Closed chrispugmire closed 5 years ago
Okay so if you're getting errors like:
WARNING:root:Setting up a new session...
Exception in user code:
------------------------------------------------------------
Traceback (most recent call last):
File "/usr/lib/python3.7/site-packages/urllib3/connection.py", line 160, in _new_conn
(self._dns_host, self.port), self.timeout, **extra_kw)
File "/usr/lib/python3.7/site-packages/urllib3/util/connection.py", line 80, in create_connection
raise err
File "/usr/lib/python3.7/site-packages/urllib3/util/connection.py", line 70, in create_connection
sock.connect(sa)
ConnectionRefusedError: [Errno 111] Connection refused
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.7/site-packages/urllib3/connectionpool.py", line 603, in urlopen
chunked=chunked)
File "/usr/lib/python3.7/site-packages/urllib3/connectionpool.py", line 355, in _make_request
conn.request(method, url, **httplib_request_kw)
File "/usr/lib/python3.7/http/client.py", line 1229, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/usr/lib/python3.7/http/client.py", line 1275, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/usr/lib/python3.7/http/client.py", line 1224, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/usr/lib/python3.7/http/client.py", line 1016, in _send_output
self.send(msg)
File "/usr/lib/python3.7/http/client.py", line 956, in send
self.connect()
File "/usr/lib/python3.7/site-packages/urllib3/connection.py", line 183, in connect
conn = self._new_conn()
File "/usr/lib/python3.7/site-packages/urllib3/connection.py", line 169, in _new_conn
self, "Failed to establish a new connection: %s" % e)
urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPConnection object at 0x7ff8f661e630>: Failed to establish a new connection: [Errno 111] Connection refused
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.7/site-packages/requests/adapters.py", line 449, in send
timeout=timeout
File "/usr/lib/python3.7/site-packages/urllib3/connectionpool.py", line 641, in urlopen
_stacktrace=sys.exc_info()[2])
File "/usr/lib/python3.7/site-packages/urllib3/util/retry.py", line 399, in increment
raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /env/main (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7ff8f661e630>: Failed to establish a new connection: [Errno 111] Connection refused'))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.7/site-packages/visdom/__init__.py", line 548, in _send
data=json.dumps(msg),
File "/usr/lib/python3.7/site-packages/requests/sessions.py", line 581, in post
return self.request('POST', url, data=data, json=json, **kwargs)
File "/usr/lib/python3.7/site-packages/requests/sessions.py", line 533, in request
resp = self.send(prep, **send_kwargs)
File "/usr/lib/python3.7/site-packages/requests/sessions.py", line 646, in send
r = adapter.send(request, **kwargs)
File "/usr/lib/python3.7/site-packages/requests/adapters.py", line 516, in send
raise ConnectionError(e, request=request)
requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /env/main (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7ff8f661e630>: Failed to establish a new connection: [Errno 111] Connection refused'))
ERROR:visdom:[Errno 111] Connection refused
These are cause visdom server has not been started.
Other than that, there is an exception at:
loss_value = loss.data[0]
File "./copy_task.py", line 217, in <module>
loss_value = loss.data[0]
IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number
This is apparently something that has changed in pytorch transition from 0.3 to 0.4. The fix is simply using loss.item()
instead of loss.data[0]
as stated in the error.
BTW if you're not interested in plotting, you can ignore visdom errors.
OH wow, I so appreciate that you took a look at this. Sorry I was probably not clear enough, the problem only occurs when you add -iterations 100 so that the task finishes, then it runs the code to test the model and that code is faulty as input_size isn't defined, and the function doesn't return loss_weights.
python copy_task.py -cuda 0 -optim rmsprop -batch_size 32 -mem_slot 64 -iterations 100
Iteration 0/100
Traceback (most recent call last):
File "copy_task.py", line 366, in <module>
input_data, target_output, loss_weights = generate_data(random_length, input_size)
NameError: name 'input_size' is not defined
So I changed as follows: (I'm assuming batch size should be 1 for a test)
input_data, target_output = generate_data(1,random_length, args.input_size)
But that fails thusly:
File "copy_task.py", line 371, in <module>
output, (chx, mhx, rv) = rnn(input_data, (None, mhx, None), reset_experience=True, pass_through_memory=True)
File "C:\Users\chrisp\Anaconda3\envs\fastai\lib\site-packages\torch\nn\modules\module.py", line 489, in __call__
result = self.forward(*input, **kwargs)
File "C:\Users\chrisp\Anaconda3\envs\fastai\lib\site-packages\dnc\dnc.py", line 235, in forward
inputs = [T.cat([input[:, x, :], last_read], 1) for x in range(max_length)]
File "C:\Users\chrisp\Anaconda3\envs\fastai\lib\site-packages\dnc\dnc.py", line 235, in <listcomp>
inputs = [T.cat([input[:, x, :], last_read], 1) for x in range(max_length)]
RuntimeError: Expected object of backend CPU but got backend CUDA for sequence element 1 in sequence argument at position #1 'tensors'
So changed like this: (making batch_size the same as the training) input_data, target_output = generate_data(args.batch_size,random_length, args.input_size)
Then it fails thusly:
Iteration 0/100
Traceback (most recent call last):
File "copy_task.py", line 371, in <module>
output, (chx, mhx, rv) = rnn(input_data, (None, mhx, None), reset_experience=True, pass_through_memory=True)
File "C:\Users\chrisp\Anaconda3\envs\fastai\lib\site-packages\torch\nn\modules\module.py", line 489, in __call__
result = self.forward(*input, **kwargs)
File "C:\Users\chrisp\Anaconda3\envs\fastai\lib\site-packages\dnc\dnc.py", line 235, in forward
inputs = [T.cat([input[:, x, :], last_read], 1) for x in range(max_length)]
File "C:\Users\chrisp\Anaconda3\envs\fastai\lib\site-packages\dnc\dnc.py", line 235, in <listcomp>
inputs = [T.cat([input[:, x, :], last_read], 1) for x in range(max_length)]
RuntimeError: Expected object of backend CPU but got backend CUDA for sequence element 1 in sequence argument at position #1 'tensors'
At which point I'm completely lost :-)
Actually, after a bit more poking, is that code just copied from the adding_task source and completely unrelated to the copy_task... it just looks very wrong?
Thanks in advance for your time! I realize I don't know what I'm doing here :-)
testing with command line:
python copy_task.py -cuda 0 -lr 0.001 -rnn_type lstm -nlayer 1 -nhlayer 2 -dropout 0 -mem_slot 32 -batch_size 1000 -optim adam -sequence_max_length 8 -iterations 100
I get multiple errors when it finishes, first on the generate_data call which has undefined parameters:
NameError: name 'input_size' is not defined
And then after fixing that I get: output = output[:, -1, :].sum().data.cpu().numpy()[0] IndexError: too many indices for array
Looks like that bit of code hasn't been used. I have tried to fix it but I'm unclear of the solution for the second issue as I'm new to pytorch, thanks in advance for any fixes.
ChrisP.