Python Deep Learning Projects

Defining a basic RNN cell model

Now we will create the RNN model, which takes a few input parameters, including the following:

• size_layer: The number of units in the RNN cell
• num_layers: The number of hidden layers
• embedded_size: The size of the embedding
• dict_size: The vocabulary size
• dimension_output: The number of classes we need to classify
• learning_rate: The learning rate of the optimization algorithm

The architecture of our RNN model consists of the following parts:

1. Two placeholders; one to feed sequence data into the model and the second for the output
2. A variable to store the embedding lookup from the dictionary
3. Then, add the RNN layer with multiple basic RNN cells
4. Create weight and bias variables
5. Compute logits 
6. Compute loss