theano-cuda

regarding setting up GPU for theano

由 无人久伴 提交于 2020-01-05 05:44:08
问题 I configure the GPU under home/.theanorc as follows bash-4.1$ cat .theanorc [global] floatX = float32 device = gpu0 [lib] cnmem = 1 Running the program gives the following warning message, how to solve this problem? python train.py Using Theano backend. WARNING (theano.sandbox.cuda): The cuda backend is deprecated and will be removed in the next release (v0.10). Please switch to the gpuarray backend. You can get more information about how to switch at this URL: https://github.com/Theano

theano.test() fails with nvcc error - nvcc fatal : Don't know what to do with 'NPY_NO_DEPRECATED_API=NPY_1_7_API_VERSION,-fPIC'

由 可紊 提交于 2019-12-12 02:23:46
问题 I'm installing Theano into an Ananconda environment and seem to have run into an install issue I don't understand. After I create the environment I run theano.test() and get the following error: ERROR:theano.sandbox.cuda:Failed to compile cuda_ndarray.cu: ('nvcc return status', 1, 'for cmd', 'nvcc -shared -O3 -m64 -Xcompiler -DCUDA_NDARRAY_CUH=m11b90075e2397c684f9dc0f7276eab8f,-D NPY_NO_DEPRECATED_API=NPY_1_7_API_VERSION,-fPIC -Xlinker -rpath,/home/brad/.theano/compiledir_Linux-4.4--generic

Python Named Entity Recognition Error: IndexError: list index out of range

由 半城伤御伤魂 提交于 2019-12-11 16:56:05
问题 Hi i am new to python and tried to run script (https://github.com/detuvoldo/tagger), I replaced the 2 lines in utils.py because i am using Windows 10 and there were some path related issues. models_path = u"\\\\?\\" + os.path.abspath(u".\\models") eval_path = os.path.abspath(u".\\evaluation") The error is run train.py --train lstm/fold1/train --dev lstm/fold1/dev --test lstm/fold1/test WARNING (theano.sandbox.cuda): The cuda backend is deprecated and will be removed in the next release (v0.10

theano.test() : optimization failure due to constant_folding (on ubuntu)

由 会有一股神秘感。 提交于 2019-12-10 19:07:15
问题 When running theano.test() on an Ubuntu operating system, some error message about an optimization failure is produced as follows: ERROR (theano.gof.opt): Optimization failure due to: constant_folding ERROR (theano.gof.opt): TRACEBACK: ERROR (theano.gof.opt): Traceback (most recent call last): File "/usr/local/lib/python2.7/dist-packages/theano/gof/opt.py", line 1286, in process_node replacements = lopt.transform(node) File "/usr/local/lib/python2.7/dist-packages/theano/tensor/opt.py", line

Installing cuDNN for Theano without root access

由 岁酱吖の 提交于 2019-12-08 03:36:56
问题 Can I install cuDNN locally without root access ? I don't have root access to a linux machine I am using (the distro is openSuse), but I have CUDA 7.5 already installed. I am using Theano and I need cuDNN to improve the speed of the operations on the GPU. I downloaded cudnn-7.5-linux-x64-v5.1 from Nvidia and as per the instructions I need to copy the CuDNN archive content to CUDA installation folder, i.e. (cuda/lib64/ and cuda/include/). But that would require me to have root access. Is it

Installing cuDNN for Theano without root access

由 ￣綄美尐妖づ 提交于 2019-12-06 08:45:59
Can I install cuDNN locally without root access ? I don't have root access to a linux machine I am using (the distro is openSuse), but I have CUDA 7.5 already installed. I am using Theano and I need cuDNN to improve the speed of the operations on the GPU. I downloaded cudnn-7.5-linux-x64-v5.1 from Nvidia and as per the instructions I need to copy the CuDNN archive content to CUDA installation folder, i.e. (cuda/lib64/ and cuda/include/). But that would require me to have root access. Is it possible that I extract the cudnn archive locally and provide theano with the path to the cudnn library ?

How to enable Keras with Theano to utilize multiple GPUs

由 三世轮回 提交于 2019-12-03 17:26:39
问题 Setup: Using a Amazon Linux system with a Nvidia GPU I'm using Keras 1.0.1 Running Theano v0.8.2 backend Using CUDA and CuDNN THEANO_FLAGS="device=gpu,floatX=float32,lib.cnmem=1" Everything works fine, but I run out of video memory on large models when I increase the batch size to speed up training. I figure moving to a 4 GPU system would in theory either improve total memory available or allow smaller batches to build faster, but observing the the nvidia stats, I can see only one GPU is used

How to enable Keras with Theano to utilize multiple GPUs

由 爷，独闯天下 提交于 2019-12-03 06:18:01
Setup: Using a Amazon Linux system with a Nvidia GPU I'm using Keras 1.0.1 Running Theano v0.8.2 backend Using CUDA and CuDNN THEANO_FLAGS="device=gpu,floatX=float32,lib.cnmem=1" Everything works fine, but I run out of video memory on large models when I increase the batch size to speed up training. I figure moving to a 4 GPU system would in theory either improve total memory available or allow smaller batches to build faster, but observing the the nvidia stats, I can see only one GPU is used by default: +------------------------------------------------------+ | NVIDIA-SMI 361.42 Driver

Error running theano.test() - ImportError: DLL load failed: A dynamic link library (DLL) initialization routine failed

由 非 Y 不嫁゛ 提交于 2019-12-02 17:53:18
问题 I'm trying to get theano up and running on a Windows 10 (x64) machine. I've installed Python from the WinPython distribution, which comes with theano already running. But after installing CUDA 8.0.44 and MingW, I constantly get the following errors when running the simple script import theano theano.test() Note that I had several warnings before, that I already solved (e.g. by installing missing packages from here. But this error gives me no usable information. The really weird thing is, that

Error running theano.test() - ImportError: DLL load failed: A dynamic link library (DLL) initialization routine failed

由 蹲街弑〆低调 提交于 2019-12-02 07:54:45
I'm trying to get theano up and running on a Windows 10 (x64) machine. I've installed Python from the WinPython distribution, which comes with theano already running. But after installing CUDA 8.0.44 and MingW, I constantly get the following errors when running the simple script import theano theano.test() Note that I had several warnings before, that I already solved (e.g. by installing missing packages from here . But this error gives me no usable information. The really weird thing is, that the module-name is not given anywhere that theano is missing. theano.gof.opt: ERROR: Optimization
订阅 theano-cuda