adding training visualizations

kvmanohar22 · Feb 4, 2018 · ebc0adf · ebc0adf
1 parent 9556afd
commit ebc0adf
Show file tree

Hide file tree

Showing 5 changed files with 11 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -61,6 +61,7 @@ Implementation of the paper : **Toward Multimodal Image-to-Image Translation**
     - [Generate Graph](#graph)
     - [Training the network](#train)
     - [Testing the network](#test)
+  - [Visualizations](#viz)
   - [TODO](#todo)
   - [Licence](#licence)
 
@@ -189,6 +190,16 @@ $ sudo pip install -r requirements.txt
   $ ./test.sh <dataset_name> <test_image_path> <checkpoint_path>
   ```
 
+<a name='viz'></a>
+# Visualizations
+Loss of discriminator and generator as function of iterations on `edges2shoes` dataset.
+
+![](imgs/loss/d_fake.png)
+![](imgs/loss/d_real.png)
+![](imgs/loss/d_loss.png)
+![](imgs/loss/g_loss.png)
+
+
 <a name='todo'></a>
 # TODO
 - [x] Residual Encoder

diff --git a/imgs/loss/d_fake.png b/imgs/loss/d_fake.png
diff --git a/imgs/loss/d_loss.png b/imgs/loss/d_loss.png
diff --git a/imgs/loss/d_real.png b/imgs/loss/d_real.png
diff --git a/imgs/loss/g_loss.png b/imgs/loss/g_loss.png