Add output example.

README.md

@@ -2,6 +2,7 @@
 
 This repository contains my implementation of [**Deep Knowledge Tracing**](https://github.com/chrispiech/DeepKnowledgeTracing) for the Udacity's Capstone Project.
 
+
 ## Overview
 
 The objective is to predict the probabilities of a student correctly answering a problem not yet seen by him. To this end, we train the model using the [**ASSISTments Skill-builder data 2009-2010**](https://sites.google.com/site/assistmentsdata/home/assistment-2009-2010-data/skill-builder-data-2009-2010) public dataset.
@@ -56,6 +57,8 @@ Tensorflow 2.0 is installed along with the project. Check the instructions below
     tensorboard --logdir=logs
     ```
 
+    ![alt text](docs/output_example.png "Output example")
+
 ## Custom Metrics
 
 To implement custom metrics, first decode the label and then calculate the metric. This step is necessary because we encode the skill id with the label to implement the custom loss.

examples/run_dkt.py

@@ -21,7 +21,7 @@ def run(args):
                             hidden_units=args.hidden_units,
                             dropout_rate=args.dropout_rate)
     model.compile(
-        optimizer='adagrad',
+        optimizer='adam',
         metrics=[
             metrics.BinaryAccuracy(),
             metrics.AUC(),
@@ -90,12 +90,12 @@ def parse_args():
     train_group = parser.add_argument_group(title="Training arguments.")
     train_group.add_argument("--batch_size",
                              type=int,
-                             default=16,
+                             default=32,
                              help="number of elements to combine in a single batch.")
 
     train_group.add_argument("--epochs",
                              type=int,
-                             default=10,
+                             default=50,
                              help="number of epochs to train.")
 
     train_group.add_argument("--test_split",