Project Criteria
- The dataset to be used is free, but has a minimum of 1000 samples.
- Must use LSTM in model architecture.
- Must use sequential model.
- Validation set is 20% of the total dataset.
- Must use Embedding.
- Must use tokenizer function.
- The accuracy of the model is at least 75% on the train set and validation set.
I'm using a dataset from Kaggle and put it into my Google Drive to make it easier to process.
TensorFlow
Matplotlib