1.安装tensorflow-gpu
2.在~/.theanorc中写入
[global]
floatX = float32
device = cuda0
[lib]
cnmem = 1
[nvcc]
flags=-D_FORCE_INLINES
fastmath = True
[blas]
ldflags = -lopenblas
[cuda]
root = /usr/local/cuda-9.1/bin
[dnn]
include_path = /usr/local/cuda/include
library_path = /usr/local/cuda/lib64
3.测试gpu是否可用
from theano import function, config, shared, tensor
import numpy
import time
vlen = 10 * 30 * 768 # 10 x #cores x # threads per core
iters = 1000
rng = numpy.random.RandomState(22)
x = shared(numpy.asarray(rng.rand(vlen), config.floatX))
f = function([], tensor.exp(x))
print(f.maker.fgraph.toposort())
t0 = time.time()
for i in range(iters):
r = f()
t1 = time.time()
print("Looping %d times took %f seconds" % (iters, t1 - t0))
print("Result is %s" % (r,))
if numpy.any([isinstance(x.op, tensor.Elemwise) and
('Gpu' not in type(x.op).__name__)
for x in f.maker.fgraph.toposort()]):
print('Used the cpu')
else:
print('Used the gpu')