本文整理汇总了Python中nervanagpu.NervanaGPU.conv_layer方法的典型用法代码示例。如果您正苦于以下问题:Python NervanaGPU.conv_layer方法的具体用法?Python NervanaGPU.conv_layer怎么用?Python NervanaGPU.conv_layer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.conv_layer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: run
# 需要导入模块: from nervanagpu import NervanaGPU [as 别名]
# 或者: from nervanagpu.NervanaGPU import conv_layer [as 别名]
def run():
ng = NervanaGPU(stochastic_round=False)
dt = np.float32
# N: Number of images in mini-batch
# C: Number of input feature maps
# K: Number of output feature maps
# D: Depth of input image
# H: Height of input image
# W: Width of input image
# T: Depth of filter kernel
# R: Height of filter kernel
# S: Width of filter kernel
#
# * images: (numColors, imgSizeY, imgSizeX, numImages) with stride given
# * filters: (numColors, filterPixels, numFilters) if conv
# * (numModules, numColors, filterPixels, numFilters) otherwise
# *
# * targets: (numFilters, numModulesY, numModulesX, numImages)
N = 128
C = 3
K = 64
D = 1
H = 64
W = 64
T = 1
R = 8
S = 8
pad_h = pad_w = 0
str_h = str_w = 4
layer = ng.conv_layer(dt, N, C, K,
D=D, H=H, W=W,
T=T, R=R, S=S,
pad_d=0, pad_h=pad_h, pad_w=pad_w,
str_d=1, str_h=str_h, str_w=str_w,
grid_P=0, grid_Q=0, update_size=None)
numImages = N
numFilters = K
numModulesY = int(math.ceil(float(H - R + 1 + 2*pad_h) / str_h))
numModulesX = int(math.ceil(float(W - S + 1 + 2*pad_w) / str_w))
print "Num Modules ", numModulesX, numModulesY
# Set up images, filters, and outputs
# imgd = np.loadtxt("im1.txt")
# img = np.zeros((64, 64, 3))
# print imgd.shape
# for i in range(3):
# img[:, :, i] = imgd[i*64:(i+1)*64, :]
# hostImages = np.tile(img)
hostImages = np.random.rand(C, H, W, N)
hostFilters = np.random.uniform(low=0.0, high=1.0, size=(C, S*R, numFilters)) #np.ones((C, S*R, numFilters)) #
hostOutputs = np.zeros((numFilters, numModulesY, numModulesX, N))
print "Input sum", np.sum(hostImages)
# Run cc2 kernel
devI = ng.array(hostImages, dtype=dt)
devF = ng.array(hostFilters, dtype=dt)
devO = ng.array(hostOutputs, dtype=dt)
ng.fprop_cuda_conv(layer, devI, devF, devO)
print "CC2 input sum: ", np.sum(devI.asnumpyarray())
print "CC2 output sum: ", np.sum(devO.asnumpyarray())
# Run maxwel kernel
# images: (C * H * W, N)
# filters: (C * S * R , numFilters)
# outputs: (numFilters * numModulesX * numModulesY, N)
devI = ng.array(hostImages.reshape((C*H*W, N)), dtype=dt)
devF = ng.array(hostFilters.reshape((C*S*R, numFilters)), dtype=dt)
devO2 = ng.array(hostOutputs.reshape(numFilters*numModulesX*numModulesY, N), dtype=dt)
ng.fprop_conv(layer, devI, devF, devO2)
print "NG input sum: ", np.sum(devI.asnumpyarray())
print "NG output sum: ", np.sum(devO2.asnumpyarray())
hostOutputs1 = np.reshape(devO.asnumpyarray(), devO2.shape)
hostOutputs2 = devO2.asnumpyarray()
for i in xrange(hostOutputs1.shape[0]):
for j in xrange(hostOutputs1.shape[1]):
assert(abs(hostOutputs1[i, j] - hostOutputs2[i, j]) < 1e-4)
示例2:
# 需要导入模块: from nervanagpu import NervanaGPU [as 别名]
# 或者: from nervanagpu.NervanaGPU import conv_layer [as 别名]
( 64, 64, 64, 1, 224,224, 1, 3, 3, 0,1,1, 1,1,1),
( 64, 64,128, 1, 112,112, 1, 3, 3, 0,1,1, 1,1,1),
( 64,128,128, 1, 112,112, 1, 3, 3, 0,1,1, 1,1,1),
( 64,128,256, 1, 56, 56, 1, 3, 3, 0,1,1, 1,1,1),
( 64,256,256, 1, 56, 56, 1, 3, 3, 0,1,1, 1,1,1),
( 64,256,512, 1, 28, 28, 1, 3, 3, 0,1,1, 1,1,1),
( 64,512,512, 1, 28, 28, 1, 3, 3, 0,1,1, 1,1,1),
( 64,512,512, 1, 14, 14, 1, 3, 3, 0,1,1, 1,1,1),
(128, 3, 64, 1, 224,224, 1,11,11, 0,3,3, 1,4,4), #Alexnet
(128, 64,192, 1, 27, 27, 1, 5, 5, 0,2,2, 1,1,1),
(128,192,384, 1, 13, 13, 1, 3, 3, 0,1,1, 1,1,1),
(128,384,256, 1, 13, 13, 1, 3, 3, 0,1,1, 1,1,1),
(128,256,256, 1, 13, 13, 1, 3, 3, 0,1,1, 1,1,1),):
conv = ng.conv_layer(dtype, *dims)
N,C,K = conv.NCK
D,H,W = conv.DHW
T,R,S = conv.TRS
M,P,Q = conv.MPQ
pad_d, pad_h, pad_w = conv.padding
str_d, str_h, str_w = conv.strides
alpha, beta = (1.0, 0.0)
dimI = conv.dimI2
dimF = conv.dimF2
dimO = conv.dimO2
print "cudnn:"
示例3: set
# 需要导入模块: from nervanagpu import NervanaGPU [as 别名]
# 或者: from nervanagpu.NervanaGPU import conv_layer [as 别名]
print context.get_device().name()
np.set_printoptions(threshold=8193, linewidth=600, formatter={'int':lambda x: "%10d" % x,'float':lambda x: "% .0f" % x})
ops = set(("update",)) # "fprop","bprop","update"
ones = 0
cpu = 0 # Set CPU to 1 to check against CPU
repeat = 1
dtype = np.float32
ng = NervanaGPU(stochastic_round=False, bench=True)
conv = ng.conv_layer(
dtype,
16,3,8, # N,C,K
1,64,64, # D,H,W
1,3,3, # T,R,S
0,1,1, # padding
1,1,1) # strides
dimI = conv.dimI
dimF = conv.dimF
dimO = conv.dimO
# colapse outer dimensions into one and preserve inner dimension
# this allows for easy cpu convolution in numpy
def slicable(dim, pad=0):
dim0 = reduce(mul, dim[:-1], 1) + pad
return (dim0, dim[-1])