def local_conv3d_gradinputs_cpu(node):
if not isinstance(node.op, AbstractConv3d_gradInputs):
return None
kern, topgrad, shape = node.inputs
if ((not isinstance(kern.type, TensorType) or
not isinstance(topgrad.type, TensorType))):
return None
if node.op.border_mode not in ['valid', (0, 0, 0)]:
return None
if node.op.filter_dilation != (1, 1, 1):
return None
# need to flip the kernel if necessary (conv3D does not flip)
if node.op.filter_flip:
kern = kern[:, :, ::-1, ::-1, ::-1]
# conv3D expects shape (batch, row, column, time, channel)
kern = kern.dimshuffle(0, 2, 3, 4, 1)
topgrad = topgrad.dimshuffle(0, 2, 3, 4, 1)
bias = theano.tensor.zeros_like(kern[0, 0, 0, 0, :])
rval = convTransp3D(kern, bias, node.op.subsample, topgrad, shape)
copy_stack_trace(node.outputs[0], rval)
rval = rval.dimshuffle(0, 4, 1, 2, 3)
rval = theano.tensor.patternbroadcast(rval,
node.outputs[0].broadcastable)
return [rval]
def local_conv3d_gradinputs_cpu(node):
if not isinstance(node.op, AbstractConv3d_gradInputs):
return None
kern, topgrad, shape = node.inputs
if ((not isinstance(kern.type, TensorType)
or not isinstance(topgrad.type, TensorType))):
return None
if node.op.border_mode not in ['valid', (0, 0, 0)]:
return None
if node.op.filter_dilation != (1, 1, 1):
return None
# need to flip the kernel if necessary (conv3D does not flip)
if node.op.filter_flip:
kern = kern[:, :, ::-1, ::-1, ::-1]
# conv3D expects shape (batch, row, column, time, channel)
kern = kern.dimshuffle(0, 2, 3, 4, 1)
topgrad = topgrad.dimshuffle(0, 2, 3, 4, 1)
bias = theano.tensor.zeros_like(kern[0, 0, 0, 0, :])
rval = convTransp3D(kern, bias, node.op.subsample, topgrad, shape)
copy_stack_trace(node.outputs[0], rval)
rval = rval.dimshuffle(0, 4, 1, 2, 3)
rval = theano.tensor.patternbroadcast(rval, node.outputs[0].broadcastable)
return [rval]
def setUp(self):
super(TestConv3D, self).setUp()
utt.seed_rng()
self.rng = N.random.RandomState(utt.fetch_seed())
mode = copy.copy(theano.compile.mode.get_default_mode())
mode.check_py_code = False
self.W = shared(N.ndarray(shape=(1, 1, 1, 1, 1), dtype=floatX))
self.b = shared(N.zeros(1, dtype=floatX))
self.rb = shared(N.zeros(1, dtype=floatX))
self.V = shared(N.ndarray(shape=(1, 1, 1, 1, 1), dtype=floatX))
self.d = shared(N.ndarray(shape=(3, ), dtype=int))
self.H = conv3D(self.V, self.W, self.b, self.d)
self.H_func = function([], self.H, mode=mode)
self.H_shape_func = function([], self.H.shape, mode=mode)
self.RShape = T.vector(dtype='int64')
self.otherH = T.TensorType(floatX,
(False, False, False, False, False))(name='otherH')
self.transp = convTransp3D(self.W, self.rb, self.d,
self.otherH, self.RShape)
self.transp_func = function([self.otherH, self.RShape],
self.transp, mode=mode)
self.R = convTransp3D(self.W, self.rb, self.d, self.H, self.RShape)
self.R_func = function([self.RShape], self.R, mode=mode)
self.R_shape_func = function([self.RShape], self.R.shape)
self.reconsObj = T.sum(T.sqr(self.V - self.R))
self.reconsObjFunc = function([self.RShape], self.reconsObj, mode=mode)
self.gradientsFunc = function([self.RShape],
[T.grad(self.reconsObj, self.W), T.grad(self.reconsObj,
self.H), T.grad(self.reconsObj, self.V),
T.grad(self.reconsObj, self.b)], mode=mode)
self.check_c_against_python = function([self.RShape],
[T.grad(self.reconsObj, self.W), T.grad(self.reconsObj,
self.H), T.grad(self.reconsObj, self.V),
T.grad(self.reconsObj, self.b)], mode='DEBUG_MODE')
self.dCdW_shape_func = function([self.RShape],
T.grad(self.reconsObj, self.W).shape, mode=mode)
def grad(self, inputs, output_gradients):
C, d, WShape, B = inputs
dLdA, = output_gradients
z = T.zeros_like(C[0, 0, 0, 0, :])
dLdC = convTransp3D(dLdA, z, d, B, C.shape[1:4])
# d actually does affect the outputs, so it's not disconnected
dLdd = grad_undefined(self, 1, d)
# The shape of the weights doesn't affect the output elements
dLdWShape = DisconnectedType()()
dLdB = conv3D(C, dLdA, T.zeros_like(B[0, 0, 0, 0, :]), d)
return [dLdC, dLdd, dLdWShape, dLdB]
def grad(self, inputs, output_gradients):
C, d, WShape, B = inputs
dLdA, = output_gradients
z = T.zeros_like(C[0, 0, 0, 0, :])
dLdC = convTransp3D(dLdA, z, d, B, C.shape[1:4])
# d actually does affect the outputs, so it's not disconnected
dLdd = grad_undefined(self, 1, d)
# The shape of the weights doesn't affect the output elements
dLdWShape = DisconnectedType()()
dLdB = conv3D(C, dLdA, T.zeros_like(B[0, 0, 0, 0, :]), d)
return [dLdC, dLdd, dLdWShape, dLdB]
def setUp(self):
utt.seed_rng()
self.rng = N.random.RandomState(utt.fetch_seed())
mode = copy.copy(theano.compile.mode.get_default_mode())
mode.check_py_code = False
self.W = shared(N.ndarray(shape=(1,1,1,1,1), dtype=floatX))
self.b = shared(N.zeros(1,dtype=floatX))
self.rb = shared(N.zeros(1,dtype=floatX))
self.V = shared(N.ndarray(shape=(1,1,1,1,1), dtype=floatX))
self.d = shared(N.ndarray(shape=(3,),dtype=int))
self.H = conv3D(self.V, self.W, self.b, self.d)
self.H_func = function([], self.H, mode = mode)
self.H_shape_func = function( [], self.H.shape, mode = mode)
self.RShape = T.vector(dtype='int64')
self.otherH = T.TensorType(floatX,(False,False,False,False,False))(name='otherH')
self.transp = convTransp3D(self.W, self.rb, self.d, self.otherH, self.RShape)
self.transp_func = function([self.otherH,self.RShape],self.transp, mode=mode)
self.R = convTransp3D(self.W, self.rb, self.d, self.H, self.RShape)
self.R_func = function([self.RShape], self.R, mode = mode)
self.R_shape_func = function([self.RShape], self.R.shape)
self.reconsObj = T.sum(T.sqr(self.V-self.R))
self.reconsObjFunc = function([self.RShape], self.reconsObj, mode=mode)
self.gradientsFunc = function([self.RShape], [ T.grad(self.reconsObj, self.W), T.grad(self.reconsObj, self.H), T.grad(self.reconsObj, self.V), T.grad(self.reconsObj,self.b) ] , mode=mode)
self.check_c_against_python = function([self.RShape], [ T.grad(self.reconsObj, self.W), T.grad(self.reconsObj, self.H), T.grad(self.reconsObj, self.V), T.grad(self.reconsObj,self.b) ] , mode='DEBUG_MODE')
self.dCdW_shape_func = function([self.RShape], T.grad(self.reconsObj, self.W).shape, mode=mode)
def local_conv2d_gradinputs_cpu(node):
if not isinstance(node.op, AbstractConv2d_gradInputs):
return None
kern, topgrad, shape = node.inputs
if ((not isinstance(kern.type, TensorType)
or not isinstance(topgrad.type, TensorType))):
return None
if node.op.border_mode not in ['full', 'valid']:
return None
if not node.op.filter_flip:
# Not tested yet
return None
# Conv 3d implementation, needed when subsample > 2
if node.op.border_mode == 'valid' and node.op.subsample != (1, 1):
kern = kern[:, :, ::-1, ::-1]
shuffled_kern = kern.dimshuffle(0, 2, 3, 'x', 1)
shuffled_topgrad = topgrad.dimshuffle(0, 2, 3, 'x', 1)
b = theano.tensor.zeros_like(shuffled_kern[0, 0, 0, 0, :])
rval = convTransp3D(W=shuffled_kern,
b=b,
d=(node.op.subsample[0], node.op.subsample[1], 1),
H=shuffled_topgrad,
RShape=(shape[0], shape[1], 1))
copy_stack_trace(node.outputs[0], rval)
rval = theano.tensor.addbroadcast(rval, 3)
rval = rval.dimshuffle(0, 4, 1, 2)
rval = theano.tensor.patternbroadcast(rval,
node.outputs[0].broadcastable)
copy_stack_trace(node.outputs[0], rval)
return [rval]
# Conv2d Implementation
dx, dy = node.op.subsample
if dx not in (1, 2) or dy not in (1, 2):
# Not implemented in the gradient of ConvOp
return None
if node.op.imshp is None:
op_imshp = (None, None, None, None)
else:
op_imshp = node.op.imshp
if node.op.kshp is None:
op_kshp = (None, None, None, None)
else:
op_kshp = node.op.kshp
if None in op_imshp or None in op_kshp:
if (dx, dy) != (1, 1):
return None
mode = 'valid'
if not node.op.border_mode == 'full':
mode = 'full'
filters = kern.dimshuffle((1, 0, 2, 3))
filters = filters[:, :, ::-1, ::-1]
outshp = get_conv_output_shape(op_imshp, op_kshp, node.op.border_mode,
node.op.subsample)[2:]
fulloutshp = get_conv_output_shape(op_imshp, op_kshp, node.op.border_mode,
(1, 1))[2:]
nkern = op_imshp[1]
imshp = (op_kshp[0], outshp[0], outshp[1])
imshp_logical = (op_kshp[0], fulloutshp[0], fulloutshp[1])
din = ConvOp(imshp,
op_kshp[2:],
nkern,
op_imshp[0],
1,
1,
output_mode=mode,
unroll_batch=None,
unroll_kern=None,
unroll_patch=None,
imshp_logical=imshp_logical,
kshp_logical=None,
version=-1,
direction_hint='bprop inputs')
din = din(topgrad, filters)
copy_stack_trace(node.outputs[0], din)
din = theano.tensor.patternbroadcast(din, node.outputs[0].broadcastable)
copy_stack_trace(node.outputs[0], din)
return [din]
def local_conv2d_gradinputs_cpu(node):
if not isinstance(node.op, AbstractConv2d_gradInputs):
return None
kern, topgrad, shape = node.inputs
if ((not isinstance(kern.type, TensorType) or
not isinstance(topgrad.type, TensorType))):
return None
if node.op.border_mode not in ['full', 'valid']:
return None
if not node.op.filter_flip:
# Not tested yet
return None
# Conv 3d implementation, needed when subsample > 2
if node.op.border_mode == 'valid' and node.op.subsample != (1, 1):
kern = kern[:, :, ::-1, ::-1]
shuffled_kern = kern.dimshuffle(0, 2, 3, 'x', 1)
shuffled_topgrad = topgrad.dimshuffle(0, 2, 3, 'x', 1)
b = theano.tensor.zeros_like(shuffled_kern[0, 0, 0, 0, :])
rval = convTransp3D(W=shuffled_kern, b=b,
d=(node.op.subsample[0], node.op.subsample[1], 1),
H=shuffled_topgrad,
RShape=(shape[0], shape[1], 1))
copy_stack_trace(node.outputs[0], rval)
rval = theano.tensor.addbroadcast(rval, 3)
rval = rval.dimshuffle(0, 4, 1, 2)
rval = theano.tensor.patternbroadcast(rval,
node.outputs[0].broadcastable)
copy_stack_trace(node.outputs[0], rval)
return [rval]
# Conv2d Implementation
dx, dy = node.op.subsample
if dx not in (1, 2) or dy not in (1, 2):
# Not implemented in the gradient of ConvOp
return None
if node.op.imshp is None:
op_imshp = (None, None, None, None)
else:
op_imshp = node.op.imshp
if node.op.kshp is None:
op_kshp = (None, None, None, None)
else:
op_kshp = node.op.kshp
if None in op_imshp or None in op_kshp:
if (dx, dy) != (1, 1):
return None
mode = 'valid'
if not node.op.border_mode == 'full':
mode = 'full'
filters = kern.dimshuffle((1, 0, 2, 3))
filters = filters[:, :, ::-1, ::-1]
outshp = get_conv_output_shape(op_imshp, op_kshp,
node.op.border_mode, node.op.subsample)[2:]
fulloutshp = get_conv_output_shape(op_imshp, op_kshp,
node.op.border_mode, (1, 1))[2:]
nkern = op_imshp[1]
imshp = (op_kshp[0], outshp[0], outshp[1])
imshp_logical = (op_kshp[0], fulloutshp[0], fulloutshp[1])
din = ConvOp(imshp,
op_kshp[2:],
nkern,
op_imshp[0],
1, 1, output_mode=mode,
unroll_batch=None, unroll_kern=None,
unroll_patch=None,
imshp_logical=imshp_logical,
kshp_logical=None,
version=-1,
direction_hint='bprop inputs')
din = din(topgrad, filters)
copy_stack_trace(node.outputs[0], din)
din = theano.tensor.patternbroadcast(din, node.outputs[0].broadcastable)
copy_stack_trace(node.outputs[0], din)
return [din]
def setUp(self):
super(TestConv3D, self).setUp()
utt.seed_rng()
self.rng = N.random.RandomState(utt.fetch_seed())
mode = copy.copy(theano.compile.mode.get_default_mode())
mode.check_py_code = False
self.W = shared(N.ndarray(shape=(1, 1, 1, 1, 1), dtype=floatX))
self.W.name = 'W'
self.b = shared(N.zeros(1, dtype=floatX))
self.b.name = 'b'
self.rb = shared(N.zeros(1, dtype=floatX))
self.rb.name = 'rb'
self.V = shared(N.ndarray(shape=(1, 1, 1, 1, 1), dtype=floatX))
self.V.name = 'V'
self.d = shared(N.ndarray(shape=(3, ), dtype=int))
self.d.name = 'd'
self.H = conv3D(self.V, self.W, self.b, self.d)
self.H.name = 'H'
self.H_func = function([], self.H, mode=mode)
self.H_shape_func = function([], self.H.shape, mode=mode)
self.RShape = T.vector(dtype='int64')
self.RShape.name = 'RShape'
self.otherH = T.TensorType(
floatX, (False, False, False, False, False))(name='otherH')
self.transp = convTransp3D(self.W, self.rb, self.d, self.otherH,
self.RShape)
self.transp.name = 'transp'
self.transp_func = function([self.otherH, self.RShape],
self.transp,
mode=mode)
self.R = convTransp3D(self.W, self.rb, self.d, self.H, self.RShape)
self.R.name = 'R'
self.R_func = function([self.RShape], self.R, mode=mode)
self.R_shape_func = function([self.RShape], self.R.shape)
diff = self.V - self.R
diff.name = 'diff'
sqr = T.sqr(diff)
sqr.name = 'sqr'
self.reconsObj = T.sum(sqr)
self.reconsObj.name = 'reconsObj'
self.reconsObjFunc = function([self.RShape], self.reconsObj, mode=mode)
W_grad = T.grad(self.reconsObj, self.W)
self.gradientsFunc = function([self.RShape], [
W_grad,
T.grad(self.reconsObj, self.H),
T.grad(self.reconsObj, self.V),
T.grad(self.reconsObj, self.b)
],
mode=mode)
self.check_c_against_python = function([self.RShape], [
T.grad(self.reconsObj, self.W),
T.grad(self.reconsObj, self.H),
T.grad(self.reconsObj, self.V),
T.grad(self.reconsObj, self.b)
],
mode='DEBUG_MODE')
self.dCdW_shape_func = function([self.RShape],
T.grad(self.reconsObj, self.W).shape,
mode=mode)
def __call__(self, t):
output = convTransp3D(self.W + t * self.dW, self.b + t * self.db,
self.d, self.H + t * self.dH, self.RShape)
return output
def __call__(self, t):
output = convTransp3D(self.W + t * self.dW, self.b + t * self.db,
self.d, self.H + t * self.dH, self.RShape)
return output
