Code optimization

In the block above we are appending to train_losses and test_losses. Instead of computing the values again, it might be more efficient to retrieve the most recently added values in the array.

Author: NadimKawwa

intro-to-pytorch/Part 5 - Inference and Validation (Solution).ipynb

@@ -426,8 +426,8 @@
     "        test_losses.append(test_loss/len(testloader))\n",
     "\n",
     "        print(\"Epoch: {}/{}.. \".format(e+1, epochs),\n",
-    "              \"Training Loss: {:.3f}.. \".format(running_loss/len(trainloader)),\n",
-    "              \"Test Loss: {:.3f}.. \".format(test_loss/len(testloader)),\n",
+    "              \"Training Loss: {:.3f}.. \".format(train_losses[-1]),\n",
+    "              \"Test Loss: {:.3f}.. \".format(test_losses[-1]),\n",
     "              \"Test Accuracy: {:.3f}\".format(accuracy/len(testloader)))"
    ]
   },