Update README.md
Browse files
README.md
CHANGED
@@ -6,7 +6,13 @@ tags:
|
|
6 |
|
7 |
## Model description
|
8 |
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
## Intended uses & limitations
|
12 |
|
@@ -14,15 +20,18 @@ More information needed
|
|
14 |
|
15 |
## Training and evaluation data
|
16 |
|
17 |
-
|
18 |
|
19 |
## Training procedure
|
20 |
|
21 |
### Training hyperparameters
|
22 |
|
23 |
The following hyperparameters were used during training:
|
24 |
-
-
|
|
|
|
|
25 |
- training_precision: float32
|
|
|
26 |
|
27 |
## Training Metrics
|
28 |
|
|
|
6 |
|
7 |
## Model description
|
8 |
|
9 |
+
This repo contains the model which showcases the learning capabilities of LSTM using a simple example. A single-layer LSTM is made to learn to add two numbers, provided as strings. The model has been trained for adding two numbers where each number can have maximum of 5 digits.
|
10 |
+
|
11 |
+
*Example:*
|
12 |
+
Input: "535+61"
|
13 |
+
Output: "596"
|
14 |
+
|
15 |
+
Full credits to [Smerity](https://twitter.com/Smerity) and others for this work.
|
16 |
|
17 |
## Intended uses & limitations
|
18 |
|
|
|
20 |
|
21 |
## Training and evaluation data
|
22 |
|
23 |
+
The data consists of generation of two random 5 digit numbers as input and their sum as output. These numbers (_and their sum)_ are encoded and fed as input to LSTM. The full data creation code is available within the [example](https://keras.io/examples/nlp/addition_rnn/).
|
24 |
|
25 |
## Training procedure
|
26 |
|
27 |
### Training hyperparameters
|
28 |
|
29 |
The following hyperparameters were used during training:
|
30 |
+
- learning_rate: 0.001
|
31 |
+
- train_batch_size: 32
|
32 |
+
- optimizer: {'name': 'Adam', 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
33 |
- training_precision: float32
|
34 |
+
- num_epochs: 30
|
35 |
|
36 |
## Training Metrics
|
37 |
|