Is It Possible To Run Caffe Models On The Data-set Which Is Not Stored In Data-source Like Lmdb?

I have 2 sets of image patches data i.e. training and testing sets. Both of these have been written to LMDB files. I am running convolutional neurall network on this data using Caf

Solution 1:

You can write your own python data layer. See discussions here and implementation for of input data layer for video stream here.

Basically you will need add to you network description layer like:

layer {
  type: 'Python'
  name: 'data'
  top: 'data'
  top: 'label'
  python_param {
    # the module name -- usually the filename -- that needs to be in $PYTHONPATH
    module: 'filename'# the layer name -- the class name in the module
    layer: 'CustomInputDataLayer'
  }
}

and implement the layer interface in Python:

classCustomInputDataLayer(caffe.Layer):defsetup(self):
         ...

    defreshape(self, bottom, top)
        top[0].reshape(BATCH_SIZE, your_data.shape)
        top[1].reshape(BATCH_SIZE, your_label.shape)

    defforward(self, bottom, top):
        # assign output
        top[0].data[...] = your_data
        top[1].data[...] = your_label

    defbackward(self, top, propagate_down, bottom):
        pass

Solution 2:

Other than defining custom python layers, you can use the following options:

• use ImageData layer: it has a source parameter (source: name of a text file, with each line giving an image filename and label)

• use MemoryData layer: using which you can load input images directly from memory to your network using ‘setinputarrays‘ method in python. Be cautious about using this layer as it only accepts labels which are single values and you cannot use images as labels (e.g. In semantic segmentation)

• use a deploy version of your network like this:

  input:"data"input_shape {
  dim:n# batch sizedim:c# number of channelsdim:r# image size1dim:w# image size2
  }
  
  input:"label"input_shape {
  dim:n# batch sizedim:c# number of channelsdim:r# label image size1dim:w# label image size2
  }
   ...#your other layers to follow

• use an HDF5 input layer (more or less ine lmdb, but lmdb is more computationally efficient)

You can find the details of these layers here: http://caffe.berkeleyvision.org/tutorial/layers.html

There are examples available online as well.