Training is interspersed with ConnectionErrors

[9thDimension]

Just doing a first test run on the facades data before using my own dataset. The training seems to be progressing slowly. But it looks like each epoch I see an error:

/home/sal9000/virtualenvs/pytorch_seg_env/bin/python /home/sal9000/Sources/pytorch-CycleGAN-and-pix2pix/train.py --dataroot /home/sal9000/Sources/pytorch-CycleGAN-and-pix2pix/datasets/datasets/facades --name facades_peex2peex --model pix2pix --which_model_netG unet_256 --which_direction AtoB --lambda_A 100 --dataset_mode aligned --no_lsgan --norm batch --pool_size 0 --gpu_ids -1
------------ Options -------------
batchSize: 1
beta1: 0.5
checkpoints_dir: ./checkpoints
continue_train: False
dataroot: /home/sal9000/Sources/pytorch-CycleGAN-and-pix2pix/datasets/datasets/facades
dataset_mode: aligned
display_freq: 400
display_id: 1
display_ncols: 4
display_port: 8097
display_server: http://localhost
display_winsize: 256
epoch_count: 1
fineSize: 256
gpu_ids: []
init_type: normal
input_nc: 3
isTrain: True
lambda_A: 100.0
lambda_B: 10.0
lambda_identity: 0.5
loadSize: 286
lr: 0.0002
lr_decay_iters: 50
lr_policy: lambda
max_dataset_size: inf
model: pix2pix
nThreads: 4
n_layers_D: 3
name: facades_peex2peex
ndf: 64
ngf: 64
niter: 100
niter_decay: 100
no_dropout: False
no_flip: False
no_html: False
no_lsgan: True
norm: batch
output_nc: 3
phase: train
pool_size: 0
print_freq: 100
resize_or_crop: resize_and_crop
save_epoch_freq: 5
save_latest_freq: 5000
serial_batches: False
suffix: 
update_html_freq: 1000
verbose: False
which_direction: AtoB
which_epoch: latest
which_model_netD: basic
which_model_netG: unet_256
-------------- End ----------------
CustomDatasetDataLoader
dataset [AlignedDataset] was created
#training images = 400
initialize network with normal
initialize network with normal
model [Pix2PixModel] was created
---------- Networks initialized -------------
[Network G] Total number of parameters : 54.414 M
[Network D] Total number of parameters : 2.769 M
-----------------------------------------------
create web directory ./checkpoints/facades_peex2peex/web...
(epoch: 1, iters: 100, time: 3.225, data: 0.076) G_GAN: 3.367 G_L1: 29.776 D_real: 0.047 D_fake: 0.053 
Exception in user code:
Traceback (most recent call last):
------------------------------------------------------------
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/visdom/__init__.py", line 388, in _send
    data=json.dumps(msg),
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/api.py", line 112, in post
    return request('post', url, data=data, json=json, **kwargs)
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/api.py", line 58, in request
    return session.request(method=method, url=url, **kwargs)
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/sessions.py", line 508, in request
    resp = self.send(prep, **send_kwargs)
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/sessions.py", line 618, in send
    r = adapter.send(request, **kwargs)
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/adapters.py", line 508, in send
    raise ConnectionError(e, request=request)
ConnectionError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /events (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f9050a18110>: Failed to establish a new connection: [Errno 111] Connection refused',))
(epoch: 1, iters: 200, time: 6.900, data: 0.001) G_GAN: 3.504 G_L1: 59.496 D_real: 0.009 D_fake: 0.272 
Traceback (most recent call last):
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/visdom/__init__.py", line 388, in _send
    data=json.dumps(msg),
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/api.py", line 112, in post
    return request('post', url, data=data, json=json, **kwargs)
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/api.py", line 58, in request
    return session.request(method=method, url=url, **kwargs)
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/sessions.py", line 508, in request
    resp = self.send(prep, **send_kwargs)
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/sessions.py", line 618, in send
    r = adapter.send(request, **kwargs)
  File "/home/sal9000/virtualenvs/pytorch_seg_env/local/lib/python2.7/site-packages/requests/adapters.py", line 508, in send
    raise ConnectionError(e, request=request)
ConnectionError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /events (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f9050a46a50>: Failed to establish a new connection: [Errno 111] Connection refused',))
Exception in user code:
------------------------------------------------------------

[ACUPSUN]

run python -m visdom.server，then run your code

[junyanz]

Yes. See #230 for more details.