本文整理汇总了Python中nervanagpu.NervanaGPU.max方法的典型用法代码示例。如果您正苦于以下问题:Python NervanaGPU.max方法的具体用法?Python NervanaGPU.max怎么用?Python NervanaGPU.max使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类nervanagpu.NervanaGPU
的用法示例。
在下文中一共展示了NervanaGPU.max方法的3个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: max
# 需要导入模块: from nervanagpu import NervanaGPU [as 别名]
# 或者: from nervanagpu.NervanaGPU import max [as 别名]
glops = max(glops16, glops32, glops64, glops128)
if glops16 == glops:
fastest = 16
elif glops32 == glops:
fastest = 32
elif glops64 == glops:
fastest = 64
else:
fastest = 128
glopsref = cublas_dot(devA2, devB2, devC2, repeat=repeat)
partial1 = ng.empty((devC1.shape[0],1), dtype=np.float32)
partial2 = partial1[0:1,0:1]
diff = ng.max(abs(devC2 - devC1), partial=partial1, out=partial2).get()[0,0]
mean = ng.mean(abs(devC2), partial=partial1, out=partial2).get()[0,0]
flops_diff = glops - glopsref
note = "**************" if flops_diff <= 0 else ""
print "Faster: %.0f gflops Choice: %d Error: %.3f%%%s" % (flops_diff, fastest, 100 * diff / mean, note)
print "--------------------------------------------------------------------------------"
cublas.cublasDestroy(handle)
示例2: GPU
# 需要导入模块: from nervanagpu import NervanaGPU [as 别名]
# 或者: from nervanagpu.NervanaGPU import max [as 别名]
#.........这里部分代码省略.........
each output feature map stored in out.
ifmshape (tuple): Dimensions of each input feature map (typically
height and width).
links (GPUTensor): Input receptive field indices.
nifm (int): Total number of input feature maps.
padding (int): Number of additional elements to include along each
dimension of each local receptive field during the
convolution operation.
stride (int): Number of neurons to shift the filter at each step.
ngroups (int): Number of groups.
fwidth (int): Filter width.
updatebuf (GPUTensor): Temporary storage buffer used to hold the
updated gradient for a single receptive
field
local (bool, optional): Whether to do local filtering (True) or
convolution (False, the default)
layer (Layer): The layer object.
"""
self.ng.update_conv(layer=updatebuf, I=inputs, E=deltas, grad_F=out,
alpha=1.0, repeat=1)
def fprop_pool(self, out, inputs, op, ofmshape, ofmsize, ofmlocs, fshape,
ifmshape, links, nifm, padding, stride, fpropbuf):
"""
Forward propagate the inputs of a Pooling network layer to
produce output pre-activations (ready for transformation by an
activation function).
Arguments:
out (GPUTensor): Where to store the forward propagated results.
inputs (GPUTensor): Will be either the dataset input values (first
layer), or the outputs from the previous layer.
op (string): The type of pooling operation to apply. We support
"max", "avg", "l2" currently.
ofmshape (tuple): Dimensions of each output feature map (typically
number of height and width neurons).
ofmsize (int): Total size of each output feature map.
ofmlocs (GPUTensor): Indices giving the location of each element in
each output feature map stored in out.
fshape (tuple): Dimensions of each filter (typically height and
width).
ifmshape (tuple): Dimensions of each input feature map (typically
number of height and width neurons).
links (GPUTensor): Input receptive field indices.
nifm (int): Total number of input feature maps.
padding (int): Number of additional elements to include along each
dimension of each local receptive field during the
pooling operation.
stride (int): Number of neurons to shift the filter at each step.
fpropbuf (GPUTensor): Temporary storage buffer used to hold the
pooled outputs for a single receptive field.
"""
op = op.lower()
if op == "max":
self.ng.fprop_pool(layer=fpropbuf, I=inputs, O=out, repeat=1)
else:
raise AttributeError("unexpected pooling op type: %s", op)
def bprop_pool(self, out, fouts, inputs, deltas, op, ofmshape, ofmsize,
ofmlocs, fshape, fpsize, ifmshape, links, nifm, padding,
stride, bpropbuf):
"""
Backward propagate the error through a pooling network layer.
Arguments:
out (GPUTensor): Where to store the backward propagated errors.
示例3:
# 需要导入模块: from nervanagpu import NervanaGPU [as 别名]
# 或者: from nervanagpu.NervanaGPU import max [as 别名]
ng.fprop_conv (conv, nlI, nlF, nlO, alpha=alpha, repeat=repeat)
ng.bprop_conv (conv, nlF, nlE, nlB, alpha=alpha, repeat=repeat)
ng.update_conv(conv, nlI, nlE, nlU, alpha=alpha, repeat=repeat)
nlI = nlF = nlE = None
print "\ncudnn vs nervanaLib:"
parO = ng.empty((N,1), dtype=np.float32)
parB = ng.empty((N,1), dtype=np.float32)
parU = ng.empty((K,1), dtype=np.float32)
maxO = parO[0:1,0:1]
maxB = parB[0:1,0:1]
maxU = parU[0:1,0:1]
maxo = ng.max(abs(cuO - nlO.T), partial=parO, out=maxO).get()[0,0]
maxb = ng.max(abs(cuB - nlB.T), partial=parB, out=maxB).get()[0,0]
maxu = ng.max(abs(cuU - nlU.T), partial=parU, out=maxU).get()[0,0]
meano = ng.mean(abs(cuO), partial=parO, out=maxO).get()[0,0]
meanb = ng.mean(abs(cuB), partial=parB, out=maxB).get()[0,0]
meanu = ng.mean(abs(cuU), partial=parU, out=maxU).get()[0,0]
print " maxerr mean pct"
print "fprop: %7.5f %6.2f %5.3f" % (maxo, meano, 100*maxo/meano)
print "bprop: %7.5f %6.2f %5.3f" % (maxb, meanb, 100*maxb/meanb)
print "updat: %7.5f %6.2f %5.3f" % (maxu, meanu, 100*maxu/meanu)
# free up memory from this layer before proceeding
cuB = cuU = cuO = None
nlB = nlU = nlO = None