NVIDIA GPU-REST-Engine Issue

AI & Data Science Deep Learning (Training & Inference) DIGITS
, , ,
#1

Hi, I am trying to setup the NVIDIA GPU-REST-Engine (GitHub - NVIDIA/gpu-rest-engine: A REST API for Caffe using Docker and Go) from NVIDIA’s GitHub and have had issues. As I run the following command:

sudo docker build -t inference_server -f Dockerfile.caffe_server .

To perform the caffe build as outlined, I continue to receive the same error on step 7/26.


...7%, 17 MB, 13 KB/s, 1261 seconds passedTraceback (most recent call last):
  File "/caffe/scripts/download_model_binary.py", line 74, in <module>
    frontmatter['caffemodel_url'], model_filename, reporthook)
  File "/usr/lib/python2.7/urllib.py", line 98, in urlretrieve
    return opener.retrieve(url, filename, reporthook, data)
  File "/usr/lib/python2.7/urllib.py", line 292, in retrieve
    "of %i bytes" % (read, size), result)
urllib.ContentTooShortError: retrieval incomplete: got only 17831848 out of 243862418 bytes
The command '/bin/sh -c /caffe/scripts/download_model_binary.py /caffe/models/bvlc_reference_caffenet &                                                                                                                                      &     /caffe/data/ilsvrc12/get_ilsvrc_aux.sh' returned a non-zero code: 1

Any help would be greatly appreciated!