aboutsummaryrefslogtreecommitdiff
path: root/report/paper.md
diff options
context:
space:
mode:
authorVasil Zlatanov <v@skozl.com>2019-03-07 16:26:28 +0000
committerVasil Zlatanov <v@skozl.com>2019-03-07 16:26:28 +0000
commit66ab6413de42d91b8ea5d425636f5721f61b1426 (patch)
tree996a824f2215f6f14e4e6cd145aff93c91537bd3 /report/paper.md
parent23fa20a9a8e8dc34410c400545ef182b0552e72a (diff)
downloade4-gan-66ab6413de42d91b8ea5d425636f5721f61b1426.tar.gz
e4-gan-66ab6413de42d91b8ea5d425636f5721f61b1426.tar.bz2
e4-gan-66ab6413de42d91b8ea5d425636f5721f61b1426.zip
Add table
Diffstat (limited to 'report/paper.md')
-rw-r--r--report/paper.md19
1 files changed, 19 insertions, 0 deletions
diff --git a/report/paper.md b/report/paper.md
index 0227b1e..e1a78c6 100644
--- a/report/paper.md
+++ b/report/paper.md
@@ -73,6 +73,7 @@ challenge and how they are specifically addressing. Is there the **mode collapse
# Inception Score
+
## Classifier Architecture Used
## Results
@@ -86,6 +87,24 @@ MNIST real testing set (10K), in comparison to the inception scores.
**Please measure and discuss the inception scores for the different hyper-parameters/tricks and/or
architectures in Q2.**
+We measure the performance of the considered GAN's using the Inecption score [@inception], as calculated
+with L2-Net logits.
+
+$$ \textrm{IS}(x) = \exp(\mathcal{E}_x \left( \textrm{KL} ( p(y\|x) \|\| p(y) ) \right) ) $$
+
+GAN type Inception Score (L2-Net)
+------------ -----------------------------
+MNIST(ref) 9.67
+cGAN 6.01
+cGAN+VB 6.2
+cGAN+LS 6.3
+cGAN+VB+LS 6.4
+cDCGAN+VB 6.5
+cDCGAN+LS 6.8
+cDCGAN+VB+LS 7.3
+
+
+
# Re-training the handwritten digit classifier
## Results