jens/Rbm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add mnist_h32 to the test suite

Browse Source 
Single-layer Deep stack (28x28->32), weights load fine but genuinely
fail the reconstruction check: error 0.231 vs. mean-baseline 0.067,
worse than the 1.5x tolerance. Unlike norb_small_16h_v2/many (which fail
because no current-format weights exist at all), this one has weights
that load successfully but just don't reconstruct well -- training
params look ordinary (RaoBlackwell, 1000 epochs) and the training data
looks like normal-scale MNIST pixels, so this looks like a genuinely
under-trained or abandoned saved snapshot rather than a test bug.
7/11 pass.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016K8Gu7Qejd11JbdiHZqYAs
This commit is contained in:
jens
2026-07-27 14:58:04 +02:00
co-authored by Claude Sonnet 5
parent 86764bb261
commit db7eb72174
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
source/main.cpp
+1 -1
View File
@@ -90,7 +90,7 @@ TestResult testProject(const std::string &name)
int main()
{
std::vector<std::string> projects = {"1-hot", "prims", "norb_small_16h_v2", "norb_small_16h", "mnist_2", "prims_deep", "count", "many", "mnist_deep"};
std::vector<std::string> projects = {"1-hot", "prims", "norb_small_16h_v2", "norb_small_16h", "mnist_2", "prims_deep", "count", "many", "mnist_deep", "mnist_h32"};
int numPassed = 0;
for (const std::string &name : projects)