Deploy YOLOv5 in sagemaker - ModelError: InvokeEndpoint operation: Received server error (0)

I'm trying to deploy custom trained Yolov5 model in Sagemaker for inference. (Note : The model was not trained in sagemaker).

Followed this doc for deploying the model and inference script - Sagemaker docs

ModelError                                Traceback (most recent call last)
<ipython-input-7-063ca701eab7> in <module>
----> 1 result1=predictor.predict("FILE0032.JPG")
      2 print(result1)

~/anaconda3/envs/python3/lib/python3.6/site-packages/sagemaker/predictor.py in predict(self, data, initial_args, target_model, target_variant, inference_id)
    159             data, initial_args, target_model, target_variant, inference_id
    160         )
--> 161         response = self.sagemaker_session.sagemaker_runtime_client.invoke_endpoint(**request_args)
    162         return self._handle_response(response)
    163 

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py in _api_call(self, *args, **kwargs)
    399                     "%s() only accepts keyword arguments." % py_operation_name)
    400             # The "self" in this scope is referring to the BaseClient.
--> 401             return self._make_api_call(operation_name, kwargs)
    402 
    403         _api_call.__name__ = str(py_operation_name)

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py in _make_api_call(self, operation_name, api_params)
    729             error_code = parsed_response.get("Error", {}).get("Code")
    730             error_class = self.exceptions.from_code(error_code)
--> 731             raise error_class(parsed_response, operation_name)
    732         else:
    733             return parsed_response

ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received server error (0) from primary with message "Your invocation timed out while waiting for a response from container primary. Review the latency metrics for each container in Amazon CloudWatch, resolve the issue, and try again.". See https://ap-south-1.console.aws.amazon.com/cloudwatch/home?region=ap-south-1#logEventViewer:group=/aws/sagemaker/Endpoints/pytorch-inference-2022-06-14-11-58-04-086 in account 772044684908 for more information.

After researching about InvokeEndpoint, tried this

import boto3

sagemaker_runtime = boto3.client("sagemaker-runtime", region_name='ap-south-1')
endpoint_name='pytorch-inference-2022-06-14-11-58-04-086'
response = sagemaker_runtime.invoke_endpoint(
                            EndpointName=endpoint_name, 
                            Body=bytes('{"features": ["This is great!"]}', 'utf-8') # Replace with your own data.
                            )
print(response['Body'].read().decode('utf-8'))

But this didn't help as well,

detailed output :

ReadTimeoutError                          Traceback (most recent call last)
<ipython-input-8-b5ca204734c4> in <module>
     12 response = sagemaker_runtime.invoke_endpoint(
     13                             EndpointName=endpoint_name,
---> 14                             Body=bytes('{"features": ["This is great!"]}', 'utf-8') # Replace with your own data.
     15                             )
     16 

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py in _api_call(self, *args, **kwargs)
    399                     "%s() only accepts keyword arguments." % py_operation_name)
    400             # The "self" in this scope is referring to the BaseClient.
--> 401             return self._make_api_call(operation_name, kwargs)
    402 
    403         _api_call.__name__ = str(py_operation_name)

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py in _make_api_call(self, operation_name, api_params)
    716             apply_request_checksum(request_dict)
    717             http, parsed_response = self._make_request(
--> 718                 operation_model, request_dict, request_context)
    719 
    720         self.meta.events.emit(

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py in _make_request(self, operation_model, request_dict, request_context)
    735     def _make_request(self, operation_model, request_dict, request_context):
    736         try:
--> 737             return self._endpoint.make_request(operation_model, request_dict)
    738         except Exception as e:
    739             self.meta.events.emit(

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py in make_request(self, operation_model, request_dict)
    105         logger.debug("Making request for %s with params: %s",
    106                      operation_model, request_dict)
--> 107         return self._send_request(request_dict, operation_model)
    108 
    109     def create_request(self, params, operation_model=None):

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py in _send_request(self, request_dict, operation_model)
    182             request, operation_model, context)
    183         while self._needs_retry(attempts, operation_model, request_dict,
--> 184                                 success_response, exception):
    185             attempts += 1
    186             self._update_retries_context(

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py in _needs_retry(self, attempts, operation_model, request_dict, response, caught_exception)
    306             event_name, response=response, endpoint=self,
    307             operation=operation_model, attempts=attempts,
--> 308             caught_exception=caught_exception, request_dict=request_dict)
    309         handler_response = first_non_none_response(responses)
    310         if handler_response is None:

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/hooks.py in emit(self, event_name, **kwargs)
    356     def emit(self, event_name, **kwargs):
    357         aliased_event_name = self._alias_event_name(event_name)
--> 358         return self._emitter.emit(aliased_event_name, **kwargs)
    359 
    360     def emit_until_response(self, event_name, **kwargs):

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/hooks.py in emit(self, event_name, **kwargs)
    227                  handlers.
    228         """
--> 229         return self._emit(event_name, kwargs)
    230 
    231     def emit_until_response(self, event_name, **kwargs):

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/hooks.py in _emit(self, event_name, kwargs, stop_on_response)
    210         for handler in handlers_to_call:
    211             logger.debug('Event %s: calling handler %s', event_name, handler)
--> 212             response = handler(**kwargs)
    213             responses.append((handler, response))
    214             if stop_on_response and response is not None:

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/retryhandler.py in __call__(self, attempts, response, caught_exception, **kwargs)
    192             checker_kwargs.update({'retries_context': retries_context})
    193 
--> 194         if self._checker(**checker_kwargs):
    195             result = self._action(attempts=attempts)
    196             logger.debug("Retry needed, action of: %s", result)

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/retryhandler.py in __call__(self, attempt_number, response, caught_exception, retries_context)
    266 
    267         should_retry = self._should_retry(attempt_number, response,
--> 268                                           caught_exception)
    269         if should_retry:
    270             if attempt_number >= self._max_attempts:

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/retryhandler.py in _should_retry(self, attempt_number, response, caught_exception)
    292             # If we've exceeded the max attempts we just let the exception
    293             # propogate if one has occurred.
--> 294             return self._checker(attempt_number, response, caught_exception)
    295 
    296 

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/retryhandler.py in __call__(self, attempt_number, response, caught_exception)
    332         for checker in self._checkers:
    333             checker_response = checker(attempt_number, response,
--> 334                                        caught_exception)
    335             if checker_response:
    336                 return checker_response

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/retryhandler.py in __call__(self, attempt_number, response, caught_exception)
    232         elif caught_exception is not None:
    233             return self._check_caught_exception(
--> 234                 attempt_number, caught_exception)
    235         else:
    236             raise ValueError("Both response and caught_exception are None.")

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/retryhandler.py in _check_caught_exception(self, attempt_number, caught_exception)
    374         # the MaxAttemptsDecorator is not interested in retrying the exception
    375         # then this exception just propogates out past the retry code.
--> 376         raise caught_exception

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py in _do_get_response(self, request, operation_model, context)
    247             http_response = first_non_none_response(responses)
    248             if http_response is None:
--> 249                 http_response = self._send(request)
    250         except HTTPClientError as e:
    251             return (None, e)

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py in _send(self, request)
    319 
    320     def _send(self, request):
--> 321         return self.http_session.send(request)
    322 
    323 

~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/httpsession.py in send(self, request)
    449             raise ConnectTimeoutError(endpoint_url=request.url, error=e)
    450         except URLLib3ReadTimeoutError as e:
--> 451             raise ReadTimeoutError(endpoint_url=request.url, error=e)
    452         except ProtocolError as e:
    453             raise ConnectionClosedError(

ReadTimeoutError: Read timeout on endpoint URL: "https://runtime.sagemaker.ap-south-1.amazonaws.com/endpoints/pytorch-inference-2022-06-14-11-58-04-086/invocations"