Add deconv cpu impl #5224
Merged
Add deconv cpu impl #5224
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Ldpe2G
reviewed
Jun 17, 2021
| namespace { | ||
|
|
||
| template<typename T> | ||
| using Im2ColFunc = void (*)(const T* in_dptr, const ShapeView& in_shape, |
Ldpe2G
reviewed
Jun 17, 2021
| const int32_t* padding_before, T* in_diff_ptr); | ||
|
|
||
| template<typename T> | ||
| using GemmFunc = void (*)(enum CBLAS_TRANSPOSE trans_a, enum CBLAS_TRANSPOSE trans_b, const int m, |
Ldpe2G
reviewed
Jun 17, 2021
| template<typename T> | ||
| struct ConvKernelUtil final { | ||
| public: | ||
| static void NCDHWIm2Col(const T* in_dptr, const ShapeView& in_shape, |
Ldpe2G
reviewed
Jun 17, 2021
| struct ConvOpKernelState final : public user_op::OpKernelState { | ||
| Im2ColFunc<T> im2col_func_; | ||
| Col2ImFunc<T> col2im_func_; | ||
| GemmFunc<T> forward_func_; |
Ldpe2G
reviewed
Jun 17, 2021
| int32_t idx_offset = conv_state->idx_offset_; | ||
|
|
||
| FOR_RANGE(int64_t, i, 0, in->shape().At(0)) { | ||
| // channels first: col_buf' = weight(T) * out[i]' |
Ldpe2G
reviewed
Jun 17, 2021
| conv_state->weight_5d_shape_.At(0), static_cast<T>(1), weight->dptr<T>(), | ||
| GetImgDptr<T>(in, i), static_cast<T>(0), col_buf->mut_dptr<T>()); | ||
|
|
||
| // in' = col2im(col_buf') |
Ldpe2G
approved these changes
Jun 17, 2021
Ldpe2G
requested review from
oneflow-ci-bot
and removed request for
oneflow-ci-bot
oneflow-ci-bot
requested review from
oneflow-ci-bot
and removed request for
oneflow-ci-bot
oneflow-ci-bot
requested review from
oneflow-ci-bot
and removed request for
oneflow-ci-bot
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
添加反卷积的cpu实现。