Skip to content

P
pytensor
提交 486b760d authored 作者: --global's avatar --global
浏览文件
操作

Remove nb_dim param from dnn convolutions

上级 b9e29760
隐藏空白字符变更
内嵌 并排
正在显示 包含 42 行增加 和 51 行删除
theano/sandbox/cuda/dnn.py
浏览文件 @ 486b760d
......@@ -534,7 +534,7 @@ class GpuDnnConv(DnnBase, COp):
"""
__props__ = ('workmem', 'inplace')
__input_name__ = ('image', 'kernel', 'output',
'descriptor', 'alpha', 'beta', 'nb_dim')
'descriptor', 'alpha', 'beta')
def __init__(self, workmem=None, inplace=False):
"""
......@@ -608,7 +608,7 @@ class GpuDnnConv(DnnBase, COp):
return [alg_def, alg_choose_def, alg_choose_time_def] + inpl_def
def make_node(self, img, kern, output, desc, alpha=None, beta=None, nb_dim=None):
def make_node(self, img, kern, output, desc, alpha=None, beta=None):
img = as_cuda_ndarray_variable(img)
kern = as_cuda_ndarray_variable(kern)
output = as_cuda_ndarray_variable(output)
......@@ -625,13 +625,12 @@ class GpuDnnConv(DnnBase, COp):
alpha = ensure_float(alpha, _one, 'alpha')
beta = ensure_float(beta, _zero, 'beta')
nb_dim = ensure_int(nb_dim, _ifour, 'nb_dim')
return Apply(self, [img, kern, output, desc, alpha, beta, nb_dim],
return Apply(self, [img, kern, output, desc, alpha, beta],
[output.type()])
def grad(self, inp, grads):
img, kerns, output, desc, alpha, beta, nb_dim = inp
img, kerns, output, desc, alpha, beta = inp
top, = grads
top = gpu_contiguous(top)
......@@ -640,14 +639,13 @@ class GpuDnnConv(DnnBase, COp):
d_kerns = GpuDnnConvGradW()(img, top, gpu_alloc_empty(*kerns.shape), desc)
d_alpha = grad_not_implemented(self, 4, alpha)
d_beta = grad_not_implemented(self, 5, beta)
d_nb_dim = grad_not_implemented(self, 6, nb_dim)
return [d_img * alpha, d_kerns * alpha, top * beta,
DisconnectedType()(), d_alpha, d_beta, d_nb_dim]
DisconnectedType()(), d_alpha, d_beta]
def connection_pattern(self, node):
# not connected to desc
return [[1], [1], [1], [0], [1], [1], [1]]
return [[1], [1], [1], [0], [1], [1]]
@staticmethod
def get_out_shape(ishape, kshape, border_mode, subsample):
......@@ -695,7 +693,7 @@ class GpuDnnConv3d(GpuDnnConv):
"""
__props__ = ('workmem', 'inplace')
__input_name__ = ('image', 'kernel', 'output',
'descriptor', 'alpha', 'beta', 'nb_dim')
'descriptor', 'alpha', 'beta')
def __init__(self, workmem=None, inplace=False):
"""
......@@ -705,7 +703,7 @@ class GpuDnnConv3d(GpuDnnConv):
super(GpuDnnConv3d, self).__init__(workmem='guess', inplace=inplace)
assert self.workmem in ['none', 'time','guess']
def make_node(self, img, kern, output, desc, alpha=None, beta=None, nb_dim=None):
def make_node(self, img, kern, output, desc, alpha=None, beta=None):
img = as_cuda_ndarray_variable(img)
kern = as_cuda_ndarray_variable(kern)
......@@ -721,13 +719,12 @@ class GpuDnnConv3d(GpuDnnConv):
raise TypeError('desc must be cudnnConvolutionDescriptor_t')
alpha = ensure_float(alpha, _one, 'alpha')
beta = ensure_float(beta, _zero, 'beta')
nb_dim = ensure_int(nb_dim, _ifive, 'nb_dim')
return Apply(self, [img, kern, output, desc, alpha, beta, nb_dim],
return Apply(self, [img, kern, output, desc, alpha, beta],
[output.type()])
def grad(self, inp, grads):
img, kerns, output, desc, alpha, beta, nb_dim = inp
img, kerns, output, desc, alpha, beta = inp
top, = grads
top = gpu_contiguous(top)
......@@ -736,10 +733,9 @@ class GpuDnnConv3d(GpuDnnConv):
d_kerns = GpuDnnConvGrad3dW()(img, top, gpu_alloc_empty(*kerns.shape), desc)
d_alpha = grad_not_implemented(self, 4, alpha)
d_beta = grad_not_implemented(self, 5, beta)
d_nb_dim = grad_not_implemented(self, 6, nb_dim)
return [d_img * alpha, d_kerns * alpha, top * beta,
DisconnectedType()(), d_alpha, d_beta, d_nb_dim]
DisconnectedType()(), d_alpha, d_beta]
@staticmethod
def get_out_shape(ishape, kshape, border_mode, subsample):
......@@ -788,7 +784,7 @@ class GpuDnnConvGradW(DnnBase, COp):
"""
__props__ = ('workmem', 'inplace',)
__input_name__ = ('image', 'grad', 'output', 'descriptor', 'alpha', 'beta', 'nb_dim')
__input_name__ = ('image', 'grad', 'output', 'descriptor', 'alpha', 'beta')
def __init__(self, inplace=False, workmem=None):
COp.__init__(self, ["dnn_base.c", "dnn_conv_base.c", "dnn_gw.c"],
......@@ -809,7 +805,7 @@ class GpuDnnConvGradW(DnnBase, COp):
self.inplace = False
def grad(self, inp, grads):
img, top, output, desc, alpha, beta, nb_dim = inp
img, top, output, desc, alpha, beta = inp
kerns, = grads
kerns = gpu_contiguous(kerns)
......@@ -818,14 +814,13 @@ class GpuDnnConvGradW(DnnBase, COp):
d_top = GpuDnnConv()(img, kerns, gpu_alloc_empty(*top.shape), desc)
d_alpha = grad_not_implemented(self, 4, alpha)
d_beta = grad_not_implemented(self, 5, beta)
d_nb_dim = grad_not_implemented(self, 6, nb_dim)
return (d_img * alpha, d_top * alpha, kerns * beta,
DisconnectedType()(), d_alpha, d_beta, d_nb_dim)
DisconnectedType()(), d_alpha, d_beta)
def connection_pattern(self, node):
# not connected to desc
return [[1], [1], [1], [0], [1], [1], [1]]
return [[1], [1], [1], [0], [1], [1]]
def get_op_params(self):
if self.inplace:
......@@ -854,7 +849,7 @@ class GpuDnnConvGradW(DnnBase, COp):
return inplace_def + [alg_def, alg_choose_def]
def make_node(self, img, topgrad, output, desc, alpha=None, beta=None, nb_dim=None):
def make_node(self, img, topgrad, output, desc, alpha=None, beta=None):
img = as_cuda_ndarray_variable(img)
topgrad = as_cuda_ndarray_variable(topgrad)
output = as_cuda_ndarray_variable(output)
......@@ -871,10 +866,8 @@ class GpuDnnConvGradW(DnnBase, COp):
alpha = ensure_float(alpha, _one, 'alpha')
beta = ensure_float(beta, _zero, 'beta')
nb_dim = ensure_int(nb_dim, _ifour, 'nb_dim')
return Apply(self, [img, topgrad, output, desc, alpha, beta, nb_dim],
return Apply(self, [img, topgrad, output, desc, alpha, beta],
[output.type()])
def infer_shape(self, node, shape):
......@@ -890,14 +883,14 @@ class GpuDnnConv3dGradW(GpuDnnConvGradW):
"""
__props__ = ('workmem', 'inplace',)
__input_name__ = ('image', 'grad', 'output', 'descriptor', 'alpha', 'beta', 'nb_dim')
__input_name__ = ('image', 'grad', 'output', 'descriptor', 'alpha', 'beta')
def __init__(self, inplace=False, workmem=None):
super(GpuDnnConv3dGradW, self).__init__(inplace=inplace, workmem='none')
assert self.workmem in ['none', 'time','guess']
def grad(self, inp, grads):
img, top, output, desc, alpha, beta, nb_dim = inp
img, top, output, desc, alpha, beta = inp
kerns, = grads
kerns = gpu_contiguous(kerns)
......@@ -906,12 +899,11 @@ class GpuDnnConv3dGradW(GpuDnnConvGradW):
d_top = GpuDnnConv3d()(img, kerns, gpu_alloc_empty(*top.shape), desc)
d_alpha = grad_not_implemented(self, 4, alpha)
d_beta = grad_not_implemented(self, 5, beta)
d_nb_dim = grad_not_implemented(self, 6, nb_dim)
return (d_img * alpha, d_top * alpha, kerns * beta,
DisconnectedType()(), d_alpha, d_beta, d_nb_dim)
DisconnectedType()(), d_alpha, d_beta)
def make_node(self, img, topgrad, output, desc, alpha=None, beta=None, nb_dim=None):
def make_node(self, img, topgrad, output, desc, alpha=None, beta=None):
img = as_cuda_ndarray_variable(img)
topgrad = as_cuda_ndarray_variable(topgrad)
output = as_cuda_ndarray_variable(output)
......@@ -929,9 +921,8 @@ class GpuDnnConv3dGradW(GpuDnnConvGradW):
alpha = ensure_float(alpha, _one, 'alpha')
beta = ensure_float(beta, _zero, 'beta')
nb_dim = ensure_int(nb_dim, _ifive, 'nb_dim')
return Apply(self, [img, topgrad, output, desc, alpha, beta, nb_dim],
return Apply(self, [img, topgrad, output, desc, alpha, beta],
[output.type()])
......@@ -946,8 +937,7 @@ class GpuDnnConvGradI(DnnBase, COp):
"""
__props__ = ('workmem', 'inplace',)
__input_name__ = ('kernel', 'grad', 'output',
'descriptor', 'alpha', 'beta', 'nb_dim')
__input_name__ = ('kernel', 'grad', 'output', 'descriptor', 'alpha', 'beta')
def __init__(self, inplace=False, workmem=None):
COp.__init__(self, ["dnn_base.c", "dnn_conv_base.c", "dnn_gi.c"],
......@@ -966,7 +956,7 @@ class GpuDnnConvGradI(DnnBase, COp):
self.workmem = 'none'
def grad(self, inp, grads):
kerns, top, output, desc, alpha, beta, nb_dim = inp
kerns, top, output, desc, alpha, beta = inp
img, = grads
img = gpu_contiguous(img)
......@@ -975,14 +965,13 @@ class GpuDnnConvGradI(DnnBase, COp):
d_top = GpuDnnConv()(img, kerns, gpu_alloc_empty(*top.shape), desc)
d_alpha = grad_not_implemented(self, 4, alpha)
d_beta = grad_not_implemented(self, 5, beta)
d_nb_dim = grad_not_implemented(self, 6, nb_dim)
return (d_kerns * alpha, d_top * alpha, img * beta,
DisconnectedType()(), d_alpha, d_beta, d_nb_dim)
DisconnectedType()(), d_alpha, d_beta)
def connection_pattern(self, node):
# not connected to desc
return [[1], [1], [1], [0], [1], [1], [1]]
return [[1], [1], [1], [0], [1], [1]]
def get_op_params(self):
if self.inplace:
......@@ -1011,7 +1000,7 @@ class GpuDnnConvGradI(DnnBase, COp):
return inplace_def + [alg_def, alg_choose_def]
def make_node(self, kern, topgrad, output, desc, alpha=None, beta=None, nb_dim=None):
def make_node(self, kern, topgrad, output, desc, alpha=None, beta=None):
kern = as_cuda_ndarray_variable(kern)
topgrad = as_cuda_ndarray_variable(topgrad)
output = as_cuda_ndarray_variable(output)
......@@ -1028,9 +1017,8 @@ class GpuDnnConvGradI(DnnBase, COp):
alpha = ensure_float(alpha, _one, 'alpha')
beta = ensure_float(beta, _zero, 'beta')
nb_dim = ensure_int(nb_dim, _ifour, 'nb_dim')
return Apply(self, [kern, topgrad, output, desc, alpha, beta, nb_dim],
return Apply(self, [kern, topgrad, output, desc, alpha, beta],
[output.type()])
def infer_shape(self, node, shape):
......@@ -1048,8 +1036,7 @@ class GpuDnnConv3dGradI(GpuDnnConvGradI):
"""
__props__ = ('inplace',)
__input_name__ = ('kernel', 'grad', 'output',
'descriptor', 'alpha', 'beta', 'nb_dim')
__input_name__ = ('kernel', 'grad', 'output', 'descriptor', 'alpha', 'beta')
def __init__(self, inplace=False, workmem=None):
### deterministic (default value) is not yet supported for conv3d
......@@ -1060,7 +1047,7 @@ class GpuDnnConv3dGradI(GpuDnnConvGradI):
def grad(self, inp, grads):
kerns, top, output, desc, alpha, beta, nb_dim = inp
kerns, top, output, desc, alpha, beta = inp
img, = grads
img = gpu_contiguous(img)
......@@ -1069,12 +1056,11 @@ class GpuDnnConv3dGradI(GpuDnnConvGradI):
d_top = GpuDnnConv3d()(img, kerns, gpu_alloc_empty(*top.shape), desc)
d_alpha = grad_not_implemented(self, 4, alpha)
d_beta = grad_not_implemented(self, 5, beta)
d_nb_dim = grad_not_implemented(self, 6, nb_dim)
return (d_kerns * alpha, d_top * alpha, img * beta,
DisconnectedType()(), d_alpha, d_beta, d_nb_dim)
DisconnectedType()(), d_alpha, d_beta)
def make_node(self, kern, topgrad, output, desc, alpha=None, beta=None, nb_dim=None):
def make_node(self, kern, topgrad, output, desc, alpha=None, beta=None):
kern = as_cuda_ndarray_variable(kern)
topgrad = as_cuda_ndarray_variable(topgrad)
output = as_cuda_ndarray_variable(output)
......@@ -1091,9 +1077,8 @@ class GpuDnnConv3dGradI(GpuDnnConvGradI):
alpha = ensure_float(alpha, _one, 'alpha')
beta = ensure_float(beta, _zero, 'beta')
nb_dim = ensure_int(nb_dim, _ifive, 'nb_dim')
return Apply(self, [kern, topgrad, output, desc, alpha, beta, nb_dim],
return Apply(self, [kern, topgrad, output, desc, alpha, beta],
[output.type()])
......
theano/sandbox/cuda/dnn_fwd.c
浏览文件 @ 486b760d
......@@ -3,7 +3,7 @@
int
APPLY_SPECIFIC(conv_fwd)(CudaNdarray *input, CudaNdarray *kerns,
CudaNdarray *om, cudnnConvolutionDescriptor_t desc,
float alpha, float beta, int nb_dim, CudaNdarray **output) {
float alpha, float beta, CudaNdarray **output) {
cudnnStatus_t err = CUDNN_STATUS_SUCCESS;
if (CudaNdarray_HOST_DIMS(input)[1] != CudaNdarray_HOST_DIMS(kerns)[1]) {
......@@ -17,6 +17,8 @@ APPLY_SPECIFIC(conv_fwd)(CudaNdarray *input, CudaNdarray *kerns,
if (c_set_filterNd(kerns, APPLY_SPECIFIC(kerns)) == -1)
return 1;
int nb_dim = CudaNdarray_NDIM(input);
#ifdef CONV_INPLACE
Py_XDECREF(*output);
*output = om;
......
theano/sandbox/cuda/dnn_gi.c
浏览文件 @ 486b760d
......@@ -3,7 +3,7 @@
int
APPLY_SPECIFIC(conv_gi)(CudaNdarray *kerns, CudaNdarray *output,
CudaNdarray *im, cudnnConvolutionDescriptor_t desc,
float alpha, float beta, int nb_dim, CudaNdarray **input) {
float alpha, float beta, CudaNdarray **input) {
cudnnStatus_t err = CUDNN_STATUS_SUCCESS;
if (CudaNdarray_HOST_DIMS(im)[1] != CudaNdarray_HOST_DIMS(kerns)[1]) {
......@@ -17,6 +17,8 @@ APPLY_SPECIFIC(conv_gi)(CudaNdarray *kerns, CudaNdarray *output,
if (c_set_filterNd(kerns, APPLY_SPECIFIC(kerns)) == -1)
return 1;
int nb_dim = CudaNdarray_NDIM(output);
#ifdef CONV_INPLACE
Py_XDECREF(*input);
*input = im;
......
theano/sandbox/cuda/dnn_gw.c
浏览文件 @ 486b760d
......@@ -3,7 +3,7 @@
int
APPLY_SPECIFIC(conv_gw)(CudaNdarray *input, CudaNdarray *output,
CudaNdarray *km, cudnnConvolutionDescriptor_t desc,
float alpha, float beta, int nb_dim, CudaNdarray **kerns) {
float alpha, float beta, CudaNdarray **kerns) {
cudnnStatus_t err = CUDNN_STATUS_SUCCESS;
if (CudaNdarray_HOST_DIMS(input)[1] != CudaNdarray_HOST_DIMS(km)[1]) {
......@@ -17,6 +17,8 @@ APPLY_SPECIFIC(conv_gw)(CudaNdarray *input, CudaNdarray *output,
if (c_set_tensorNd(output, APPLY_SPECIFIC(output)) == -1)
return 1;
int nb_dim = CudaNdarray_NDIM(output);
#ifdef CONV_INPLACE
Py_XDECREF(*kerns);
*kerns = km;
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论