DenseNet Pretrained Weight conversion

[ahundt]

I'm interested in converting the pretrained weights of DenseNet.

I adapted the instructions at:
https://github.com/nicolov/segmentation_keras/tree/master/conversion

However this runs into the following problem:

± sudo docker run -v `pwd`:/workspace -ti `docker build -q .`
Traceback (most recent call last):
  File "./convert.py", line 60, in <module>
    main()
  File "./convert.py", line 56, in main
    args.phase)
  File "./convert.py", line 27, in convert
    transformer = TensorFlowTransformer(def_path, caffemodel_path, phase=phase)
  File "/workspace/caffe-tensorflow/kaffe/tensorflow/transformer.py", line 221, in __init__
    self.load(def_path, data_path, phase)
  File "/workspace/caffe-tensorflow/kaffe/tensorflow/transformer.py", line 227, in load
    graph = GraphBuilder(def_path, phase).build()
  File "/workspace/caffe-tensorflow/kaffe/graph.py", line 140, in __init__
    self.load()
  File "/workspace/caffe-tensorflow/kaffe/graph.py", line 146, in load
    text_format.Merge(def_file.read(), self.params)
  File "/usr/local/lib/python2.7/dist-packages/google/protobuf/text_format.py", line 476, in Merge
    descriptor_pool=descriptor_pool)
  File "/usr/local/lib/python2.7/dist-packages/google/protobuf/text_format.py", line 526, in MergeLines
    return parser.MergeLines(lines, message)
  File "/usr/local/lib/python2.7/dist-packages/google/protobuf/text_format.py", line 559, in MergeLines
    self._ParseOrMerge(lines, message)
  File "/usr/local/lib/python2.7/dist-packages/google/protobuf/text_format.py", line 574, in _ParseOrMerge
    self._MergeField(tokenizer, message)
  File "/usr/local/lib/python2.7/dist-packages/google/protobuf/text_format.py", line 675, in _MergeField
    merger(tokenizer, message, field)
  File "/usr/local/lib/python2.7/dist-packages/google/protobuf/text_format.py", line 764, in _MergeMessageField
    self._MergeField(tokenizer, sub_message)
  File "/usr/local/lib/python2.7/dist-packages/google/protobuf/text_format.py", line 675, in _MergeField
    merger(tokenizer, message, field)
  File "/usr/local/lib/python2.7/dist-packages/google/protobuf/text_format.py", line 764, in _MergeMessageField
    self._MergeField(tokenizer, sub_message)
  File "/usr/local/lib/python2.7/dist-packages/google/protobuf/text_format.py", line 643, in _MergeField
    (message_descriptor.full_name, name))
google.protobuf.text_format.ParseError: 54:5 : Message type "caffe.PoolingParameter" has no field named "ceil_mode".

Which is due to the ceil_mode param as per shicai/DenseNet-Caffe#1 which requires this caffe pull request https://github.com/BVLC/caffe/pull/3057/files

[flyyufelix]

You have to manually add ceil mode to caffe. See this commit:

https://github.com/BVLC/caffe/pull/3057/files

Then you have to recompile Caffe and use the caffe_pb2.py (located at python/caffe/proto) to read protobuf content (i.e. caffemodel) with python.

[ahundt]

Oh because the dockerfile will not check out the version with ceil mode support... how tricky! I wonder why they don't merge that PR it has been there for ages. :-/