Menu
So I'm trying to figure out Sagemaker and can get an endpoint for a tensorflow model up and running. Strangely enough, when I send small images to it, up to 220x220 (40kb), it runs just fine! However I get a connection closed error when I try anything larger, say 225x225.
I've tried from different networks and computers and get the same error. Also, I don't think I'm anywhere near the 5MB limit for sagemaker requests so I must admit I'm stumped on this one. Anyone happen to know what might be the cause of this? Thanks for your help. I'm calling my model via boto as follows:
config = Config(connect_timeout=999999, read_timeout=9999999)
client = boto3.client("runtime.sagemaker", config=config)
data = {"instances": [{"x":x, "x2":x2}]}
response = client.invoke_endpoint(EndpointName='dcscn',
Body=json.dumps(data),
ContentType="application/json")
response_body = response['Body']
The error I get is:
Traceback (most recent call last):
File "/Users/bhhj/anaconda/lib/python3.6/site-packages/urllib3/connectionpool.py", line 600, in urlopen
chunked=chunked)
File "/Users/bhhj/anaconda/lib/python3.6/site-packages/urllib3/connectionpool.py", line 354, in _make_request
conn.request(method, url, **httplib_request_kw)
File "/Users/bhhj/anaconda/lib/python3.6/http/client.py", line 1239, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/awsrequest.py", line 125, in _send_request
method, url, body, headers, *args, **kwargs)
File "/Users/bhhj/anaconda/lib/python3.6/http/client.py", line 1285, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/Users/bhhj/anaconda/lib/python3.6/http/client.py", line 1234, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/awsrequest.py", line 152, in _send_output
self.send(msg)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/awsrequest.py", line 236, in send
return super(AWSConnection, self).send(str)
File "/Users/bhhj/anaconda/lib/python3.6/http/client.py", line 986, in send
self.sock.sendall(data)
File "/Users/bhhj/anaconda/lib/python3.6/ssl.py", line 975, in sendall
v = self.send(byte_view[count:])
File "/Users/bhhj/anaconda/lib/python3.6/ssl.py", line 944, in send
return self._sslobj.write(data)
File "/Users/bhhj/anaconda/lib/python3.6/ssl.py", line 642, in write
return self._sslobj.write(data)
BrokenPipeError: [Errno 32] Broken pipe
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/httpsession.py", line 258, in send
decode_content=False,
File "/Users/bhhj/anaconda/lib/python3.6/site-packages/urllib3/connectionpool.py", line 638, in urlopen
_stacktrace=sys.exc_info()[2])
File "/Users/bhhj/anaconda/lib/python3.6/site-packages/urllib3/util/retry.py", line 343, in increment
raise six.reraise(type(error), error, _stacktrace)
File "/Users/bhhj/anaconda/lib/python3.6/site-packages/urllib3/packages/six.py", line 685, in reraise
raise value.with_traceback(tb)
File "/Users/bhhj/anaconda/lib/python3.6/site-packages/urllib3/connectionpool.py", line 600, in urlopen
chunked=chunked)
File "/Users/bhhj/anaconda/lib/python3.6/site-packages/urllib3/connectionpool.py", line 354, in _make_request
conn.request(method, url, **httplib_request_kw)
File "/Users/bhhj/anaconda/lib/python3.6/http/client.py", line 1239, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/awsrequest.py", line 125, in _send_request
method, url, body, headers, *args, **kwargs)
File "/Users/bhhj/anaconda/lib/python3.6/http/client.py", line 1285, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/Users/bhhj/anaconda/lib/python3.6/http/client.py", line 1234, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/awsrequest.py", line 152, in _send_output
self.send(msg)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/awsrequest.py", line 236, in send
return super(AWSConnection, self).send(str)
File "/Users/bhhj/anaconda/lib/python3.6/http/client.py", line 986, in send
self.sock.sendall(data)
File "/Users/bhhj/anaconda/lib/python3.6/ssl.py", line 975, in sendall
v = self.send(byte_view[count:])
File "/Users/bhhj/anaconda/lib/python3.6/ssl.py", line 944, in send
return self._sslobj.write(data)
File "/Users/bhhj/anaconda/lib/python3.6/ssl.py", line 642, in write
return self._sslobj.write(data)
urllib3.exceptions.ProtocolError: ('Connection aborted.', BrokenPipeError(32, 'Broken pipe'))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "ping_endpoint.py", line 100, in <module>
ContentType="application/json")
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/client.py", line 357, in _api_call
return self._make_api_call(operation_name, kwargs)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/client.py", line 648, in _make_api_call
operation_model, request_dict, request_context)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/client.py", line 667, in _make_request
return self._endpoint.make_request(operation_model, request_dict)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/endpoint.py", line 102, in make_request
return self._send_request(request_dict, operation_model)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/endpoint.py", line 137, in _send_request
success_response, exception):
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/endpoint.py", line 231, in _needs_retry
caught_exception=caught_exception, request_dict=request_dict)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/hooks.py", line 356, in emit
return self._emitter.emit(aliased_event_name, **kwargs)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/hooks.py", line 228, in emit
return self._emit(event_name, kwargs)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/hooks.py", line 211, in _emit
response = handler(**kwargs)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/retryhandler.py", line 183, in __call__
if self._checker(attempts, response, caught_exception):
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/retryhandler.py", line 251, in __call__
caught_exception)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/retryhandler.py", line 277, in _should_retry
return self._checker(attempt_number, response, caught_exception)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/retryhandler.py", line 317, in __call__
caught_exception)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/retryhandler.py", line 223, in __call__
attempt_number, caught_exception)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/retryhandler.py", line 359, in _check_caught_exception
raise caught_exception
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/endpoint.py", line 200, in _do_get_response
http_response = self._send(request)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/endpoint.py", line 244, in _send
return self.http_session.send(request)
File "/Users/bhhj/.local/lib/python3.6/site-packages/botocore/httpsession.py", line 289, in send
endpoint_url=request.url
botocore.exceptions.ConnectionClosedError: Connection was closed before we received a valid response from endpoint URL:
888
To troubleshoot this error, check the following: Confirm that you're using the correct AWS Region and Amazon S3 endpoint. Verify that your network can connect to those Amazon S3 endpoints. Verify that your DNS can resolve to those Amazon S3 endpoints.
The reason the "Could not connect to the endpoint URL" error occurs is because an incorrect region code is set when running an AWS CLI command. In order to solve the "Could not connect to the endpoint URL" error, set the region to a valid AWS region code, e.g. us-east-1 .
An S3 bucket can be accessed through its URL. The URL format of a bucket is either of two options: http://s3.amazonaws.com/[bucket_name]/ http://[bucket_name].s3.amazonaws.com/
To check that your VPC Endpoint for S3 is working correctly, find the URL of your target bucket in the AWS console and use the hostname there as the target of a traceroute command on one of your virtual machines in your SDDC.
You can get the "Could not connect to the endpoint URL" error if there's a typo or error in the specified Region or endpoint. For example, the following command results in the error because there's an extra "e" in the endpoint name:
Then, the AWS CLI can redirect the request to the bucket's Regional S3 endpoint. You can get the "Could not connect to the endpoint URL" error if there's a typo or error in the specified Region or endpoint. For example, the following command results in the error because there's an extra "e" in the endpoint name:
This is a bug, why is it closed? The default timeout is too small and the error says 'Connection was closed...' has nothing to do with the actual problem: the operation was arbitrarily cancelled before the upload finished because it was too slow.
When you run a command using the AWS CLI, API requests are sent to the default AWS Region's S3 endpoint. Or, API requests are sent to a Region-specific S3 endpoint when the Region is specified in the command.
It can be a network error. If you are connected to a VPN , try after disconnecting it try with better internet connection my case, closing the VPN worked
170
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
