mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 21:14:14 +08:00
0ddaaf6a92
Summary: This directory is opted-in to clang-format but is not format-clean. This blocks continuous formatting from being enabled on fbcode, and causes hassle for other codemods that leave inconsistent formatting. This diff runs clang-format, which is widely used and considered safe. If you are unhappy with the formatting of a particular block, please *accept this diff* and then in a stacked commit undo the change and wrap that code in `// clang-format off` and `// clang-format on`, or `/* clang-format off */` and `/* clang-format on */`. drop-conflicts Test Plan: sandcastleit Reviewed By: jerryzh168 Differential Revision: D22311706 fbshipit-source-id: 1ca59a82e96156a4a5dfad70ba3e64d44c5e762a
48 lines
1.4 KiB
C++
48 lines
1.4 KiB
C++
#ifndef CAFFE2_OPERATORS_CONV_TRANSPOSE_MOBILE_OP_H_
|
|
#define CAFFE2_OPERATORS_CONV_TRANSPOSE_MOBILE_OP_H_
|
|
|
|
#include "caffe2/core/common.h"
|
|
|
|
#ifdef C10_MOBILE
|
|
|
|
#include "caffe2/core/context.h"
|
|
#include "caffe2/core/operator.h"
|
|
#include "caffe2/operators/conv_transpose_unpool_op_base.h"
|
|
|
|
namespace caffe2 {
|
|
|
|
template <typename T, class Context>
|
|
class ConvTransposeMobileOp final : public ConvTransposeUnpoolBase<Context> {
|
|
public:
|
|
USE_CONV_TRANSPOSE_UNPOOL_BASE_FUNCTIONS(Context);
|
|
ConvTransposeMobileOp(const OperatorDef& operator_def, Workspace* ws)
|
|
: ConvTransposeUnpoolBase<Context>(operator_def, ws) {
|
|
OPERATOR_NEEDS_FEATURE(
|
|
order_ == StorageOrder::NCHW,
|
|
"Only NCHW order is supported right now.");
|
|
OPERATOR_NEEDS_FEATURE(
|
|
this->pad_l() == 0, "operator does not handle row width padding");
|
|
OPERATOR_NEEDS_FEATURE(
|
|
this->pad_r() == 0, "operator does not handle row width padding");
|
|
OPERATOR_NEEDS_FEATURE(this->stride_w() <= 4, "stride width must be <= 4");
|
|
}
|
|
|
|
bool RunOnDeviceWithOrderNCHW() override;
|
|
bool RunOnDeviceWithOrderNHWC() override;
|
|
|
|
private:
|
|
// We store a numThreasds per-worker tiles of Y, and numThreads per-worker
|
|
// threadBuffer for the gemm output, laid out in that order.
|
|
Tensor threadBuffer_{CPU};
|
|
|
|
// Input: X, W, b
|
|
// Output: Y
|
|
INPUT_TAGS(INPUT, FILTER, BIAS);
|
|
};
|
|
|
|
} // namespace caffe2
|
|
|
|
#endif // C10_MOBILE
|
|
|
|
#endif // CAFFE2_OPERATORS_CONV_TRANSPOSE_MOBILE_OP_H_
|