mirror of
https://github.com/jung-geun/PSO.git
synced 2026-09-20 14:11:48 +09:00
Migrate the package and examples to the tensor-native PyTorch implementation, add benchmark evidence, and add the guarded post-training convergence protocol with TensorBoard progress monitoring and hash-verified recovery. Constraint: Preserve one-shot official-test sealing and auditable research artifacts Rejected: Commit local .omc runs and downloaded datasets | multi-gigabyte runtime state is machine-local Confidence: high Scope-risk: broad Not-tested: Production CUDA run on pieroot-server
322 B
322 B
| 1 | section | metric | value |
|---|---|---|---|
| 2 | protocol | version | MNIST-PSO-RAW-V5 1.0.0 |
| 3 | pilot | selected_dimension | full |
| 4 | single_model | test_accuracy | 83.23 |
| 5 | single_model | test_nll | 0.556332 |
| 6 | single_model | test_brier | 0.253921 |
| 7 | single_model | test_ece | 0.085242 |
| 8 | ensemble | test_accuracy | 87.0 |
| 9 | ensemble | test_nll | 0.535928 |
| 10 | ensemble | pairwise_disagreement | 0.1585 |