[Errno 111] Connection refused

[nagitam]

Hi,
I am getting this error
RuntimeError: The shape of the mask [8, 32756] at index 0 does not match the shape of the indexed tensor [262048, 1] at index 0
Exception ignored in: <bound method _DataLoaderIter.del of <torch.utils.data.dataloader._DataLoaderIter object at 0x7f801b6ccf28>>'

I am using pytorch 0.4.0. and python 3.5 anaconda 4.5.9.
Any help? Thanks

[lzx1413]

Please refer to the code of 0.4 branch, I am working on the pytorch 4.1 .

[lxtGH]

Hi! When I train the ssd vgg, I met this error.
Traceback (most recent call last):
File "train_test.py", line 424, in
train()
File "train_test.py", line 289, in train
loss_l, loss_c = criterion(out, priors, targets)
File "/home/lxt/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/lxt/study/PytorchSSD/layers/modules/multibox_loss.py", line 97, in forward
_,loss_idx = loss_c.sort(1, descending=True)
RuntimeError: merge_sort: failed to synchronize: an illegal memory access was encountered
@lzx1413

[nagitam]

Thanks You!

…

On Tue, 25 Sep 2018 at 4:01 pm, lzx1413 ***@***.***> wrote: Please refer to the code of 0.4 branch, I am working on the pytorch 4.1 . — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#48 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AYnAX34FvXgZrrExhU6ioRl6HA7j3x4Bks5uecafgaJpZM4W3n11> .

[lzx1413]

@lxtGH this is because the loss is nan, you can ignore it or reduce the lr_rate to avoid it.

[Eileen2014]

我用的pytorch是0.3.1,cuda8.0,ubuntu16
Traceback (most recent call last):
File "/home/cv2018/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 333, in del
self._shutdown_workers()
File "/home/cv2018/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 319, in _shutdown_workers
self.data_queue.get()
File "/home/cv2018/anaconda3/lib/python3.6/multiprocessing/queues.py", line 337, in get
return _ForkingPickler.loads(res)
File "/home/cv2018/anaconda3/lib/python3.6/site-packages/torch/multiprocessing/reductions.py", line 70, in rebuild_storage_fd
fd = df.detach()
File "/home/cv2018/anaconda3/lib/python3.6/multiprocessing/resource_sharer.py", line 57, in detach
with _resource_sharer.get_connection(self._id) as conn:
File "/home/cv2018/anaconda3/lib/python3.6/multiprocessing/resource_sharer.py", line 87, in get_connection
c = Client(address, authkey=process.current_process().authkey)
File "/home/cv2018/anaconda3/lib/python3.6/multiprocessing/connection.py", line 487, in Client
c = SocketClient(address)
File "/home/cv2018/anaconda3/lib/python3.6/multiprocessing/connection.py", line 614, in SocketClient
s.connect(address)
ConnectionRefusedError: [Errno 111] Connection refused

[moyan007]

Please refer to the code of 0.4 branch, I am working on the pytorch 4.1 .

@lzx1413 ,Hello sir, Did you run the demo correctly on the pytorch 4.1? I try to run the demo on the pytorch 0.4.0, 0.4.1 and 0.3.1 , all of which received the error that [Errno 111] Connection refused . Can you help me with that? Thanks a lot

[weycui]

您好，我也遇到了同样的问题。 是什么原因造成的呢？Ubuntu还是pytorch 版本？

[moyan007]

您好，我也遇到了同样的问题。 是什么原因造成的呢？Ubuntu还是pytorch 版本？

pytorch version

[weycui]

您好，我也遇到了同样的问题。 是什么原因造成的呢？Ubuntu还是pytorch 版本？

pytorch version

麻烦您说一下哪个版本匹配会好一点。 我现在用的是pytorch0.4 python3.6

[moyan007]

您好，我也遇到了同样的问题。 是什么原因造成的呢？Ubuntu还是pytorch 版本？

pytorch version

麻烦您说一下哪个版本匹配会好一点。 我现在用的是pytorch0.4 python3.6

我记得好像0.3.1可以直接运行，0.4+的版本的话改了之后同样可以运行，修改的地方应该是在multiBoxLoss部分

[weycui]

您好，我也遇到了同样的问题。 是什么原因造成的呢？Ubuntu还是pytorch 版本？

pytorch version

麻烦您说一下哪个版本匹配会好一点。 我现在用的是pytorch0.4 python3.6

我记得好像0.3.1可以直接运行，0.4+的版本的话改了之后同样可以运行，修改的地方应该是在multiBoxLoss部分

嗯嗯谢谢，我在仔细阅读一下原码

[InvictusY]

您好，我也遇到了同样的问题。 是什么原因造成的呢？Ubuntu还是pytorch 版本？

您好，请问这个问题您解决了吗？方便给我解答一下吗？

[weycui]

您好，我也遇到了同样的问题。 是什么原因造成的呢？Ubuntu还是pytorch 版本？

您好，请问这个问题您解决了吗？方便给我解答一下吗？

还没有

[weycui]

Please refer to the code of 0.4 branch, I am working on the pytorch 4.1 .

@lzx1413 ,Hello sir, Did you run the demo correctly on the pytorch 4.1? I try to run the demo on the pytorch 0.4.0, 0.4.1 and 0.3.1 , all of which received the error that [Errno 111] Connection refused . Can you help me with that? Thanks a lot

不好意思打扰了，这个链接错误我还是没有解决。请问您是怎么解决的

[miaoshuyu]

RuntimeError: The shape of the mask [8, 32756] at index 0 does not match the shape of the indexed tensor [262048, 1] at index 0
This problem can be solved as followes:
1、
loss_c[pos] = 0
to：
loss_c = loss_c.view(num, -1)
loss_c[pos] = 0

2、
N = num_pos.data.sum()
to:
N = num_pos.data.sum().double()
loss_l = loss_l.double()
loss_c = loss_c.double()