Closed ojasviyadav closed 3 years ago
If you're running the script.py to train, make sure to change "python train.py" to "python3 train.py". I guess I had this issue before and this fixed it.
I have to do this:
cp -r lib/nn models/
then vi models/networks.py
to change the line to:
from .nn import SynchronizedBatchNorm2d as SynBN2d
However, when I run this command:
python scripts/script.py --predict
I saw these errors:
Total number of parameters: 8636675
-----------------------------------------------
model [SingleGANModel] was created
No handlers could be found for logger "visdom"
Exception in user code:
------------------------------------------------------------
Traceback (most recent call last):
File "/usr/local/lib/python2.7/site-packages/visdom/__init__.py", line 711, in _send
data=json.dumps(msg),
File "/usr/local/lib/python2.7/site-packages/visdom/__init__.py", line 677, in _handle_post
r = self.session.post(url, data=data)
File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 572, in post
return self.request('POST', url, data=data, json=json, **kwargs)
File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 524, in request
resp = self.send(prep, **send_kwargs)
File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 637, in send
r = adapter.send(request, **kwargs)
File "/usr/lib/python2.7/dist-packages/requests/adapters.py", line 516, in send
raise ConnectionError(e, request=request)
ConnectionError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /env/main (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f091bea73d0>: Failed to establish a new connection: [Errno 111] Connection refused',))
24
Traceback (most recent call last):
File "predict.py", line 25, in <module>
for i, data in enumerate(dataset):
File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/dataloader.py", line 345, in __next__
data = self._next_data()
File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/usr/local/lib64/python2.7/site-packages/torch/_utils.py", line 394, in reraise
raise self.exc_type(msg)
ZeroDivisionError: Caught ZeroDivisionError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/tmp/gan/EnlightenGAN/data/unaligned_dataset.py", line 82, in __getitem__
B_img = self.B_imgs[index % self.B_size]
ZeroDivisionError: integer division or modulo by zero
You should firstly run python -m visdom.server
to launch a port to receive visual results. Then make sure your dataset path is correct. From the above error message, the dataset length is zero which might be caused by wrong dataset path.
If you're running the script.py to train, make sure to change "python train.py" to "python3 train.py". I guess I had this issue before and this fixed it.
This is not working for me
However, when I run this command:
python scripts/script.py --predict
I saw these errors:
Total number of parameters: 8636675 ----------------------------------------------- model [SingleGANModel] was created No handlers could be found for logger "visdom" Exception in user code: ------------------------------------------------------------ Traceback (most recent call last): File "/usr/local/lib/python2.7/site-packages/visdom/__init__.py", line 711, in _send data=json.dumps(msg), File "/usr/local/lib/python2.7/site-packages/visdom/__init__.py", line 677, in _handle_post r = self.session.post(url, data=data) File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 572, in post return self.request('POST', url, data=data, json=json, **kwargs) File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 524, in request resp = self.send(prep, **send_kwargs) File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 637, in send r = adapter.send(request, **kwargs) File "/usr/lib/python2.7/dist-packages/requests/adapters.py", line 516, in send raise ConnectionError(e, request=request) ConnectionError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /env/main (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f091bea73d0>: Failed to establish a new connection: [Errno 111] Connection refused',)) 24 Traceback (most recent call last): File "predict.py", line 25, in <module> for i, data in enumerate(dataset): File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/dataloader.py", line 345, in __next__ data = self._next_data() File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data return self._process_data(data) File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data data.reraise() File "/usr/local/lib64/python2.7/site-packages/torch/_utils.py", line 394, in reraise raise self.exc_type(msg) ZeroDivisionError: Caught ZeroDivisionError in DataLoader worker process 0. Original Traceback (most recent call last): File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/tmp/gan/EnlightenGAN/data/unaligned_dataset.py", line 82, in __getitem__ B_img = self.B_imgs[index % self.B_size] ZeroDivisionError: integer division or modulo by zero
I fixed the original error. But just like you, I am also getting this error
@ojasviyadav Could you please check whether your dataset path is correct?
However, when I run this command:
python scripts/script.py --predict
I saw these errors:
Total number of parameters: 8636675 ----------------------------------------------- model [SingleGANModel] was created No handlers could be found for logger "visdom" Exception in user code: ------------------------------------------------------------ Traceback (most recent call last): File "/usr/local/lib/python2.7/site-packages/visdom/__init__.py", line 711, in _send data=json.dumps(msg), File "/usr/local/lib/python2.7/site-packages/visdom/__init__.py", line 677, in _handle_post r = self.session.post(url, data=data) File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 572, in post return self.request('POST', url, data=data, json=json, **kwargs) File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 524, in request resp = self.send(prep, **send_kwargs) File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 637, in send r = adapter.send(request, **kwargs) File "/usr/lib/python2.7/dist-packages/requests/adapters.py", line 516, in send raise ConnectionError(e, request=request) ConnectionError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /env/main (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f091bea73d0>: Failed to establish a new connection: [Errno 111] Connection refused',)) 24 Traceback (most recent call last): File "predict.py", line 25, in <module> for i, data in enumerate(dataset): File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/dataloader.py", line 345, in __next__ data = self._next_data() File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data return self._process_data(data) File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data data.reraise() File "/usr/local/lib64/python2.7/site-packages/torch/_utils.py", line 394, in reraise raise self.exc_type(msg) ZeroDivisionError: Caught ZeroDivisionError in DataLoader worker process 0. Original Traceback (most recent call last): File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/usr/local/lib64/python2.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/tmp/gan/EnlightenGAN/data/unaligned_dataset.py", line 82, in __getitem__ B_img = self.B_imgs[index % self.B_size] ZeroDivisionError: integer division or modulo by zero
I also met the same error. Have you solve this problem?
@zhangziyezzy Could you please try to print self.B_size
?
I have recreated a new env and also installed all the packages in requirement.txt. when I just run the test code "python scripts/script.py --predict", it's ok, just like this:
Total number of parameters: 8636675 model [SingleGANModel] was created Setting up a new session... 3 process image... ['../test_dataset/testA/P1000511.jpg'] process image... ['../test_dataset/testA/P1000333.jpg'] process image... ['../test_dataset/testA/P1000205.jpg']
But I could not find where is the output saved
It should be in the results
@xzhub @zhangziyezzy
The error is because of no data placed in testB
. You should put your input images in testA
and at least put one image in testB
.
OK, I find the results of "fake” images in ./ablation
folder.
I'm running Python 3.5. I have also installed all the packages in requirement.txt. I'm getting this error:
I tried to google this error and this repository had 2 issues that are now closed which were similar to this one. In those it was mentioned to install Python3.5 and make sure requirement.txt was fulfilled. I have tried that.
The only difference I had was that I did not start the visdom server because I'm training this on a remote machine using the terminal. But I am not sure if that is causing this issue?