_public_numbers(self)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\cryptography\hazmat\backends\openssl\backend.py", line 871, in load_dsa_public_numbers
dsa._check_dsa_parameters(numbers.parameter_numbers)
File "C:\Users\melih.celik\AppData\Local\Programs\Python\Python39\lib\site-packages\netmiko\tplink\tplink_jetstream.py", line 145, in _override_check_dsa_parameters
if crypto_utils.bit_length(parameters.q) not in [160, 256]:
AttributeError: module 'cryptography.utils' has no attribute 'bit_length'
Thanks for your help in advance.
It looks like tplink_jetstream.py assumes that a (now removed) helper function is available to it. The simplest fix here would be to go into that file and modify the line containing crypto_utils.bit_length(parameters.q) to read parameters.q.bit_length() instead.
I have a computer that has a C and D drive, where PyCharm, Python and the source code are installed on the D drive. I'm using Pipenv with PIPENV_VENV_IN_PROJECT set to enabled so that also ends up in the D drive. Despite all this, when running with code coverage enabled, I get this error:
Destroying test database for alias 'default'...
Traceback (most recent call last):
File "D:\Development\PyCharm\PyCharm 2019.1.1\helpers\coverage_runner\run_coverage.py", line 54, in <module>
main()
File "D:\Business\projectx\.venv\lib\site-packages\coverage\cmdline.py", line 770, in main
status = CoverageScript().command_line(argv)
File "D:\Business\projectx\.venv\lib\site-packages\coverage\cmdline.py", line 489, in command_line
return self.do_run(options, args)
File "D:\Business\projectx\.venv\lib\site-packages\coverage\cmdline.py", line 657, in do_run
self.coverage.save()
File "D:\Business\projectx\.venv\lib\site-packages\coverage\control.py", line 529, in save
data = self.get_data()
File "D:\Business\projectx\.venv\lib\site-packages\coverage\control.py", line 583, in get_data
if self._collector and self._collector.flush_data():
File "D:\Business\projectx\.venv\lib\site-packages\coverage\collector.py", line 425, in flush_data
self.covdata.add_lines(abs_file_dict(self.data))
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 236, in add_lines
self._choose_lines_or_arcs(lines=True)
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 279, in _choose_lines_or_arcs
with self._connect() as con:
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 160, in _connect
self._create_db()
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 117, in _create_db
with self._db:
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 525, in __enter__
self.connect()
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 510, in connect
filename = os.path.relpath(self.filename)
File "D:\Business\projectx\.venv\lib\ntpath.py", line 562, in relpath
path_drive, start_drive))
ValueError: path is on mount 'C:', start on mount 'D:'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\Development\PyCharm\PyCharm 2019.1.1\helpers\coverage_runner\run_coverage.py", line 58, in <module>
main(["xml", "-o", coverage_file + ".xml", "--ignore-errors"])
File "D:\Business\projectx\.venv\lib\site-packages\coverage\cmdline.py", line 770, in main
status = CoverageScript().command_line(argv)
File "D:\Business\projectx\.venv\lib\site-packages\coverage\cmdline.py", line 511, in command_line
self.coverage.load()
File "D:\Business\projectx\.venv\lib\site-packages\coverage\control.py", line 336, in load
self._data.read()
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 409, in read
with self._connect(): # TODO: doesn't look right
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 160, in _connect
self._create_db()
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 117, in _create_db
with self._db:
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 525, in __enter__
self.connect()
File "D:\Business\projectx\.venv\lib\site-packages\coverage\sqldata.py", line 510, in connect
filename = os.path.relpath(self.filename)
File "D:\Business\projectx\.venv\lib\ntpath.py", line 562, in relpath
path_drive, start_drive))
ValueError: path is on mount 'C:', start on mount 'D:'
Any ideas why?
I am using faster_rcnn_inception_resnet_v2_atrous_oid.config. I shows the following problem. Help me please:
File "train.py", line 167, in <module>
tf.app.run()
File "C:\Users\mgp21\Anaconda3\envs\deeplearning\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "train.py", line 92, in main
FLAGS.pipeline_config_path)
File "C:\Users\mgp21\Anaconda3\envs\deeplearning\models\research\object_detection\utils\config_util.py", line 88, in get_configs_from_pipeline_file
text_format.Merge(proto_str, pipeline_config)
File "C:\Users\mgp21\Anaconda3\envs\deeplearning\lib\site-packages\google\protobuf\text_format.py", line 533, in Merge
descriptor_pool=descriptor_pool)
File "C:\Users\mgp21\Anaconda3\envs\deeplearning\lib\site-packages\google\protobuf\text_format.py", line 587, in MergeLines
return parser.MergeLines(lines, message)
File "C:\Users\mgp21\Anaconda3\envs\deeplearning\lib\site-packages\google\protobuf\text_format.py", line 620, in MergeLines
self._ParseOrMerge(lines, message)
File "C:\Users\mgp21\Anaconda3\envs\deeplearning\lib\site-packages\google\protobuf\text_format.py", line 635, in _ParseOrMerge
self._MergeField(tokenizer, message)
File "C:\Users\mgp21\Anaconda3\envs\deeplearning\lib\site-packages\google\protobuf\text_format.py", line 735, in _MergeField
merger(tokenizer, message, field)
File "C:\Users\mgp21\Anaconda3\envs\deeplearning\lib\site-packages\google\protobuf\text_format.py", line 823, in _MergeMessageField
self._MergeField(tokenizer, sub_message)
File "C:\Users\mgp21\Anaconda3\envs\deeplearning\lib\site-packages\google\protobuf\text_format.py", line 703, in _MergeField
(message_descriptor.full_name, name))
google.protobuf.text_format.ParseError: 160:3 : Message type "object_detection.protos.TrainConfig" has no field named "fine_tune_checkpoint_type".
It's a matter of TensorFlow version, you're probably using a newer .config with an older TensorFlow, see https://github.com/tensorflow/models/issues/4056.