About the running time and gpu memory usage
Closed this issue · 6 comments
Hi, @mesnico, could you share the GPU device you used and how long it takes to training this network?
Hi @LMdeLiangMi, I used 2 Tesla K40 GPUs, for a total of 48Gb of VRAM. It took about 30-40 minutes per epoch. I trained for about 350 epochs before reaching a good convergence for the from-pixels version so in the end my training took about 10 days.
I found that the data loader seems so slow because it does the image processing on CPU. I am trying to write a new loader based on Nvidia Dali.
@LMdeLiangMi Never heard about Dali, it seems interesting! However, check your CPU utilization. If it is low, I can tell you that, during my experiments, I observed that the disk was very often the bottleneck. Consider moving the CLEVR dataset onto a solid-state drive, if you haven't yet. You should observe a higher utilization of both CPUs and GPUs, together with an overall training speedup.
@mesnico I put the dataset on memory and use Dali, so now it is okay. By the way, could you tell me why label subs 1 in utils.py?
label = (label - 1).squeeze(1)
@LMdeLiangMi I'm glad you solved the problem.
By the way, could you tell me why label subs 1 in utils.py?
You can see that in the function build_dictionaries() I employed the one-based indexing while constructing the dictionaries, both for the questions and the answers. This is basically because the index 0 is usually reserved for padding (the padding is not necessary for the answers, I did so for consistency with the questions dictionary).
However, while preparing the data for the network, I need to shift back all the answer indexes, otherwise I would have a useless output neuron corresponding to the dummy index 0.
I see. Thanks.