blob: 088d6a0e5f0dfe946ce585b0ece51e6511558fb5 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
|
/* Copyright 2015 Google Inc. 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 <string>
#include "tensorflow/core/framework/op_kernel.h"
#include "tensorflow/core/lib/core/errors.h"
#include "tensorflow/core/lib/hash/hash.h"
#include "tensorflow/core/public/status.h"
#include "tensorflow/core/public/tensor.h"
namespace tensorflow {
class StringToHashBucketOp : public OpKernel {
public:
explicit StringToHashBucketOp(OpKernelConstruction* ctx) : OpKernel(ctx) {
OP_REQUIRES_OK(ctx, ctx->GetAttr("num_buckets", &num_buckets_));
}
void Compute(OpKernelContext* context) override {
const Tensor* input_tensor;
OP_REQUIRES_OK(context, context->input("string_tensor", &input_tensor));
const auto& input_flat = input_tensor->flat<string>();
Tensor* output_tensor = nullptr;
OP_REQUIRES_OK(context,
context->allocate_output("output", input_tensor->shape(),
&output_tensor));
auto output_flat = output_tensor->flat<int64>();
for (size_t i = 0; i < input_flat.size(); ++i) {
const uint64 input_hash = Hash64(input_flat(i));
const uint64 bucket_id = input_hash % num_buckets_;
// The number of buckets is always in the positive range of int64 so is
// the resulting bucket_id. Casting the bucket_id from uint64 to int64 is
// safe.
output_flat(i) = static_cast<int64>(bucket_id);
}
}
private:
int64 num_buckets_;
TF_DISALLOW_COPY_AND_ASSIGN(StringToHashBucketOp);
};
REGISTER_KERNEL_BUILDER(Name("StringToHashBucket").Device(DEVICE_CPU),
StringToHashBucketOp);
} // namespace tensorflow
|
