提交 f3818bd3 编写于 作者: X xzl

Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_dilation

...@@ -27,6 +27,7 @@ class BeamSearchDecodeOp : public framework::OperatorBase { ...@@ -27,6 +27,7 @@ class BeamSearchDecodeOp : public framework::OperatorBase {
void Run(const framework::Scope& scope, void Run(const framework::Scope& scope,
const platform::DeviceContext& dev_ctx) const override { const platform::DeviceContext& dev_ctx) const override {
framework::ExecutionContext ctx(*this, scope, dev_ctx); framework::ExecutionContext ctx(*this, scope, dev_ctx);
const LoDTensorArray* ids = ctx.Input<LoDTensorArray>("Ids"); const LoDTensorArray* ids = ctx.Input<LoDTensorArray>("Ids");
const LoDTensorArray* scores = ctx.Input<LoDTensorArray>("Scores"); const LoDTensorArray* scores = ctx.Input<LoDTensorArray>("Scores");
const size_t step_num = ids->size(); const size_t step_num = ids->size();
......
...@@ -29,7 +29,7 @@ class L1NormKernel : public framework::OpKernel<T> { ...@@ -29,7 +29,7 @@ class L1NormKernel : public framework::OpKernel<T> {
Out->mutable_data<T>(context.GetPlace()); Out->mutable_data<T>(context.GetPlace());
auto x = framework::EigenVector<T>::Flatten(*X); auto x = framework::EigenVector<T>::Flatten(*X);
auto out = framework::EigenVector<T>::Flatten(*Out); auto out = framework::EigenScalar<T>::From(*Out);
auto place = context.GetEigenDevice<Place>(); auto place = context.GetEigenDevice<Place>();
out.device(place) = x.abs().sum(); out.device(place) = x.abs().sum();
......
...@@ -29,7 +29,7 @@ class SquaredL2NormKernel : public framework::OpKernel<T> { ...@@ -29,7 +29,7 @@ class SquaredL2NormKernel : public framework::OpKernel<T> {
Out->mutable_data<T>(context.GetPlace()); Out->mutable_data<T>(context.GetPlace());
auto x = framework::EigenVector<T>::Flatten(*X); auto x = framework::EigenVector<T>::Flatten(*X);
auto out = framework::EigenVector<T>::Flatten(*Out); auto out = framework::EigenScalar<T>::From(*Out);
auto place = context.GetEigenDevice<Place>(); auto place = context.GetEigenDevice<Place>();
out.device(place) = x.square().sum(); out.device(place) = x.square().sum();
......
...@@ -42,6 +42,9 @@ limitations under the License. */ ...@@ -42,6 +42,9 @@ limitations under the License. */
#include "paddle/platform/gpu_info.h" #include "paddle/platform/gpu_info.h"
#endif #endif
// disable auto conversion to list in Python
PYBIND11_MAKE_OPAQUE(paddle::framework::LoDTensorArray);
namespace paddle { namespace paddle {
namespace pybind { namespace pybind {
static size_t UniqueIntegerGenerator(const std::string &prefix) { static size_t UniqueIntegerGenerator(const std::string &prefix) {
......
...@@ -839,6 +839,23 @@ def batch_norm(input, ...@@ -839,6 +839,23 @@ def batch_norm(input,
return helper.append_activation(batch_norm_out) return helper.append_activation(batch_norm_out)
def beam_search_decode(ids, scores, main_program=None, startup_program=None):
helper = LayerHelper('beam_search_decode', **locals())
sentence_ids = helper.create_tmp_variable(dtype=ids.data_type)
sentence_scores = helper.create_tmp_variable(dtype=ids.data_type)
helper.append_op(
type="beam_search_decode",
inputs={"Ids": ids,
"Scores": scores},
outputs={
"SentenceIds": sentence_ids,
"SentenceScores": sentence_scores
})
return sentence_ids, sentence_scores
class BlockGuard(object): class BlockGuard(object):
""" """
BlockGuard class. BlockGuard class.
......
import unittest
import numpy as np
import paddle.v2.framework.core as core
from paddle.v2.framework.op import Operator
class TestBeamSearchDecodeOp(unittest.TestCase):
def setUp(self):
self.scope = core.Scope()
self.cpu_place = core.CPUPlace()
def append_lod_tensor(self, tensor_array, lod, data):
lod_tensor = core.LoDTensor()
lod_tensor.set_lod(lod)
lod_tensor.set(data, self.cpu_place)
tensor_array.append(lod_tensor)
def test_get_set(self):
ids = self.scope.var("ids").get_lod_tensor_array()
self.append_lod_tensor(
ids, [[0, 3, 6], [0, 1, 2, 3, 4, 5, 6]],
np.array(
[1, 2, 3, 4, 5, 6], dtype="int64"))
self.append_lod_tensor(
ids, [[0, 3, 6], [0, 1, 1, 3, 5, 5, 6]],
np.array(
[0, 1, 2, 3, 4, 5], dtype="int64"))
self.append_lod_tensor(
ids, [[0, 3, 6], [0, 0, 1, 2, 3, 4, 5]],
np.array(
[0, 1, 2, 3, 4], dtype="int64"))
scores = self.scope.var("scores").get_lod_tensor_array()
self.append_lod_tensor(
scores, [[0, 3, 6], [0, 1, 2, 3, 4, 5, 6]],
np.array(
[1, 2, 3, 4, 5, 6], dtype="float32"))
self.append_lod_tensor(
scores, [[0, 3, 6], [0, 1, 1, 3, 5, 5, 6]],
np.array(
[0, 1, 2, 3, 4, 5], dtype="float32"))
self.append_lod_tensor(
scores, [[0, 3, 6], [0, 0, 1, 2, 3, 4, 5]],
np.array(
[0, 1, 2, 3, 4], dtype="float32"))
sentence_ids = self.scope.var("sentence_ids").get_tensor()
sentence_scores = self.scope.var("sentence_scores").get_tensor()
beam_search_decode_op = Operator(
"beam_search_decode",
# inputs
Ids="ids",
Scores="scores",
# outputs
SentenceIds="sentence_ids",
SentenceScores="sentence_scores")
ctx = core.DeviceContext.create(self.cpu_place)
beam_search_decode_op.run(self.scope, ctx)
expected_lod = [[0, 4, 8], [0, 1, 3, 6, 9, 10, 13, 16, 19]]
self.assertEqual(sentence_ids.lod(), expected_lod)
self.assertEqual(sentence_scores.lod(), expected_lod)
expected_data = np.array(
[2, 1, 0, 3, 1, 0, 3, 2, 1, 5, 4, 3, 2, 4, 4, 3, 6, 5, 4], "int64")
self.assertTrue(np.array_equal(np.array(sentence_ids), expected_data))
self.assertTrue(
np.array_equal(np.array(sentence_scores), expected_data))
if __name__ == '__main__':
unittest.main()
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册