# <center><i class="fa fa-edit"></i> Deep Learning with Keras </center>
###### tags: `Internship`
:::info
**Goal:**
- [x] Tools
- [x] Steps

**Resources:**

- [Python TensorFlow Tutorial](https://adventuresinmachinelearning.com/python-tensorflow-tutorial/)
- [LSTM Implementation in Python/Numpy](https://gist.github.com/tmatha/f1c7082acdc9af21aade33b98687f2c6)
- [LSTM Implementation in TensorFlow eager execution](https://gist.github.com/tmatha/905ae0c0d304119851d7432e5b359330)
:::

## How to build a deep learning with Keras?
### Tools
1. Anaconda
2. Jupyter Notebook
3. Keras
4. Data preprocessing tools, such as pandas, numpy, etc. For this you can install the package by installing them into your conda environment

### Step
1. Import your needed package, for example:
2. Do data preprocessing. In this step, it depends on what kind of data and mehod you want to use.
3. Split your dataset into training and testing dataset, in LSTM, you have to reshape the input to 3D array
4. Define your LSTM model
- Model Spec:
- Model name: LSTM
- Number of LSTM: 50 unit
- Output node: 1
- Loss metric : Mean Average Error
- Optimizer function: Adam
- Epoch: 50
- Batch size: 72