Open ngluna opened 4 years ago
I got the same error. Error message from this cell
predictor = estimator_eval.deploy(initial_instance_count=1,
instance_type='ml.t3.medium',
source_dir='src',
entry_point='deploy-mxnet-coach.py')
is not too illuminating
Exception in thread Thread-10:
Traceback (most recent call last):
File "/home/ec2-user/anaconda3/envs/mxnet_p36/lib/python3.6/site-packages/sagemaker/local/image.py", line 618, in run
_stream_output(self.process)
File "/home/ec2-user/anaconda3/envs/mxnet_p36/lib/python3.6/site-packages/sagemaker/local/image.py", line 677, in _stream_output
raise RuntimeError("Process exited with code: %s" % exit_code)
RuntimeError: Process exited with code: 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/ec2-user/anaconda3/envs/mxnet_p36/lib/python3.6/threading.py", line 916, in _bootstrap_inner
self.run()
File "/home/ec2-user/anaconda3/envs/mxnet_p36/lib/python3.6/site-packages/sagemaker/local/image.py", line 623, in run
raise RuntimeError(msg)
RuntimeError: Failed to run: ['docker-compose', '-f', '/tmp/tmp62zck2uq/docker-compose.yaml', 'up', '--build', '--abort-on-container-exit'], Process exited with code: 1
In notebook: https://github.com/awslabs/amazon-sagemaker-examples/blob/master/reinforcement_learning/rl_hvac_coach_energyplus/rl_hvac_coach_energyplus.ipynb
Model deployment is unsuccessful. Testing the model endpoint with
action, action_mean, action_std = predictor.predict(np.array([0., 0., 2.,]))
Returns:
AttributeError: 'NoneType' object has no attribute 'predict'
To reproduce error: