mirror of
https://github.com/jung-geun/PSO.git
synced 2026-09-20 14:11:48 +09:00
jung-geun
813433000a
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
11 lines
322 B
CSV
11 lines
322 B
CSV
section,metric,value
|
|
protocol,version,MNIST-PSO-RAW-V5 1.0.0
|
|
pilot,selected_dimension,full
|
|
single_model,test_accuracy,83.23
|
|
single_model,test_nll,0.556332
|
|
single_model,test_brier,0.253921
|
|
single_model,test_ece,0.085242
|
|
ensemble,test_accuracy,87.0
|
|
ensemble,test_nll,0.535928
|
|
ensemble,pairwise_disagreement,0.1585
|