search

ndrplz / dreyeve

[TPAMI 2018] Predicting the Driver’s Focus of Attention: the DR(eye)VE Project. A deep neural network learnt to reproduce the human driver focus of attention (FoA) in a variety of real-world driving scenarios.
https://arxiv.org/pdf/1705.03854.pdf
MIT License
99 stars 33 forks source link

semseg predictions #16

Closed varunjammula closed 4 years ago

varunjammula commented 4 years ago

Hi, I am trying to perform semantic segmentation on the images and for 1 sequence it takes approx 51 hrs. Can you let me know how to speed this up?

DavideA commented 4 years ago

Hi,

are you using a GPU?

D

varunjammula commented 4 years ago

Thanks for pointing that out. I assumed theano would pick up GPU by default. For future reference, we can run Theano GPU like: THEANO_FLAGS=device=cuda,floatX=float32 python main.py --sequence ID

kj-kx commented 3 years ago

hi，thank you for your share! when i run train.py with gpu,errors happen ! could you tell me how to deal with it ERROR (theano.gof.opt): Optimization failure due to: LocalOptGroup(local_abstractconv_cudnn,local_abstractconv_gw_cudnn,local_abstractconv_gi_cudnn,local_abstractconv_gemm,local_abstractconv3d_gemm,local_abstractconv_gradweights_gemm,local_abstractconv3d_gradweights_gemm,local_abstractconv_gradinputs_gemm,local_abstractconv3d_gradinputs_gemm) ERROR (theano.gof.opt): node: AbstractConv3d_gradWeights{convdim=3, border_mode='half', subsample=(1, 1, 1), filter_flip=True, imshp=(None, None, None, None, None), kshp=(512, 512, 3, 3, 3), filter_dilation=(1, 1, 1), num_groups=1, unshared=False}(GpuElemwise{mul,no_inplace}.0, GpuElemwise{add,no_inplace}.0, MakeVector{dtype='int64'}.0) ERROR (theano.gof.opt): TRACEBACK:

HHUBRO commented 7 months ago

Could you please tell me which version of python, theano, cuda, keras you use? I'm facing some problem with GPU. Thanks a lot!