feat: add sequential MNIST, Penn Treebank, and TIMIT benchmarks - #54
Open
MartinuzziFrancesco wants to merge 3 commits into
Open
feat: add sequential MNIST, Penn Treebank, and TIMIT benchmarks#54MartinuzziFrancesco wants to merge 3 commits into
MartinuzziFrancesco wants to merge 3 commits into
Conversation
Rework adding_problem and copy_memory to match their canonical paper definitions (two-half marker sampling, T+20 protocol) and add reproducibility/validation options shared across all benchmark generators. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01V4c1s7psjFQPEbfbLDXrDA
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## main #54 +/- ##
==========================================
- Coverage 95.24% 95.10% -0.15%
==========================================
Files 34 42 +8
Lines 2187 2573 +386
==========================================
+ Hits 2083 2447 +364
- Misses 104 126 +22 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
Same pattern as sequential_mnist: caller supplies CIFAR-10 tensors, adapter flattens to a 1024-step, 3-channel pixel sequence with optional fixed permutation. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
adding_problem/copy_memory: DataLoader shuffling always runs its sampler on CPU, so a non-CPU generator used for data generation can no longer be forwarded to the loader (it now falls back to its own seeding instead of erroring). sequential_mnist/sequential_cifar10: correct docstring overclaims about paper-exact pixel scan direction and a bogus IndRNN citation. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Rework adding_problem and copy_memory to match their canonical paper definitions (two-half marker sampling, T+20 protocol) and add reproducibility/validation options shared across all benchmark generators.