| datasets: | |
| - prabinpanta0/celsius-to-fahrenheit | |
| language: en | |
| library_name: tf-keras | |
| license: mit | |
| metrics: mean_squared_error | |
| pipeline_tag: tabular-regression | |
| tags: | |
| - temperature-conversion | |
| - celsius-to-fahrenheit | |
| - tensorflow | |
| - neural-network | |
| # My Temperature Conversion Model | |
| This model is a simple neural network that converts temperatures from Celsius to Fahrenheit. | |
| ## Model Description | |
| 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. | |
| ## Usage | |
| To use this model, you can load it with TensorFlow and make predictions as shown below: | |
| ```python | |
| import tensorflow as tf | |
| model = tf.keras.models.load_model('celsius-to-fahrenheit') | |
| prediction = model.predict([100.0]) | |
| print(f"Prediction for 100°C in Fahrenheit: {prediction[0][0]}") | |
| ``` | |
| ## Training | |
| The model was trained using the following parameters: | |
| - Optimizer: Adam | |
| - Loss function: Mean Squared Error | |
| - Epochs: 1000 | |
| - Batch size: 10 | |
| ## Metrics | |
| The model was evaluated based on the Mean Squared Error loss during training. | |
|  | |
| ## Model Output | |
|  | |
| ## Datasets | |
| The model was trained on the [prabinpanta0/celsius-to-fahrenheit](https://huggingface.co/datasets/prabinpanta0/celsius-to-fahrenheit) dataset. | |
| ## License | |
| This model is released under the MIT license. |