How to use the cgt.nn.SpatialConvolution function in cgt
To help you get started, we’ve selected a few cgt examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
joschu / cgt / examples / cgt_theano_feedforward_comparison.py View on Github 
def build_convnet_return_loss(X, y):
np.random.seed(0)
conv1 = nn.rectify(
nn.SpatialConvolution(1, 32, kernelshape=(3,3), pad=(0,0),
weight_init=nn.IIDGaussian(std=.1))(X))
pool1 = nn.max_pool_2d(conv1, kernelshape=(3,3), stride=(2,2))
conv2 = nn.rectify(
nn.SpatialConvolution(32, 32, kernelshape=(3,3), pad=(0,0),
weight_init=nn.IIDGaussian(std=.1))(pool1))
pool2 = nn.max_pool_2d(conv2, kernelshape=(3,3), stride=(2,2))
d0,d1,d2,d3 = pool2.shape
flatlayer = pool2.reshape([d0,d1*d2*d3])
nfeats = cgt.infer_shape(flatlayer)[1]
logprobs = nn.logsoftmax(nn.Affine(nfeats, 10)(flatlayer))
loss = -logprobs[cgt.arange(X.shape[0]), y].mean()
return lossX = cgt.tensor4('X', fixed_shape=(None,) + x_shape)
U = cgt.matrix('U', fixed_shape=(None,) + u_shape)
# encoding
Xlevels = {}
for level in range(levels[-1]+1):
if level == 0:
Xlevel = X
else:
if level == 1:
xlevelm1_c_dim = x_c_dim
xlevel_c_dim = x1_c_dim
else:
xlevelm1_c_dim = xlevel_c_dim
xlevel_c_dim = 2 * xlevel_c_dim
Xlevel_1 = nn.rectify(nn.SpatialConvolution(xlevelm1_c_dim, xlevel_c_dim, kernelshape=(3,3), pad=(1,1), stride=(1,1), name='conv%d_1'%level,
weight_init=nn.IIDGaussian(std=0.01))(Xlevels[level-1]))
Xlevel_2 = nn.rectify(nn.SpatialConvolution(xlevel_c_dim, xlevel_c_dim, kernelshape=(3,3), pad=(1,1), stride=(1,1), name='conv%d_2'%level,
weight_init=nn.IIDGaussian(std=0.01))(Xlevel_1))
Xlevel = nn.max_pool_2d(Xlevel_2, kernelshape=(2,2), pad=(0,0), stride=(2,2))
Xlevels[level] = Xlevel
# bilinear
Xlevels_next_pred_0 = {}
Ylevels = OrderedDict()
Ylevels_diff_pred = OrderedDict()
for level in levels:
Xlevel = Xlevels[level]
Xlevel_diff_pred = Bilinear(input_shapes, b=None, axis=2, name='bilinear%d'%level)(Xlevel, U)
Xlevels_next_pred_0[level] = Xlevel + Xlevel_diff_pred
Ylevels[level] = Xlevel.reshape((Xlevel.shape[0], cgt.mul_multi(Xlevel.shape[1:])))
Ylevels_diff_pred[level] = Xlevel_diff_pred.reshape((Xlevel_diff_pred.shape[0], cgt.mul_multi(Xlevel_diff_pred.shape[1:])))def build_convnet_return_loss(X, y):
np.random.seed(0)
conv1 = nn.rectify(
nn.SpatialConvolution(1, 32, kernelshape=(3,3), pad=(0,0),
weight_init=nn.IIDGaussian(std=.1))(X))
pool1 = nn.max_pool_2d(conv1, kernelshape=(3,3), stride=(2,2))
conv2 = nn.rectify(
nn.SpatialConvolution(32, 32, kernelshape=(3,3), pad=(0,0),
weight_init=nn.IIDGaussian(std=.1))(pool1))
pool2 = nn.max_pool_2d(conv2, kernelshape=(3,3), stride=(2,2))
d0,d1,d2,d3 = pool2.shape
flatlayer = pool2.reshape([d0,d1*d2*d3])
nfeats = cgt.infer_shape(flatlayer)[1]
logprobs = nn.logsoftmax(nn.Affine(nfeats, 10)(flatlayer))
loss = -logprobs[cgt.arange(X.shape[0]), y].mean()
return lossdef main():
parser = argparse.ArgumentParser()
parser.add_argument("--profile",action="store_true")
parser.add_argument("--unittest",action="store_true")
parser.add_argument("--epochs",type=int,default=10)
parser.add_argument("--devtype",choices=["cpu","gpu"],default="cpu")
args = parser.parse_args()
cgt.update_config(default_device=cgt.core.Device(devtype=args.devtype), backend="native")
batchsize = 64
Xshape = (batchsize, 3, 32, 32)
X = cgt.tensor4("X", fixed_shape = Xshape)
y = cgt.vector("y", fixed_shape = (batchsize,), dtype='i4')
conv1 = nn.SpatialConvolution(3, 32, kernelshape=(5,5), pad=(2,2),
weight_init=nn.IIDGaussian(std=1e-4))(X)
relu1 = nn.rectify(conv1)
pool1 = nn.max_pool_2d(relu1, kernelshape=(3,3), stride=(2,2))
conv2 = nn.SpatialConvolution(32, 32, kernelshape=(5,5), pad=(2,2),
weight_init=nn.IIDGaussian(std=0.01))(pool1)
relu2 = nn.rectify(conv2)
pool2 = nn.max_pool_2d(relu2, kernelshape=(3,3), stride=(2,2))
conv3 = nn.SpatialConvolution(32, 64, kernelshape=(5,5), pad=(2,2),
weight_init=nn.IIDGaussian(std=0.01))(pool2)
pool3 = nn.max_pool_2d(conv3, kernelshape=(3,3), stride=(2,2))
relu3 = nn.rectify(pool3)
d0,d1,d2,d3 = relu3.shape
flatlayer = relu3.reshape([d0,d1*d2*d3])
nfeats = cgt.infer_shape(flatlayer)[1]
ip1 = nn.Affine(nfeats, 10)(flatlayer)
logprobs = nn.logsoftmax(ip1)parser.add_argument("--epochs",type=int,default=10)
parser.add_argument("--devtype",choices=["cpu","gpu"],default="cpu")
args = parser.parse_args()
cgt.update_config(default_device=cgt.core.Device(devtype=args.devtype), backend="native")
batchsize = 64
Xshape = (batchsize, 3, 32, 32)
X = cgt.tensor4("X", fixed_shape = Xshape)
y = cgt.vector("y", fixed_shape = (batchsize,), dtype='i4')
conv1 = nn.SpatialConvolution(3, 32, kernelshape=(5,5), pad=(2,2),
weight_init=nn.IIDGaussian(std=1e-4))(X)
relu1 = nn.rectify(conv1)
pool1 = nn.max_pool_2d(relu1, kernelshape=(3,3), stride=(2,2))
conv2 = nn.SpatialConvolution(32, 32, kernelshape=(5,5), pad=(2,2),
weight_init=nn.IIDGaussian(std=0.01))(pool1)
relu2 = nn.rectify(conv2)
pool2 = nn.max_pool_2d(relu2, kernelshape=(3,3), stride=(2,2))
conv3 = nn.SpatialConvolution(32, 64, kernelshape=(5,5), pad=(2,2),
weight_init=nn.IIDGaussian(std=0.01))(pool2)
pool3 = nn.max_pool_2d(conv3, kernelshape=(3,3), stride=(2,2))
relu3 = nn.rectify(pool3)
d0,d1,d2,d3 = relu3.shape
flatlayer = relu3.reshape([d0,d1*d2*d3])
nfeats = cgt.infer_shape(flatlayer)[1]
ip1 = nn.Affine(nfeats, 10)(flatlayer)
logprobs = nn.logsoftmax(ip1)
loss = -logprobs[cgt.arange(batchsize), y].mean()
params = nn.get_parameters(loss)
