prabinpanta0
commited on
Commit
•
bcdc72a
1
Parent(s):
6b96cd5
Update README.md
Browse files
README.md
CHANGED
@@ -9,3 +9,35 @@ tags:
|
|
9 |
- tensorflow
|
10 |
- neural-network
|
11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
- tensorflow
|
10 |
- neural-network
|
11 |
---
|
12 |
+
# My Temperature Conversion Model
|
13 |
+
|
14 |
+
This model is a simple neural network that converts temperatures from Celsius to Fahrenheit.
|
15 |
+
|
16 |
+
## Model Description
|
17 |
+
|
18 |
+
This model was created as a practice exercise for the course "Intro to TensorFlow for Deep Learning" from Udacity, given by TensorFlow. It was trained on a dataset of temperature values in Celsius and their corresponding values in Fahrenheit. The model uses a small neural network built with TensorFlow.
|
19 |
+
|
20 |
+
## Usage
|
21 |
+
|
22 |
+
To use this model, you can load it with TensorFlow and make predictions as shown below:
|
23 |
+
|
24 |
+
```python
|
25 |
+
import tensorflow as tf
|
26 |
+
|
27 |
+
model = tf.keras.models.load_model('my_tf_model')
|
28 |
+
prediction = model.predict([100.0])
|
29 |
+
print(f"Prediction for 100°C in Fahrenheit: {prediction[0][0]}")
|
30 |
+
```
|
31 |
+
## Training
|
32 |
+
The model was trained using the following parameters:
|
33 |
+
|
34 |
+
```yml
|
35 |
+
Optimizer: Adam
|
36 |
+
Loss function: Mean Squared Error
|
37 |
+
Epochs: 1000
|
38 |
+
Batch size: 10
|
39 |
+
Metrics
|
40 |
+
The model was evaluated based on the Mean Squared Error loss during training.
|
41 |
+
```
|
42 |
+
## License
|
43 |
+
This model is released under the MIT license.
|