def deconv(self, X, subsample=(2, 2), border_mode=(2, 2), conv_mode='conv', atype='sigmoid'):
"""
sets up dummy convolutional forward pass and uses its grad as deconv
currently only tested/working with same padding
"""
#Always return a c contiguous output.
#Copy the input only if it is not already c contiguous.
img = gpu_contiguous(X)
kerns = gpu_contiguous(self.W)
#Implement Alloc on the gpu, but without initializing memory.
if someconfigs.backend == 'gpuarray':
gpu_alloc_img_shape = GpuAllocEmpty('float32', None)(img.shape[0], kerns.shape[1], \
img.shape[2]*subsample[0], img.shape[3]*subsample[1]).shape
#This Op builds a convolution descriptor for use in the other convolution operations.
desc = GpuDnnConvDesc(border_mode=border_mode, subsample=subsample,\
conv_mode=conv_mode)(kerns.shape)
out = GpuAllocEmpty('float32', None)(img.shape[0], kerns.shape[1], img.shape[2]*subsample[0],\
img.shape[3]*subsample[1])
elif someconfigs.backend == 'cudandarray':
gpu_alloc_img_shape = gpu_alloc_empty(img.shape[0], kerns.shape[1], \
img.shape[2]*subsample[0], img.shape[3]*subsample[1]).shape
desc = GpuDnnConvDesc(border_mode=border_mode, subsample=subsample,\
conv_mode=conv_mode)(gpu_alloc_img_shape, kerns.shape)
out = gpu_alloc_empty(img.shape[0], kerns.shape[1], img.shape[2]*subsample[0],\
img.shape[3]*subsample[1])
#The convolution gradient with respect to the inputs.
d_img = GpuDnnConvGradI()(kerns, img, out, desc)
return activation_fn_th(d_img, atype=atype)
def conv(self,
X,
subsample=(2, 2),
border_mode=(2, 2),
atype='sigmoid',
testF=False):
#ConH0 = dnn_conv(X , self.W.dimshuffle(1,0,2,3), subsample=subsample, border_mode=border_mode)
ConH0 = dnn_conv(X,
self.W,
subsample=subsample,
border_mode=border_mode)
if testF:
ConH1 = (ConH0 - self.stat_mean.dimshuffle('x', 0, 'x', 'x')) \
/ (self.stat_std.dimshuffle('x', 0, 'x', 'x') + TINY)
else:
mean = ConH0.mean(axis=[0, 2, 3]).dimshuffle('x', 0, 'x', 'x')
std = T.mean(T.sqr(ConH0 - mean),
axis=[0, 2, 3]).dimshuffle('x', 0, 'x', 'x')
ConH1 = (ConH0 - mean) / T.sqrt(std + TINY)
ConH2 = ConH1 * self.eta.dimshuffle('x', 0, 'x', 'x')\
+ self.beta.dimshuffle('x', 0, 'x', 'x')
return activation_fn_th(ConH2, atype=atype)
def conv(self, X, subsample=(2, 2), border_mode=(2, 2), atype='sigmoid'):
ConH0 = dnn_conv(X,
self.W.dimshuffle(1, 0, 2, 3),
subsample=subsample,
border_mode=border_mode)
#ConH0 = dnn_conv(X , self.W, subsample=subsample, border_mode=border_mode)
#return activation_fn_th(ConH0, atype=atype)
return activation_fn_th(ConH0 + self.c.dimshuffle('x', 0, 'x', 'x'),
atype=atype)
def deconv(self,
X,
subsample=(2, 2),
border_mode=(2, 2),
conv_mode='conv',
atype='sigmoid',
testF=False):
"""
sets up dummy convolutional forward pass and uses its grad as deconv
currently only tested/working with same padding
"""
#Always return a c contiguous output.
#Copy the input only if it is not already c contiguous.
img = gpu_contiguous(X)
kerns = gpu_contiguous(self.W)
#Implement Alloc on the gpu, but without initializing memory.
if someconfigs.backend == 'gpuarray':
gpu_alloc_img_shape = GpuAllocEmpty('float32', None)(img.shape[0], kerns.shape[1], \
img.shape[2]*subsample[0], img.shape[3]*subsample[1]).shape
#This Op builds a convolution descriptor for use in the other convolution operations.
desc = GpuDnnConvDesc(border_mode=border_mode, subsample=subsample,\
conv_mode=conv_mode)(kerns.shape)
out = GpuAllocEmpty('float32', None)(img.shape[0], kerns.shape[1], img.shape[2]*subsample[0],\
img.shape[3]*subsample[1])
elif someconfigs.backend == 'cudandarray':
gpu_alloc_img_shape = gpu_alloc_empty(img.shape[0], kerns.shape[1], \
img.shape[2]*subsample[0], img.shape[3]*subsample[1]).shape
desc = GpuDnnConvDesc(border_mode=border_mode, subsample=subsample,\
conv_mode=conv_mode)(gpu_alloc_img_shape, kerns.shape)
out = gpu_alloc_empty(img.shape[0], kerns.shape[1], img.shape[2]*subsample[0],\
img.shape[3]*subsample[1])
#The convolution gradient with respect to the inputs.
d_img = GpuDnnConvGradI()(kerns, img, out, desc)
ConH0 = d_img #+ self.b.dimshuffle('x', 0, 'x', 'x')
if testF:
ConH1 = (ConH0 - self.stat_mean.dimshuffle('x', 0, 'x', 'x')) \
/ (self.stat_std.dimshuffle('x', 0, 'x', 'x') + TINY)
else:
mean = ConH0.mean(axis=[0, 2, 3]).dimshuffle('x', 0, 'x', 'x')
std = T.mean(T.sqr(ConH0 - mean),
axis=[0, 2, 3]).dimshuffle('x', 0, 'x', 'x')
ConH1 = (ConH0 - mean) / T.sqrt(std + TINY)
ConH2 = self.eta.dimshuffle('x', 0, 'x', 'x') * ConH1 \
+ self.beta.dimshuffle('x', 0, 'x', 'x')
return activation_fn_th(ConH2, atype=atype)
def conv(self, X, subsample=(2, 2), border_mode=(2, 2), conv_mode='conv', atype='sigmoid'):
ConH0 = dnn_conv(X , self.W, subsample=subsample, border_mode=border_mode)
return activation_fn_th(ConH0, atype=atype)
def propagate(self, X, testF=False, atype='sigmoid'):
H = self.pre_activation(X, testF=False)
H = activation_fn_th(H, atype=atype)
return H