DeepDream taking too long to render image

Question

I managed to install #DeepDream in my server.

I have duo core and 2gb Ram. but it taking 1min to process a image of size 100kbp.

Any advice ?

well I though it would take maxim 5secs. @DonReba did you managed to run #DeepDream, if so. how long each render ? — Thiago, Jul 08 '15 at 09:00
Well, apparently it is what it is? Not sure where you get the expectation of 5 seconds. — runDOSrun, Jul 08 '15 at 14:26
@runDOSrun How long it takes on your side to generate the image ? Thanks for your reply — Thiago, Jul 08 '15 at 15:05
@Joolah I ran it on a considerably better machine so it didn't take long. — runDOSrun, Jul 08 '15 at 15:22

score 1 · Answer 1 · answered Jul 15 '15 at 12:31

Do you run it in a Virtual Machine on Windows or OS X? If so, then it's probably not going to work any faster. In a Virtual Machine (I'm using Docker) you're most of the time not able to use CUDA to render the Images. I have the same problem and I'm going to try it by installing Ubuntu and then install the NVidia drivers for CUDA. At the moment I'm rendering 1080p images which are around 300kb and it takes 15 minutes to do 1 image on an Intel core i7 with 8gb of ram.

I have a VM running in DigitalOcean, very slow – Thiago Jul 25 '15 at 03:16 — Thiago, Jul 25 '15 at 03:16

score 0 · Answer 2 · answered Jul 24 '15 at 21:46

0

Unless you can move to a better workstation/get a GPU, you'll have to do with resizing the image.

img = PIL.Image.open('sky1024px.jpg')
img = np.float32(img.resize( [int(0.5 * s) for s in img.size] ))

answered Jul 24 '15 at 21:46

kampta

4,748
5
31
51

score 0 · Answer 3 · edited May 23 '17 at 11:48

Taking 1 minute to process a 100kb image is a sensible turnaround time for #deepdream, and we accept that these renders have an incredibly long baking time. Often, experimental research software will run too slow, hungry for a future of faster computers. That said, there are a couple ways that come to mind about making your setup execute faster.

Thread! Increase thread count with a command line argument. Here's one way to enable multi-threading in Caffe How to enable multithreading with Caffe?
GPU! Install CUDA and switch from CPU rendering to GPU rendering. If your server doesn't have a special GPU, try getting a GPU instance on amazon ec2. https://github.com/BVLC/caffe/wiki/Install-Caffe-on-EC2-from-scratch-(Ubuntu,-CUDA-7,-cuDNN)

Thank you for ur feedback. I will try it. – Thiago Apr 22 '16 at 00:24 — Thiago, Apr 22 '16 at 00:24

score 0 · Answer 4 · answered Sep 28 '16 at 21:00

As a rule of thumb deep learning is hard on both compute and memory resources. A 2gb RAM Core Duo machine is just not a good choice for deep learning. Keep in mind a lot of the people who pioneered this field did much of their research using GTX Titan cards because CPU computation even on xeon servers is prohibitivly slow when training deep learning networks.

DeepDream taking too long to render image

4 Answers4