How to change the batch size dynamically?

[chwangaa]

In pycaffe particular

Is there any ways we can change the batch_size dynamically without modifying the prototxt file ?

I noticed the method reshape, but apparently it does not really change the shape, as after I run forward(), the shape will have be altered back to its original shape

Many thanks

[chwangaa]

Basically I am trying to see the relationship between the batch size and the running time

[seanbell]

You need to reshape the input blob and then call reshape on the net, before calling forward.

[chwangaa]

I did the following
net.blobs['data'].reshape(BLOCK_SIZE, DIMENSION, HEIGHT, WIDTH) net.blobs['label'].reshape(BLOCK_SIZE, ) net.reshape()

The shape of every layer changes correctly. However, as soon as I run forward, the shape will automatically change back :-(

[lukeyeager]

This example may be helpful to you. See the code in forward_pass():

for chunk in [caffe_images[x:x+batch_size] for x in xrange(0, len(caffe_images), batch_size)]:
    new_shape = (len(chunk),) + tuple(dims)
    if net.blobs['data'].data.shape != new_shape:
        net.blobs['data'].reshape(*new_shape)
    for index, image in enumerate(chunk):
        image_data = transformer.preprocess('data', image)
        net.blobs['data'].data[index] = image_data
    output = net.forward()[net.outputs[-1]]

[chwangaa]

Somehow I cannot manage to have it work. I am not trying to classify here. So I used the method suggested above to change the batchSize to 1000. However, the running time of forward does not even slightly alter, (i.e. when I modify the value in prototxt file the running time will be longer). Therefore I think the above method does not work

[shelhamer]

Please discuss usage on caffe-users; I've answered in the thread Regarding Change BatchSize in python.

[shellyfung]

@chwangaa Did you get the answer?

Basically I am trying to see the relationship between the batch size and the running time