Merge branch 'develop' of https://github.com/PaddlePaddle/paddle into refine-act-GRU
guosheng
7 years ago
commit
443391cec2
@ -0,0 +1,119 @@
|
||||
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved.
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License. */
|
||||
|
||||
#include "paddle/framework/tensor_util.h"
|
||||
|
||||
namespace paddle {
|
||||
namespace framework {
|
||||
template <typename Predicate, typename DevCtx>
|
||||
struct AnyDTypeVisitor {
|
||||
Predicate predicate_;
|
||||
const Tensor& tensor_;
|
||||
const DevCtx& ctx_;
|
||||
Tensor* out_;
|
||||
|
||||
AnyDTypeVisitor(Predicate predicate, const Tensor& tensor, const DevCtx& ctx,
|
||||
Tensor* out)
|
||||
: predicate_(predicate), tensor_(tensor), ctx_(ctx), out_(out) {}
|
||||
|
||||
template <typename T>
|
||||
void operator()() const {
|
||||
auto t = EigenVector<T>::Flatten(tensor_);
|
||||
auto o = EigenScalar<bool>::From(*out_);
|
||||
// return any of predicate_(t) is true.
|
||||
o.device(*ctx_.eigen_device()) = predicate_(t).any();
|
||||
}
|
||||
};
|
||||
|
||||
template <typename Predicate, typename DevCtx>
|
||||
inline void AnyImpl(Predicate predicate, const framework::Tensor& tensor,
|
||||
const DevCtx& ctx, framework::Tensor* out) {
|
||||
VisitDataType(ToDataType(tensor.type()), AnyDTypeVisitor<Predicate, DevCtx>(
|
||||
predicate, tensor, ctx, out));
|
||||
}
|
||||
|
||||
template <typename Predicate>
|
||||
struct AnyVisitor : public boost::static_visitor<bool> {
|
||||
const framework::Tensor& tensor_;
|
||||
Predicate predicate_;
|
||||
|
||||
AnyVisitor(const framework::Tensor& tensor, Predicate predicate)
|
||||
: tensor_(tensor), predicate_(std::move(predicate)) {}
|
||||
|
||||
template <typename Place>
|
||||
bool operator()(const Place& place) const {
|
||||
framework::Tensor out;
|
||||
out.Resize({1});
|
||||
out.mutable_data<bool>(place);
|
||||
auto* ctx = platform::DeviceContextPool::Instance().GetByPlace(place);
|
||||
AnyImpl(predicate_, tensor_, *ctx, &out);
|
||||
return this->GetResult(out, place);
|
||||
}
|
||||
|
||||
bool GetResult(const framework::Tensor& out,
|
||||
const platform::CUDAPlace& gpu) const {
|
||||
platform::CPUPlace cpu;
|
||||
framework::Tensor tmp;
|
||||
tmp.Resize({1});
|
||||
tmp.mutable_data<bool>(cpu);
|
||||
auto gpuctx = platform::DeviceContextPool::Instance().Get(gpu);
|
||||
gpuctx->Wait();
|
||||
CopyFrom(out, cpu, *gpuctx, &tmp);
|
||||
gpuctx->Wait();
|
||||
return GetResult(tmp, cpu);
|
||||
}
|
||||
|
||||
bool GetResult(const framework::Tensor& out,
|
||||
const platform::CPUPlace& cpu) const {
|
||||
return *out.data<bool>();
|
||||
}
|
||||
};
|
||||
|
||||
template <typename Predicate>
|
||||
inline bool Any(const framework::Tensor& tensor, Predicate predicate) {
|
||||
AnyVisitor<Predicate> visitor(tensor, predicate);
|
||||
auto place = tensor.place();
|
||||
return platform::VisitPlace(place, visitor);
|
||||
}
|
||||
|
||||
struct HasNANPredicate {
|
||||
template <typename T>
|
||||
auto operator()(const T& eigen_vec) const
|
||||
-> decltype(std::declval<T>().isnan()) {
|
||||
// Cast eigen_vector to vector of bool. true if is inf.
|
||||
return eigen_vec.isnan();
|
||||
}
|
||||
};
|
||||
|
||||
bool HasNAN(const framework::Tensor& tensor) {
|
||||
HasNANPredicate predicate;
|
||||
return Any(tensor, predicate);
|
||||
}
|
||||
|
||||
struct HasInfPredicate {
|
||||
template <typename T>
|
||||
auto operator()(const T& eigen_vec) const
|
||||
-> decltype(std::declval<T>().isinf()) {
|
||||
// Cast eigen_vector to vector of bool. true if is inf.
|
||||
return eigen_vec.isinf();
|
||||
}
|
||||
};
|
||||
|
||||
bool HasInf(const framework::Tensor& tensor) {
|
||||
HasInfPredicate predicate;
|
||||
return Any(tensor, predicate);
|
||||
}
|
||||
|
||||
} // namespace framework
|
||||
} // namespace paddle
|
||||
@ -0,0 +1 @@
|
||||
./tensor_util.cc
|
||||
@ -0,0 +1,57 @@
|
||||
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved.
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License. */
|
||||
|
||||
#include "gtest/gtest.h"
|
||||
#include "paddle/framework/tensor_util.h"
|
||||
#include "paddle/platform/device_context.h"
|
||||
#include "paddle/platform/place.h"
|
||||
|
||||
namespace paddle {
|
||||
namespace framework {
|
||||
|
||||
static __global__ void FillNAN(float* buf) {
|
||||
buf[0] = 0.0;
|
||||
buf[1] = 0.1;
|
||||
buf[2] = NAN;
|
||||
}
|
||||
static __global__ void FillInf(float* buf) {
|
||||
buf[0] = 0.0;
|
||||
buf[1] = INFINITY;
|
||||
buf[2] = 0.5;
|
||||
}
|
||||
|
||||
TEST(HasNAN, GPU) {
|
||||
Tensor tensor;
|
||||
platform::CUDAPlace gpu(0);
|
||||
auto& pool = platform::DeviceContextPool::Instance();
|
||||
auto* cuda_ctx = pool.GetByPlace(gpu);
|
||||
float* buf = tensor.mutable_data<float>({3}, gpu);
|
||||
FillNAN<<<1, 1, 0, cuda_ctx->stream()>>>(buf);
|
||||
cuda_ctx->Wait();
|
||||
ASSERT_TRUE(HasNAN(tensor));
|
||||
}
|
||||
|
||||
TEST(HasInf, GPU) {
|
||||
Tensor tensor;
|
||||
platform::CUDAPlace gpu(0);
|
||||
auto& pool = platform::DeviceContextPool::Instance();
|
||||
auto* cuda_ctx = pool.GetByPlace(gpu);
|
||||
float* buf = tensor.mutable_data<float>({3}, gpu);
|
||||
FillInf<<<1, 1, 0, cuda_ctx->stream()>>>(buf);
|
||||
cuda_ctx->Wait();
|
||||
ASSERT_TRUE(HasInf(tensor));
|
||||
}
|
||||
|
||||
} // namespace framework
|
||||
} // namespace paddle
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue