liyong
4 years ago
parent
f487797694
commit
fb2bd156c9
@ -0,0 +1,53 @@
|
||||
/**
|
||||
* Copyright 2020 Huawei Technologies Co., Ltd
|
||||
*
|
||||
* 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 "minddata/dataset/kernels/data/unique_op.h"
|
||||
|
||||
#include "minddata/dataset/core/tensor.h"
|
||||
#include "minddata/dataset/kernels/tensor_op.h"
|
||||
|
||||
namespace mindspore {
|
||||
namespace dataset {
|
||||
|
||||
Status UniqueOp::Compute(const TensorRow &input, TensorRow *output) {
|
||||
IO_CHECK_VECTOR(input, output);
|
||||
CHECK_FAIL_RETURN_UNEXPECTED(input.size() == 1, "Input should be one tensor");
|
||||
|
||||
auto in_tensor = input[0];
|
||||
auto in_tensor_shape = in_tensor->shape();
|
||||
auto in_tensor_type = in_tensor->type();
|
||||
|
||||
CHECK_FAIL_RETURN_UNEXPECTED(in_tensor_type.IsNumeric(), "Tensor type must be numeric.");
|
||||
CHECK_FAIL_RETURN_UNEXPECTED(in_tensor_shape.Rank() >= 2, "Tensor must be at least 2-D in order to do unique op.");
|
||||
CHECK_FAIL_RETURN_UNEXPECTED(
|
||||
in_tensor->Size() <= std::numeric_limits<int32_t>::max(),
|
||||
"UniqueOp does not support input tensor large than " + std::to_string(std::numeric_limits<int32_t>::max()));
|
||||
|
||||
RETURN_IF_NOT_OK(in_tensor->Reshape(TensorShape({in_tensor->Size()})));
|
||||
|
||||
std::shared_ptr<Tensor> out;
|
||||
std::shared_ptr<Tensor> out_idx;
|
||||
std::shared_ptr<Tensor> out_cnt;
|
||||
|
||||
RETURN_IF_NOT_OK(Unique(in_tensor, &out, &out_idx, &out_cnt));
|
||||
|
||||
output->push_back(out);
|
||||
output->push_back(out_idx);
|
||||
output->push_back(out_cnt);
|
||||
return Status::OK();
|
||||
}
|
||||
} // namespace dataset
|
||||
} // namespace mindspore
|
||||
@ -0,0 +1,45 @@
|
||||
/**
|
||||
* Copyright 2020 Huawei Technologies Co., Ltd
|
||||
*
|
||||
* 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.
|
||||
*/
|
||||
#ifndef MINDSPORE_CCSRC_MINDDATA_DATASET_KERNELS_DATA_UNIQUE_OP_H_
|
||||
#define MINDSPORE_CCSRC_MINDDATA_DATASET_KERNELS_DATA_UNIQUE_OP_H_
|
||||
|
||||
#include <limits>
|
||||
#include <vector>
|
||||
#include <memory>
|
||||
#include <string>
|
||||
|
||||
#include "minddata/dataset/core/tensor.h"
|
||||
#include "minddata/dataset/kernels/tensor_op.h"
|
||||
#include "minddata/dataset/kernels/data/data_utils.h"
|
||||
|
||||
namespace mindspore {
|
||||
namespace dataset {
|
||||
|
||||
class UniqueOp : public TensorOp {
|
||||
public:
|
||||
UniqueOp() = default;
|
||||
|
||||
~UniqueOp() override = default;
|
||||
|
||||
Status Compute(const TensorRow &input, TensorRow *output) override;
|
||||
|
||||
uint32_t NumOutput() override { return 0; }
|
||||
|
||||
std::string Name() const override { return kUniqueOp; }
|
||||
};
|
||||
} // namespace dataset
|
||||
} // namespace mindspore
|
||||
#endif // MINDSPORE_CCSRC_MINDDATA_DATASET_KERNELS_UNIQUE_OP_H_
|
||||
@ -0,0 +1,45 @@
|
||||
# Copyright 2020 Huawei Technologies Co., Ltd
|
||||
#
|
||||
# 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.
|
||||
# ==============================================================================
|
||||
"""
|
||||
Testing unique op in DE
|
||||
"""
|
||||
import numpy as np
|
||||
|
||||
import mindspore.dataset as ds
|
||||
import mindspore.dataset.transforms.c_transforms as ops
|
||||
|
||||
|
||||
def compare(array, res, idx, cnt):
|
||||
data = ds.NumpySlicesDataset([array], column_names="x")
|
||||
data = data.batch(2)
|
||||
data = data.map(operations=ops.Unique(), input_columns=["x"], output_columns=["x", "y", "z"],
|
||||
column_order=["x", "y", "z"])
|
||||
for d in data.create_dict_iterator(num_epochs=1, output_numpy=True):
|
||||
np.testing.assert_array_equal(res, d["x"])
|
||||
np.testing.assert_array_equal(idx, d["y"])
|
||||
np.testing.assert_array_equal(cnt, d["z"])
|
||||
|
||||
|
||||
def test_duplicate_basics():
|
||||
compare([0, 1, 2, 1, 2, 3], np.array([0, 1, 2, 3]),
|
||||
np.array([0, 1, 2, 1, 2, 3]), np.array([1, 2, 2, 1]))
|
||||
compare([0.0, 1.0, 2.0, 1.0, 2.0, 3.0], np.array([0.0, 1.0, 2.0, 3.0]),
|
||||
np.array([0, 1, 2, 1, 2, 3]), np.array([1, 2, 2, 1]))
|
||||
compare([1, 1, 1, 1, 1, 1], np.array([1]),
|
||||
np.array([0, 0, 0, 0, 0, 0]), np.array([6]))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_duplicate_basics()
|
||||
Loading…
Reference in new issue