mindwrapped commited on
Commit
15f3e3c
1 Parent(s): 7ad9f11

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +51 -0
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: keras
3
+ tags:
4
+ - collaborative-filtering
5
+ - recommender
6
+ - structured-data-classification
7
+ license:
8
+ - cc0-1.0
9
+ ---
10
+
11
+ ## Model description
12
+
13
+ This repo contains the model and the notebook on [how to build and train a Keras model for Collaborative Filtering for Movie Recommendations](https://keras.io/examples/structured_data/collaborative_filtering_movielens/).
14
+
15
+ Full credits to [Siddhartha Banerjee](https://twitter.com/sidd2006).
16
+
17
+ ## Intended uses & limitations
18
+
19
+ Based on a user and movies they have rated highly in the past, this model outputs the predicted rating a user would give to a movie they haven't seen yet (between 0-1). This information can be used to find out the top recommended movies for this user.
20
+
21
+ ## Training and evaluation data
22
+
23
+ The dataset consists of user's ratings on specific movies. It also consists of the movie's specific genres.
24
+
25
+ ## Training procedure
26
+
27
+ The model was trained for 5 epochs with a batch size of 64.
28
+
29
+ ### Training hyperparameters
30
+
31
+ The following hyperparameters were used during training:
32
+ - optimizer: {'name': 'Adam', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
33
+ - training_precision: float32
34
+
35
+ ## Training Metrics
36
+
37
+ | Epochs | Train Loss | Validation Loss |
38
+ |--- |--- |--- |
39
+ | 1| 0.637| 0.619|
40
+ | 2| 0.614| 0.616|
41
+ | 3| 0.609| 0.611|
42
+ | 4| 0.608| 0.61|
43
+ | 5| 0.608| 0.609|
44
+ ## Model Plot
45
+
46
+ <details>
47
+ <summary>View Model Plot</summary>
48
+
49
+ ![Model Image](./model.png)
50
+
51
+ </details>