New sample op #42
Open
New sample op #42
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
zheng-da
reviewed
Nov 20, 2018
| heap[i] += w; | ||
| i = i >> 1; | ||
| } | ||
| } |
There was a problem hiding this comment.
This method is probably not necessary.
zheng-da
reviewed
Nov 20, 2018
|
|
||
| // Sample a vector by given the size n | ||
| void SampleWithoutReplacement(size_t n, | ||
| std::vector<size_t>& samples) { |
| } | ||
| size_t i = 0; | ||
| for (auto it = sampled_idxs.begin(); it != sampled_idxs.end(); it++, i++) | ||
| sorted_idxs[i] = *it; |
There was a problem hiding this comment.
this isn't sampling with shuffle.
| @@ -163,96 +493,266 @@ static void GetSample(std::vector<dgl_id_t>& ver_list, | |||
| } | |||
| mp[rand_num] = true; | |||
| out.push_back(ver_list[rand_num]); | |||
| out_edge.push_back(edge_list[rand_num]); | |||
| sample_count++; | |||
| if (sample_count == max_num_neighbor) { | |||
| break; | |||
| } | |||
| } | |||
| } | |||
There was a problem hiding this comment.
it doesn't seem we need this function.
|
|
||
| // sample from arrayHeap | ||
| size_t Sample() { | ||
| float xi = heap[1] * (rand()%100/(float)101); |
There was a problem hiding this comment.
so heap[1] is the root of the tree?
| sp_prob[i] = probability[ver_list[i]]; | ||
| } | ||
| ArrayHeap arrayHeap(sp_prob); | ||
| arrayHeap.SampleWithoutReplacement(max_num_neighbor, sp_index); |
| tmp_edge_list, | ||
| num_neighbor, | ||
| tmp_sampled_src_list, | ||
| tmp_sampled_edge_list); |
There was a problem hiding this comment.
you didn't use GetUniformSampleShuffle.
| num_edges += tmp_sampled_src_list.size(); | ||
|
|
||
| // TODO The code doesn't limit the maximal number of vertices correctly. | ||
| sub_vertices_count++; |
There was a problem hiding this comment.
sub_ver_mp contains the sampled vertices. Do we need count the number of sampled vertices?
it's a bit tricky when limiting the number of sampled vertices. actually, we need to make sure sub_ver_mp.size() <= max_num_vertices.
| // set seed for random sampling | ||
| srand(time(nullptr)); | ||
|
|
||
| //#pragma omp parallel for |
| srand(time(nullptr)); | ||
| const float* probability = inputs[1].data().dptr<float>(); | ||
|
|
||
| //#pragma omp parallel for |
| const int dev_mask, | ||
| DispatchMode* dispatch_mode, | ||
| std::vector<int> *in_attrs, | ||
| std::vector<int> *out_attrs) { |
There was a problem hiding this comment.
can we merge these functions for uniform and non-uniform?
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.
No description provided.