add spp（Spatial pyramid pooling ） op #6204
Merged
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
added 6 commits
December 3, 2017 14:40
NHZlX
reviewed
Dec 12, 2017
paddle/operators/spp_op.cc
Outdated
| "M = C * H * W"); | ||
| AddAttr<int>("pyramid_height", "(int), multi level pooling"); | ||
| AddComment(R"DOC( | ||
| "Does spatial pyramid pooling on the input image by taking the max, |
There was a problem hiding this comment.
The document is too simple to be easy to understand for the novice.
NHZlX
reviewed
Dec 12, 2017
paddle/operators/spp_op.h
Outdated
| std::vector<int64_t> output_shape_vec({in_x->dims()[0], in_x->dims()[1]}); | ||
| output_shape_vec.push_back( | ||
| (input_h - kernel_size_h + 2 * padding_h) / kernel_size_h + 1); | ||
| output_shape_vec.push_back( |
There was a problem hiding this comment.
Is (input_h - kernel_size_h + 2 * padding_h) / kernel_size_h + 1) equals to bins? Why do we have to recaulate.
NHZlX
reviewed
Dec 12, 2017
paddle/operators/spp_op.h
Outdated
| framework::DDim output_flatten_shape( | ||
| framework::make_ddim(output_flatten_shape_vec)); | ||
| out_flatten_level.ShareDataWith(out_level); | ||
| out_flatten_level.Resize(output_flatten_shape); |
There was a problem hiding this comment.
why not use out_level to resize, but reapply a new variable out_flatten_level?
NHZlX
reviewed
Dec 12, 2017
paddle/operators/spp_op.h
Outdated
| framework::Tensor out_level; | ||
| framework::Tensor outgrad_level; | ||
| std::vector<int64_t> out_shape_vec({in_x->dims()[0], in_x->dims()[1]}); | ||
| out_shape_vec.push_back( |
sweetsky0901
commented
Dec 13, 2017
paddle/operators/spp_op.cc
Outdated
| "M = C * H * W"); | ||
| AddAttr<int>("pyramid_height", "(int), multi level pooling"); | ||
| AddComment(R"DOC( | ||
| "Does spatial pyramid pooling on the input image by taking the max, |
paddle/operators/spp_op.h
Outdated
| std::vector<int64_t> output_shape_vec({in_x->dims()[0], in_x->dims()[1]}); | ||
| output_shape_vec.push_back( | ||
| (input_h - kernel_size_h + 2 * padding_h) / kernel_size_h + 1); | ||
| output_shape_vec.push_back( |
paddle/operators/spp_op.h
Outdated
| framework::DDim output_flatten_shape( | ||
| framework::make_ddim(output_flatten_shape_vec)); | ||
| out_flatten_level.ShareDataWith(out_level); | ||
| out_flatten_level.Resize(output_flatten_shape); |
paddle/operators/spp_op.h
Outdated
| framework::Tensor out_level; | ||
| framework::Tensor outgrad_level; | ||
| std::vector<int64_t> out_shape_vec({in_x->dims()[0], in_x->dims()[1]}); | ||
| out_shape_vec.push_back( |
Closed
|
|
added 2 commits
December 17, 2017 22:09
NHZlX
approved these changes
Dec 18, 2017
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.
fix #5988