Caffe - Forward multiple images through a net in parallel - neural-network

Question

How exactly would one do this. Right now, I have to iterate through each image and forward it. I would like to know if I can set multiple images at once and forward them through
for f in fnames:
i+=1
print i,"/",len(fnames), f
img = Image.open(f)
# scale all images to 256x256
img = img.resize((256,256), PIL.Image.ANTIALIAS)
img = numpy.array(img).astype(numpy.float32)
transformed_image = transformer.preprocess('data', img)
#print transformed_image.shape
# use CNN to predict (but don't use predicted class)
net.blobs['data'].data[...] = transformed_image
output = net.forward()

Answer 1

You can do this by putting all images into a single batch and then running net.forward() once for the entire batch.
bs = len(fnames) # batch size
in_shape = net.blobs['data'].data.shape
in_shape[0] = bs # set new batch size
net.blobs['data'].reshape(*in_shape)
net.reshape()
for i, f in enumerate(fnames):
img = Image.open(f)
# scale all images to 256x256
img = img.resize((256,256), PIL.Image.ANTIALIAS)
img = numpy.array(img).astype(numpy.float32)
transformed_image = transformer.preprocess('data', img)
#print transformed_image.shape
# put the image into i-th place in batch
net.blobs['data'].data[i,:,:,:] = transformed_image
# after reading all images into batch, forward once:
net.forward()