baudm / monet-pytorch Goto Github PK

Windows 10, torch version 1.5.1

AttributeError Traceback (most recent call last)
in
2 import dill
3 #from pathos.multiprocessing import ProcessingPool as Pool
----> 4 tr_it = iter(train_dataloader)
5 progress_bar = tqdm(range(cfg["train_params"]["max_num_steps"]))
6 losses_train = []

c:\users\dilip\anaconda3\envs\tf-gpu\lib\site-packages\torch\utils\data\dataloader.py in iter(self)
277 return _SingleProcessDataLoaderIter(self)
278 else:
--> 279 return _MultiProcessingDataLoaderIter(self)
280
281 @Property

c:\users\dilip\anaconda3\envs\tf-gpu\lib\site-packages\torch\utils\data\dataloader.py in init(self, loader)
717 # before it starts, and del tries to join but will get:
718 # AssertionError: can only join a started process.
--> 719 w.start()
720 self._index_queues.append(index_queue)
721 self._workers.append(w)

c:\users\dilip\anaconda3\envs\tf-gpu\lib\multiprocessing\process.py in start(self)
110 'daemonic processes are not allowed to have children'
111 _cleanup()
--> 112 self._popen = self._Popen(self)
113 self._sentinel = self._popen.sentinel
114 # Avoid a refcycle if the target function holds an indirect

c:\users\dilip\anaconda3\envs\tf-gpu\lib\multiprocessing\context.py in _Popen(process_obj)
221 @staticmethod
222 def _Popen(process_obj):
--> 223 return _default_context.get_context().Process._Popen(process_obj)
224
225 class DefaultContext(BaseContext):

c:\users\dilip\anaconda3\envs\tf-gpu\lib\multiprocessing\context.py in _Popen(process_obj)
320 def _Popen(process_obj):
321 from .popen_spawn_win32 import Popen
--> 322 return Popen(process_obj)
323
324 class SpawnContext(BaseContext):

c:\users\dilip\anaconda3\envs\tf-gpu\lib\multiprocessing\popen_spawn_win32.py in init(self, process_obj)
87 try:
88 reduction.dump(prep_data, to_child)
---> 89 reduction.dump(process_obj, to_child)
90 finally:
91 set_spawning_popen(None)

c:\users\dilip\anaconda3\envs\tf-gpu\lib\multiprocessing\reduction.py in dump(obj, file, protocol)
58 def dump(obj, file, protocol=None):
59 '''Replacement for pickle.dump() using ForkingPickler.'''
---> 60 ForkingPickler(file, protocol).dump(obj)
61
62 #

AttributeError: Can't pickle local object 'StringEncoder..EncodeField'

Hi,

I am getting the following error when I run it:

WARNING:root:Setting up a new session...
create web directory ./checkpoints\clevr_monet\web...
Traceback (most recent call last):
  File "train.py", line 43, in <module>
    for i, data in enumerate(dataset):  # inner loop within one epoch
  File "F:\Documents\WinPython\MONet-pytorch\data\__init__.py", line 90, in __iter__
    for i, data in enumerate(self.dataloader):
  File "C:\ProgramData\Anaconda3\envs\tf-gpu\lib\site-packages\torch\utils\data\dataloader.py", line 819, in __iter__
    return _DataLoaderIter(self)
  File "C:\ProgramData\Anaconda3\envs\tf-gpu\lib\site-packages\torch\utils\data\dataloader.py", line 560, in __init__
    w.start()
  File "C:\ProgramData\Anaconda3\envs\tf-gpu\lib\multiprocessing\process.py", line 105, in start
    self._popen = self._Popen(self)
  File "C:\ProgramData\Anaconda3\envs\tf-gpu\lib\multiprocessing\context.py", line 223, in _Popen
    return _default_context.get_context().Process._Popen(process_obj)
  File "C:\ProgramData\Anaconda3\envs\tf-gpu\lib\multiprocessing\context.py", line 322, in _Popen
    return Popen(process_obj)
  File "C:\ProgramData\Anaconda3\envs\tf-gpu\lib\multiprocessing\popen_spawn_win32.py", line 65, in __init__
    reduction.dump(process_obj, to_child)
  File "C:\ProgramData\Anaconda3\envs\tf-gpu\lib\multiprocessing\reduction.py", line 60, in dump
    ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object '_get_transforms.<locals>.<lambda>'

(tf-gpu) F:\Documents\WinPython\MONet-pytorch>Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "C:\ProgramData\Anaconda3\envs\tf-gpu\lib\multiprocessing\spawn.py", line 105, in spawn_main
    exitcode = _main(fd)
  File "C:\ProgramData\Anaconda3\envs\tf-gpu\lib\multiprocessing\spawn.py", line 115, in _main
    self = reduction.pickle.load(from_parent)
EOFError: Ran out of input

It seems like the pickling within the multiprocessing library is causing the crash. I would appreciate any ideas on how to fix it.

In the file monet_model.py
I believe line 123 should be
self.loss_mask = self.criterionKL(self.m_tilde_logits.softmax(dim=1), self.m)
instead of
self.loss_mask = self.criterionKL(self.m_tilde_logits.log_softmax(dim=1), self.m)
since self.m is in the probability space and m_tilde should also be in the probability space not log-prob right?

Hi Darwin, I hope you are doing well. I have been using your codebase Genesis for several days but I got into some problems when I use my own dataset. In particular, below is the screenshot of my result when I use Monet. The desired behavior is that each object is mapped to one corresponding mask and representation slot, which is indeed the case when I use the dSprite dataset. However, when I use my own dataset, all objects are mapped to the same mask and the same slot. Could you please point out what's going on and which parameters I should change? Thanks in advance.

I want to use my own datasets to train Monet? Could you give me some suggestions? So appreciated!

https://github.com/baudm/MONet-pytorch/blob/75239c6e74e4947b6728ffb615e8e81b24718a7e/models/monet_model.py#L86C33-L86C33

log_s_k += -alpha_logits_k + log_alpha_k
why is scope computed this way, it is not equivalent to s_k = s_k * (1-alpha_k) in the paper