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

Add mnist_deep to the test suite

Browse Source 
3-layer Deep stack (28x28->256->256->16), has saved weights for all
three layers. Passes: reconstruction error 0.039 vs. mean-baseline 0.067.
7/9 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 14:54:54 +02:00
co-authored by Claude Sonnet 5
parent 7b842ea50c
commit 86764bb261
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"};
std::vector<std::string> projects = {"1-hot", "prims", "norb_small_16h_v2", "norb_small_16h", "mnist_2", "prims_deep", "count", "many", "mnist_deep"};
int numPassed = 0;
for (const std::string &name : projects)