Memtorch Non-writeable tensors

[Sunrobbie]

Hello, I'm a college student attempting to get memtorch up and running on my computer. I first tried to get the CUDA version running, but ended up switching to the CPU version of memtorch. Currently, I'm getting the following error/series of errors:

C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torchvision\datasets\mnist.py:498:` UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at  ..\torch\csrc\utils\tensor_numpy.cpp:180.)
  return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)
C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torchvision\datasets\mnist.py:498: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at  ..\torch\csrc\utils\tensor_numpy.cpp:180.)
  return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 116, in spawn_main
    exitcode = _main(fd, parent_sentinel)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 125, in _main
    prepare(preparation_data)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 236, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
    main_content = runpy.run_path(main_path,
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 268, in run_path
    return _run_module_code(code, init_globals, run_name,
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 97, in _run_module_code
    _run_code(code, mod_globals, init_globals,
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "c:\Users\sunro\testing.py", line 55, in <module>
    for batch_idx, (data, target) in enumerate(train_loader):
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 359, in __iter__
    return self._get_iterator()
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 305, in _get_iterator
    return _MultiProcessingDataLoaderIter(self)
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 918, in __init__
    w.start()
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\process.py", line 121, in start
    self._popen = self._Popen(self)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\context.py", line 224, in _Popen
    return _default_context.get_context().Process._Popen(process_obj)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\context.py", line 327, in _Popen
    return Popen(process_obj)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\popen_spawn_win32.py", line 45, in __init__
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
    _check_not_importing_main()
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
    raise RuntimeError('''
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.
C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torchvision\datasets\mnist.py:498: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at  ..\torch\csrc\utils\tensor_numpy.cpp:180.)
  return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)
Epoch: [1]              Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 116, in spawn_main
    exitcode = _main(fd, parent_sentinel)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 125, in _main
    prepare(preparation_data)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 236, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
    main_content = runpy.run_path(main_path,
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 268, in run_path
    return _run_module_code(code, init_globals, run_name,
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 97, in _run_module_code
    _run_code(code, mod_globals, init_globals,
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "c:\Users\sunro\testing.py", line 55, in <module>
    for batch_idx, (data, target) in enumerate(train_loader):
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 359, in __iter__
    return self._get_iterator()
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 305, in _get_iterator
    return _MultiProcessingDataLoaderIter(self)
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 918, in __init__
    w.start()
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\process.py", line 121, in start
    self._popen = self._Popen(self)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\context.py", line 224, in _Popen
    return _default_context.get_context().Process._Popen(process_obj)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\context.py", line 327, in _Popen
    return Popen(process_obj)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\popen_spawn_win32.py", line 45, in __init__
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
    _check_not_importing_main()
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
    raise RuntimeError('''
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.
Epoch: [1]              Epoch: [1]              Traceback (most recent call last):
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 990, in _try_get_data
    data = self._data_queue.get(timeout=timeout)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.9_3.9.2032.0_x64__qbz5n2kfra8p0\lib\multiprocessing\queues.py", line 114, in get
    raise Empty
_queue.Empty

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "c:\Users\sunro\testing.py", line 55, in <module>
    for batch_idx, (data, target) in enumerate(train_loader):
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 521, in __next__
    data = self._next_data()
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 1186, in _next_data
    idx, data = self._get_data()
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 1152, in _get_data
    success, data = self._try_get_data()
  File "C:\Users\sunro\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\LocalCache\local-packages\Python39\site-packages\torch\utils\data\dataloader.py", line 1003, in _try_get_data
    raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str)) from e
RuntimeError: DataLoader worker (pid(s) 22916, 15700) exited unexpectedly

I'm trying to run the python code from the tutorial in this instance.

[coreylammie]

Hi @Sunrobbie,

When using Python multiprocessing with Windows, your code should be wrapped in a if __name__ == '__main__': statement. In your particular instance, it appears that the following lines of code are causing the aforementioned errors (as the number of workers is 2 by default, and hence multiprocessing is used):

MemTorch/memtorch/utils.py

Lines 137 to 151 in 0dfdbe1

	train_loader = torch.utils.data.DataLoader(
	train_set, batch_size=batch_size, shuffle=True, num_workers=2
	)
	validation_loader = torch.utils.data.DataLoader(
	validation_set, batch_size=batch_size, shuffle=True, num_workers=2
	)
	else:
	train_loader = torch.utils.data.DataLoader(
	full_train_set, batch_size=batch_size, shuffle=True, num_workers=2
	)
	validation_loader = None
	test_loader = torch.utils.data.DataLoader(
	test_set, batch_size=int(batch_size / 2), shuffle=False, num_workers=2
	)

Could you please try encapsulating the tutorial code in a if __name__ == '__main__': statement and notifying me if this fixes your problem? For the training cell, the code could look as follows:

import torch
from torch.autograd import Variable
import memtorch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from memtorch.utils import LoadMNIST
import numpy as np

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5, 1)
        self.conv2 = nn.Conv2d(20, 50, 5, 1)
        self.fc1 = nn.Linear(4*4*50, 500)
        self.fc2 = nn.Linear(500, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2, 2)
        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2, 2)
        x = x.view(-1, 4*4*50)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

def test(model, test_loader):
    correct = 0
    for batch_idx, (data, target) in enumerate(test_loader):        
        output = model(data.to(device))
        pred = output.data.max(1)[1]
        correct += pred.eq(target.to(device).data.view_as(pred)).cpu().sum()

    return 100. * float(correct) / float(len(test_loader.dataset))

if __name__ == '__main__':
    device = torch.device('cpu' if 'cpu' in memtorch.__version__ else 'cuda')
    epochs = 10
    learning_rate = 1e-1
    step_lr = 5
    batch_size = 256
    train_loader, validation_loader, test_loader = LoadMNIST(batch_size=batch_size, validation=False)
    model = Net().to(device)
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.Adam(model.parameters(), lr=learning_rate)
    best_accuracy = 0
    for epoch in range(0, epochs):
        print('Epoch: [%d]\t\t' % (epoch + 1), end='')
        if epoch % step_lr == 0:
            learning_rate = learning_rate * 0.1
            for param_group in optimizer.param_groups:
                param_group['lr'] = learning_rate

        model.train()
        for batch_idx, (data, target) in enumerate(train_loader):
            optimizer.zero_grad()
            output = model(data.to(device))
            loss = criterion(output, target.to(device))
            loss.backward()
            optimizer.step()

        accuracy = test(model, test_loader)
        print('%2.2f%%' % accuracy)
        if accuracy > best_accuracy:
            torch.save(model.state_dict(), 'trained_model.pt')
            best_accuracy = accuracy

In the next release of MemTorch, I will change the default number of workers to 1 so that the tutorial can be run on Windows without adding this statement, as I understand this behavior can be confusing.

Kind Regards,

Corey.

[Sunrobbie]

Encapsulating it in that if statement fixed the problem, thank you!

[coreylammie]

No problem at all!