Update dlnd_face_generation.ipynb

I've experienced CUDA memory leakage during training, the CUDA memory was increasing at the end of each epoch. This change has solved the issue for me.

Author: jxtrbtk

project-face-generation/dlnd_face_generation.ipynb

@@ -633,8 +633,10 @@
     "        # this code assumes your generator is named G, feel free to change the name\n",
     "        # generate and save sample, fake images\n",
     "        G.eval() # for generating samples\n",
-    "        samples_z = G(fixed_z)\n",
-    "        samples.append(samples_z)\n",
+    "        with torch.no_grad():\n",
+    "            samples_z = G(fixed_z)\n",
+    "            samples_z = samples_z.detach().cpu()\n",
+    "            samples.append(samples_z)\n",
     "        G.train() # back to training mode\n",
     "\n",
     "    # Save training generator samples\n",