def gradcheck_model(cost,
params,
extravars=(),
extravals=(),
atol=1e-8,
eps=1e-9):
precision = cgt.get_precision()
if precision == "single":
cgt.utils.warn(
"You're doing a gradient check with %s precision. Use double or better yet quad for best results"
% (precision))
assert all(param.is_input() for param in params)
assert len(extravars) == len(extravals)
# Convert to Argument nodes
param_args = [
cgt.core.Argument(typ=s.typ, name=s.name) if s.is_data() else s
for s in params
]
# Get new cost in terms o farguments
cost = cgt.core.clone(cost, replace=dict(zip(params, param_args)))
grads = cgt.grad(cost, param_args)
paramvals = [param.op.get_value() for param in params]
fcost = cgt.function(param_args, cost, givens=zip(extravars, extravals))
fgrad = cgt.function(param_args, grads, givens=zip(extravars, extravals))
angrads = fgrad(*paramvals)
nugrads = numeric_grad_multi(fcost, paramvals, eps=eps)
for (angrad, nugrad) in zip(angrads, nugrads):
assert np.allclose(angrad, nugrad, atol=atol)
def test_cudnn():
compile_info = get_compile_info()
if not (compile_info["CGT_ENABLE_CUDNN"] and compile_info["CGT_ENABLE_CUDA"]):
raise SkipTest("CUDNN not enabled. Skipping this test")
Xval = nr.randn(2,3,19,18)
Wval = nr.randn(5,3,3,3)
bval = nr.randn(1,5,1,1)
X = cgt.tensor4("X", fixed_shape=Xval.shape)
W = cgt.tensor4("W", fixed_shape=Wval.shape)
b = cgt.tensor4("b", fixed_shape=bval.shape)
Y = cgt.core.Result(cudnn_ops.CudnnConvForward(1,1,1,1),[X, W, b])
Y2 = nr.randn(*cgt.core.infer_shape(Y))
fY = cgt.function([X,W,b],Y)
Yval = fY(Xval,Wval,bval)
cost = (Y*Y2).sum()
fcost = cgt.function([X,W,b],cost)
fgrad = cgt.function([X,W,b],cgt.grad(cost, [X,W,b]))
angrads = fgrad(Xval,Wval,bval)
nugrads = numeric_grad_multi(fcost, [Xval, Wval, bval],eps=1e-3)
for (nugrad,angrad) in zip(nugrads,angrads):
assert np.allclose(nugrad, angrad, rtol=9e-3, atol=1e-7)
def test_cudnn():
if not get_compile_info()["CGT_ENABLE_CUDNN"]:
raise SkipTest("CUDNN not enabled. Skipping this test")
Xval = nr.randn(2, 3, 19, 18)
Wval = nr.randn(5, 3, 3, 3)
bval = nr.randn(1, 5, 1, 1)
X = cgt.tensor4("X", fixed_shape=Xval.shape)
W = cgt.tensor4("W", fixed_shape=Wval.shape)
b = cgt.tensor4("b", fixed_shape=bval.shape)
Y = cgt.core.Result(cudnn_ops.CudnnConvForward(1, 1, 1, 1), [X, W, b])
Y2 = nr.randn(*cgt.core.infer_shape(Y))
fY = cgt.function([X, W, b], Y)
Yval = fY(Xval, Wval, bval)
cost = (Y * Y2).sum()
fcost = cgt.function([X, W, b], cost)
fgrad = cgt.function([X, W, b], cgt.grad(cost, [X, W, b]))
angrads = fgrad(Xval, Wval, bval)
nugrads = numeric_grad_multi(fcost, [Xval, Wval, bval], eps=1e-3)
for (nugrad, angrad) in zip(nugrads, angrads):
assert np.allclose(nugrad, angrad)
def test_cudnn():
with cgt.scoped_update_config(precision="double",backend="native"):
if not get_compile_info()["CGT_ENABLE_CUDNN"]:
raise SkipTest("CUDNN not enabled. Skipping this test")
Xval = nr.randn(2,3,19,18)
Wval = nr.randn(5,3,3,3)
bval = nr.randn(1,5,1,1)
X = cgt.tensor4("X", fixed_shape=Xval.shape)
W = cgt.tensor4("W", fixed_shape=Wval.shape)
b = cgt.tensor4("b", fixed_shape=bval.shape)
Y = cgt.core.Result(cudnn_ops.CudnnConvForward(1,1,1,1),[X, W, b])
Y2 = nr.randn(*cgt.core.infer_shape(Y))
fY = cgt.function([X,W,b],Y)
Yval = fY(Xval,Wval,bval)
cost = (Y*Y2).sum()
fcost = cgt.function([X,W,b],cost)
fgrad = cgt.function([X,W,b],cgt.grad(cost, [X,W,b]))
angrads = fgrad(Xval,Wval,bval)
nugrads = numeric_grad_multi(fcost, [Xval, Wval, bval],eps=1e-3)
for (nugrad,angrad) in zip(nugrads,angrads):
assert np.allclose(nugrad, angrad)
def gradcheck_model(cost, params, extravars=(), extravals=(), atol=1e-8, eps=1e-9):
precision = cgt.get_precision()
if precision == "single":
cgt.utils.warn("You're doing a gradient check with %s precision. Use double or better yet quad for best results"%(precision))
assert all(param.is_input() for param in params)
assert len(extravars) == len(extravals)
# Convert to Argument nodes
param_args = [cgt.core.Argument(typ=s.typ,name=s.name)if s.is_data() else s for s in params]
# Get new cost in terms o farguments
cost = cgt.core.clone(cost, replace=dict(zip(params,param_args)))
grads = cgt.grad(cost, param_args)
paramvals = [param.op.get_value() for param in params]
fcost = cgt.function(param_args, cost, givens=zip(extravars,extravals))
fgrad = cgt.function(param_args, grads,givens=zip(extravars,extravals))
angrads = fgrad(*paramvals)
nugrads = numeric_grad_multi(fcost, paramvals, eps=eps)
for (angrad,nugrad) in zip(angrads,nugrads):
assert np.allclose(angrad,nugrad,atol=atol)
