Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Is it normal to falling in an infinite loop? #100

Open
bayismet opened this issue Apr 27, 2022 · 0 comments
Open

Is it normal to falling in an infinite loop? #100

bayismet opened this issue Apr 27, 2022 · 0 comments

Comments

@bayismet
Copy link

Hello there!

I downloaded and executed as a .py file one of the tutorials. I'll share the exact result I get down below. Is it normal it keeps starting itself again and again? Thanks!

(graphvite) batuhanm@etiyayz:~/graphvite$ python node_representation_learning_on_large_graphs.py 
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.0460918 s
[time] GraphApplication.build: 0.166983 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 10.2 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.387883
Batch id: 2000 / 6548
loss = 0.382675
Batch id: 3000 / 6548
loss = 0.379259
Batch id: 4000 / 6548
loss = 0.376252
Batch id: 5000 / 6548
loss = 0.372444
Batch id: 6000 / 6548
loss = 0.370453
[time] GraphApplication.train: 4.45633 s
effective labels: 14472 / 14476
1
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.0466001 s
[time] GraphApplication.build: 0.145495 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 9.99 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.387772
Batch id: 2000 / 6548
loss = 0.382389
Batch id: 3000 / 6548
loss = 0.378922
Batch id: 4000 / 6548
loss = 0.376096
Batch id: 5000 / 6548
loss = 0.372452
Batch id: 6000 / 6548
loss = 0.370365
[time] GraphApplication.train: 4.49339 s
effective labels: 14472 / 14476
1
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 114, in _main
    prepare(preparation_data)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/batuhanm/graphvite/node_representation_learning_on_large_graphs.py", line 65, in <module>
    app.node_classification(file_name=gv.dataset.blogcatalog.label, portions=(0.2,))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 346, in node_classification
    results = self.gpu_map(linear_classification, settings)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 234, in gpu_map
    pool = multiprocessing.Pool(len(gpus))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 119, in Pool
    context=self.get_context())
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 176, in __init__
    self._repopulate_pool()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 241, in _repopulate_pool
    w.start()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/process.py", line 112, in start
    self._popen = self._Popen(self)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 284, in _Popen
    return Popen(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_fork.py", line 20, in __init__
    self._launch(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 136, in _check_not_importing_main
    is not going to be frozen to produce an executable.''')
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.0464778 s
[time] GraphApplication.build: 0.141464 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 9.99 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.387672
Batch id: 2000 / 6548
loss = 0.382468
Batch id: 3000 / 6548
loss = 0.379075
Batch id: 4000 / 6548
loss = 0.376327
Batch id: 5000 / 6548
loss = 0.372425
Batch id: 6000 / 6548
loss = 0.37032
[time] GraphApplication.train: 4.50981 s
effective labels: 14472 / 14476
1
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 114, in _main
    prepare(preparation_data)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/batuhanm/graphvite/node_representation_learning_on_large_graphs.py", line 65, in <module>
    app.node_classification(file_name=gv.dataset.blogcatalog.label, portions=(0.2,))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 346, in node_classification
    results = self.gpu_map(linear_classification, settings)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 234, in gpu_map
    pool = multiprocessing.Pool(len(gpus))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 119, in Pool
    context=self.get_context())
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 176, in __init__
    self._repopulate_pool()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 241, in _repopulate_pool
    w.start()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/process.py", line 112, in start
    self._popen = self._Popen(self)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 284, in _Popen
    return Popen(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_fork.py", line 20, in __init__
    self._launch(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 136, in _check_not_importing_main
    is not going to be frozen to produce an executable.''')
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.0471516 s
[time] GraphApplication.build: 0.14229 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 9.99 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.388005
Batch id: 2000 / 6548
loss = 0.382484
Batch id: 3000 / 6548
loss = 0.379027
Batch id: 4000 / 6548
loss = 0.376399
Batch id: 5000 / 6548
loss = 0.3726
Batch id: 6000 / 6548
loss = 0.370475
[time] GraphApplication.train: 4.42358 s
effective labels: 14472 / 14476
1
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 114, in _main
    prepare(preparation_data)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/batuhanm/graphvite/node_representation_learning_on_large_graphs.py", line 65, in <module>
    app.node_classification(file_name=gv.dataset.blogcatalog.label, portions=(0.2,))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 346, in node_classification
    results = self.gpu_map(linear_classification, settings)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 234, in gpu_map
    pool = multiprocessing.Pool(len(gpus))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 119, in Pool
    context=self.get_context())
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 176, in __init__
    self._repopulate_pool()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 241, in _repopulate_pool
    w.start()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/process.py", line 112, in start
    self._popen = self._Popen(self)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 284, in _Popen
    return Popen(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_fork.py", line 20, in __init__
    self._launch(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 136, in _check_not_importing_main
    is not going to be frozen to produce an executable.''')
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.0460806 s
[time] GraphApplication.build: 0.140951 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 9.99 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.387827
Batch id: 2000 / 6548
loss = 0.382371
Batch id: 3000 / 6548
loss = 0.378984
Batch id: 4000 / 6548
loss = 0.376317
Batch id: 5000 / 6548
loss = 0.372333
Batch id: 6000 / 6548
loss = 0.370397
[time] GraphApplication.train: 4.44952 s
effective labels: 14472 / 14476
1
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 114, in _main
    prepare(preparation_data)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/batuhanm/graphvite/node_representation_learning_on_large_graphs.py", line 65, in <module>
    app.node_classification(file_name=gv.dataset.blogcatalog.label, portions=(0.2,))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 346, in node_classification
    results = self.gpu_map(linear_classification, settings)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 234, in gpu_map
    pool = multiprocessing.Pool(len(gpus))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 119, in Pool
    context=self.get_context())
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 176, in __init__
    self._repopulate_pool()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 241, in _repopulate_pool
    w.start()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/process.py", line 112, in start
    self._popen = self._Popen(self)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 284, in _Popen
    return Popen(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_fork.py", line 20, in __init__
    self._launch(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 136, in _check_not_importing_main
    is not going to be frozen to produce an executable.''')
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.0463161 s
[time] GraphApplication.build: 0.141157 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 9.99 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.387918
Batch id: 2000 / 6548
loss = 0.382566
Batch id: 3000 / 6548
loss = 0.379185
Batch id: 4000 / 6548
loss = 0.37623
Batch id: 5000 / 6548
loss = 0.372305
Batch id: 6000 / 6548
loss = 0.37036
[time] GraphApplication.train: 4.48253 s
effective labels: 14472 / 14476
1
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 114, in _main
    prepare(preparation_data)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/batuhanm/graphvite/node_representation_learning_on_large_graphs.py", line 65, in <module>
    app.node_classification(file_name=gv.dataset.blogcatalog.label, portions=(0.2,))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 346, in node_classification
    results = self.gpu_map(linear_classification, settings)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 234, in gpu_map
    pool = multiprocessing.Pool(len(gpus))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 119, in Pool
    context=self.get_context())
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 176, in __init__
    self._repopulate_pool()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 241, in _repopulate_pool
    w.start()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/process.py", line 112, in start
    self._popen = self._Popen(self)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 284, in _Popen
    return Popen(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_fork.py", line 20, in __init__
    self._launch(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 136, in _check_not_importing_main
    is not going to be frozen to produce an executable.''')
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.0465286 s
[time] GraphApplication.build: 0.141467 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 9.99 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.387701
Batch id: 2000 / 6548
loss = 0.382437
Batch id: 3000 / 6548
loss = 0.378942
Batch id: 4000 / 6548
loss = 0.376202
Batch id: 5000 / 6548
loss = 0.37252
Batch id: 6000 / 6548
loss = 0.3704
[time] GraphApplication.train: 4.50553 s
effective labels: 14472 / 14476
1
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 114, in _main
    prepare(preparation_data)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/batuhanm/graphvite/node_representation_learning_on_large_graphs.py", line 65, in <module>
    app.node_classification(file_name=gv.dataset.blogcatalog.label, portions=(0.2,))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 346, in node_classification
    results = self.gpu_map(linear_classification, settings)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 234, in gpu_map
    pool = multiprocessing.Pool(len(gpus))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 119, in Pool
    context=self.get_context())
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 176, in __init__
    self._repopulate_pool()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 241, in _repopulate_pool
    w.start()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/process.py", line 112, in start
    self._popen = self._Popen(self)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 284, in _Popen
    return Popen(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_fork.py", line 20, in __init__
    self._launch(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 136, in _check_not_importing_main
    is not going to be frozen to produce an executable.''')
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.0460839 s
[time] GraphApplication.build: 0.141356 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 9.99 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.387748
Batch id: 2000 / 6548
loss = 0.382556
Batch id: 3000 / 6548
loss = 0.37917
Batch id: 4000 / 6548
loss = 0.376153
Batch id: 5000 / 6548
loss = 0.372358
Batch id: 6000 / 6548
loss = 0.37046
[time] GraphApplication.train: 4.4739 s
effective labels: 14472 / 14476
1
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 114, in _main
    prepare(preparation_data)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/batuhanm/graphvite/node_representation_learning_on_large_graphs.py", line 65, in <module>
    app.node_classification(file_name=gv.dataset.blogcatalog.label, portions=(0.2,))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 346, in node_classification
    results = self.gpu_map(linear_classification, settings)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 234, in gpu_map
    pool = multiprocessing.Pool(len(gpus))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 119, in Pool
    context=self.get_context())
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 176, in __init__
    self._repopulate_pool()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 241, in _repopulate_pool
    w.start()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/process.py", line 112, in start
    self._popen = self._Popen(self)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 284, in _Popen
    return Popen(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_fork.py", line 20, in __init__
    self._launch(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 136, in _check_not_importing_main
    is not going to be frozen to produce an executable.''')
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.0463991 s
[time] GraphApplication.build: 0.141246 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 9.99 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.387929
Batch id: 2000 / 6548
loss = 0.382644
Batch id: 3000 / 6548
loss = 0.379018
Batch id: 4000 / 6548
loss = 0.376168
Batch id: 5000 / 6548
loss = 0.372515
Batch id: 6000 / 6548
loss = 0.370471
[time] GraphApplication.train: 4.48483 s
effective labels: 14472 / 14476
1
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 114, in _main
    prepare(preparation_data)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 225, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 277, in _fixup_main_from_path
    run_name="__mp_main__")
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 263, in run_path
    pkg_name=pkg_name, script_name=fname)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 96, in _run_module_code
    mod_name, mod_spec, pkg_name, script_name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/batuhanm/graphvite/node_representation_learning_on_large_graphs.py", line 65, in <module>
    app.node_classification(file_name=gv.dataset.blogcatalog.label, portions=(0.2,))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 346, in node_classification
    results = self.gpu_map(linear_classification, settings)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 234, in gpu_map
    pool = multiprocessing.Pool(len(gpus))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 119, in Pool
    context=self.get_context())
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 176, in __init__
    self._repopulate_pool()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 241, in _repopulate_pool
    w.start()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/process.py", line 112, in start
    self._popen = self._Popen(self)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/context.py", line 284, in _Popen
    return Popen(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 32, in __init__
    super().__init__(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_fork.py", line 20, in __init__
    self._launch(process_obj)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 42, in _launch
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 143, in get_preparation_data
    _check_not_importing_main()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/spawn.py", line 136, in _check_not_importing_main
    is not going to be frozen to produce an executable.''')
RuntimeError: 
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.
loading graph from /home/batuhanm/.graphvite/dataset/blogcatalog/blogcatalog_train.txt
0.00018755%
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Graph<uint32>
------------------ Graph -------------------
#vertex: 10308, #edge: 327429
as undirected: yes, normalization: no
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
[time] GraphApplication.load: 0.046684 s
[time] GraphApplication.build: 0.141742 s
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
GraphSolver<128, float32, uint32>
----------------- Resource -----------------
#worker: 1, #sampler: 7, #partition: 1
tied weights: no, episode size: 200
gpu memory limit: 9.99 GiB
gpu memory cost: 51.5 MiB
----------------- Sampling -----------------
augmentation step: 2, shuffle base: 2
random walk length: 40
random walk batch size: 100
#negative: 1, negative sample exponent: 0.75
----------------- Training -----------------
model: LINE
optimizer: SGD
learning rate: 0.025, lr schedule: linear
weight decay: 0.005
#epoch: 2000, batch size: 100000
resume: no
positive reuse: 1, negative weight: 5
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Batch id: 0 / 6548
loss = 0
Batch id: 1000 / 6548
loss = 0.388031
Batch id: 2000 / 6548
loss = 0.382297
Batch id: 3000 / 6548
loss = 0.379089
Batch id: 4000 / 6548
loss = 0.376302
^CTraceback (most recent call last):
  File "node_representation_learning_on_large_graphs.py", line 65, in <module>
    app.node_classification(file_name=gv.dataset.blogcatalog.label, portions=(0.2,))
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 346, in node_classification
    results = self.gpu_map(linear_classification, settings)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/site-packages/graphvite/application/application.py", line 235, in gpu_map
    results = pool.map(func, settings, chunksize=1)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 268, in map
    return self._map_async(func, iterable, mapstar, chunksize).get()
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 651, in get
    self.wait(timeout)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/multiprocessing/pool.py", line 648, in wait
    self._event.wait(timeout)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/threading.py", line 552, in wait
    signaled = self._cond.wait(timeout)
  File "/home/batuhanm/miniconda3/envs/graphvite/lib/python3.7/threading.py", line 296, in wait
    waiter.acquire()
KeyboardInterrupt
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@bayismet