Caffe only trains for one label

Question

This is really weird. I'm implementing this model:

Except that I read data from a text file using an ImageData blob, batch_size: 1. There are only two labels and the text file is organized as usual

/home/.../pathToFile 0
...
/home/.../pathToFile 1

Still, Caffe only trains and tests label 0!

I run caffe using the regular tool.

./build/tools/caffe train --solver=solver.prototxt

When I open the net in pycaffe I get this message for the first time ever:

WARNING: Logging before InitGoogleLogging() is written to STDERR

and the size of the net.blobs['label'].data is now 1, when it should be 2!

Not only that but that label seems to be a float rather than an integer.

In: net.blobs['label'].data
Out: array([ 0.], dtype=float32)

I know that this has worked before, I just can't get my head around what I'm doing wrong or where to begin troubleshoot.

if your batch_size is 1 what do you expect label shape to be?? — Shai
After I changed the batch_size, label gets the right number of elements. Thank you, Shai! However, net.forward still outputs a vector of length 1. — V.Vocor
it outputs the loss, this is a scalar regardless of input size. — Shai
you can replace SoftmaxWithLoss layer with a simple Softmax layer to get the class probability per input — Shai

Shai Shai · Accepted Answer · 2016-02-21T10:49:27

The output shape of your network depends on the input batch_size: if you define batch_size: 1 than your net processes a single example each time, thus it only reads a single label. If you change batch_size to 2, caffe will read two samples and consequently the shape of label will become 2.
One exception to this "shape rule" is the loss output: the loss defines a scalar function with respect to which gradients are computed. Thus, the loss output will always be a scalar regardless of the input shape.

Regarding the data type of label: Caffe stores all variables in "Blobs" of type float32.

Caffe only trains for one label

1 Answers