示例#1
0
def test_convolution():
  imgSize = 32
  filterSize = 5
  padding = 2
  color = 1
  imgNum = 1
  filterNum = 64
  
  stride = 1
  modulesX = 1 + int(((2 * padding + imgSize - filterSize) / float(stride)))
  
  print 'Modules X', modulesX
  
  
  img = gpuarray.to_gpu(np.ones((imgSize * imgSize * color, imgNum)).astype(np.float32))
  filter = gpuarray.to_gpu(np.ones((filterSize * filterSize * color, filterNum)).astype(np.float32))
  target = gpuarray.to_gpu(np.ones((modulesX * modulesX * filterNum, imgNum)).astype(np.float32))
  
  print 'standard output for convolution'
  print convolve2d(np.ones((imgSize, imgSize)).astype(np.float32), np.ones((filterSize, filterSize)).astype(np.float32),'valid')
  cudaconv2.convFilterActs(img, filter, target, imgSize, modulesX, modulesX, -padding, stride, color, 1, 0.0, 1.0)
  
  print 'pycuda output for convolution'
  atarget = target.get()
  
  print atarget
示例#2
0
文件: layer.py 项目: smessing/striate
  def fprop(self, input, output):
    cudaconv2.convFilterActs(input, self.filter, output, self.imgSize, self.outputSize,
        self.outputSize, -self.padding, self.stride, self.numColor, 1)

    self.tmp = gpuarray.empty((self.numFilter, self.get_single_img_size() * self.batchSize/self.numFilter), dtype=np.float32)
    gpu_copy_to(output, self.tmp)
    add_vec_to_rows(self.tmp, self.bias)
    gpu_copy_to(self.tmp, output)
示例#3
0
文件: layer.py 项目: phecy/striate
    def fprop(self, input, output, train=TRAIN):
        cudaconv2.convFilterActs(input, self.weight, output, self.imgSize,
                                 self.outputSize, self.outputSize,
                                 -self.padding, self.stride, self.numColor, 1)
        self.tmp = gpuarray.empty(
            (self.numFilter,
             self.get_single_img_size() * self.batchSize / self.numFilter),
            dtype=np.float32)
        gpu_copy_to(output, self.tmp)
        add_vec_to_rows(self.tmp, self.bias)
        gpu_copy_to(self.tmp, output)

        if PFout:
            print_matrix(output, self.name)
示例#4
0
def convFilterActs(input, weight, output, bias, padding, stride):
  from distbase import cuda_base
  image_y = input.shape[ConvDataLayout.HEIGHT]
  output_y = output.shape[ConvDataLayout.HEIGHT]
  output_x = output.shape[ConvDataLayout.WIDTH]
  color = input.shape[ConvDataLayout.CHANNEL]

  cudaconv2.convFilterActs(input, weight, output, image_y, output_y, output_x, padding, stride,
      color, 1)
  batch_size = output.shape[ConvDataLayout.BATCH]
  channel = output.shape[ConvDataLayout.CHANNEL]

  # bias term
  cuda_base.add_vec_to_rows(output.reshape((channel, output_y * output_x * batch_size)), bias)
示例#5
0
  def fprop(self, input, output, train=TRAIN):
    #np.save('input.arr', input.get())
    #np.save('weight.arr', self.weight.wt.get())
    cudaconv2.convFilterActs(input, self.weight.wt, output, self.img_size, self.outputSize,
        self.outputSize, -self.padding, self.stride, self.numColor, 1)
    
    #util.log_info('%s', output.get().mean())
    self.tmp = gpuarray.empty((self.numFilter, 
                               self.get_single_img_size() * self.batch_size / self.numFilter),
                                dtype=np.float32)
    
    gpu_copy_to(output, self.tmp)
    add_vec_to_rows(self.tmp, self.bias.wt)
    gpu_copy_to(self.tmp, output)

    if PFout:
      print_matrix(output, self.name)
示例#6
0
  def fprop(self, input, output, train=TRAIN):
    #np.save('input.arr', input.get())
    #np.save('weight.arr', self.weight.wt.get())
    cudaconv2.convFilterActs(input, self.weight.wt, output, self.img_size, self.outputSize,
        self.outputSize, -self.padding, self.stride, self.numColor, 1)
    
    #util.log_info('%s', output.get().mean())
    self.tmp = gpuarray.empty((self.numFilter, 
                               self.get_single_img_size() * self.batch_size / self.numFilter),
                                dtype=np.float32)
    
    gpu_copy_to(output, self.tmp)
    add_vec_to_rows(self.tmp, self.bias.wt)
    gpu_copy_to(self.tmp, output)

    if PFout:
      print_matrix(output, self.name)
示例#7
0
padding = 2
color = 1
imgNum = 1
filterNum = 64

stride = 1
modulesX = 1 + int(((2 * padding + imgSize - filterSize) / float(stride)))


img = gpuarray.to_gpu(np.ones((imgSize * imgSize * color, imgNum)).astype(np.float32))
filter = gpuarray.to_gpu(np.ones((filterSize * filterSize * color, filterNum)).astype(np.float32))
target = gpuarray.to_gpu(np.ones((modulesX * modulesX * filterNum, imgNum)).astype(np.float32))

print 'standard output for convolution'
print convolve2d(np.ones((imgSize, imgSize)).astype(np.float32), np.ones((filterSize, filterSize)).astype(np.float32),'valid')
cudaconv2.convFilterActs(img, filter, target, imgSize, modulesX, modulesX, -padding, stride, color, 1, 0.0, 1.0)

print 'pycuda output for convolution'
print target.get()


#from pycuda.compiler import *
#mod = SourceModule(open('foo.cu').read(), no_extern_c=True, include_dirs=['/home/justin/guppy/include'])
#kernel = mod.get_function('kernel')
#def i(x): return np.int32(x)
#
#grid = (1, 32 * 32 * 64 / (4 * 8), 1)
#blocks = (32, 4, 1)
#kernel(img, filter, target, i(1), i(64), i(32), i(32), i(5), i(-2), i(1), i(32), i(32), i(1),
#    np.float32(0.0), np.float32(1.0), np.int32(True), block=blocks, grid=grid)
示例#8
0
imgNum = 1
filterNum = 64

stride = 1
modulesX = 1 + int(((2 * padding + imgSize - filterSize) / float(stride)))

print 'Modules X', modulesX


img = gpuarray.to_gpu(np.ones((imgSize * imgSize * color, imgNum)).astype(np.float32))
filter = gpuarray.to_gpu(np.ones((filterSize * filterSize * color, filterNum)).astype(np.float32))
target = gpuarray.to_gpu(np.ones((modulesX * modulesX * filterNum, imgNum)).astype(np.float32))

print 'standard output for convolution'
print convolve2d(np.ones((imgSize, imgSize)).astype(np.float32), np.ones((filterSize, filterSize)).astype(np.float32),'valid')
cudaconv2.convFilterActs(img, filter, target, imgSize, modulesX, modulesX, -padding, stride, color, 1, 0.0, 1.0)

print 'pycuda output for convolution'
atarget = target.get()

print atarget
#for i in range(atarget.shape[0]):
#  print atarget[i, 0]


#from pycuda.compiler import *
#mod = SourceModule(open('foo.cu').read(), no_extern_c=True, include_dirs=['/home/justin/guppy/include'])
#kernel = mod.get_function('kernel')
#def i(x): return np.int32(x)
#
#grid = (1, 32 * 32 * 64 / (4 * 8), 1)