Hands-On Transfer Learning with Python

Training on the full IMDB dataset with Word2vec embeddings

Now, let's try to train the document CNN model on the full IMDB dataset by transferring the learned Word2vec embeddings.

Note, we are not using the learned weights from the Amazon Review model. We will be training the model from scratch. In fact, this is what was done in the paper.

This code for this is very similar to the preceding IMDB training code. You just need to exclude the weight loading part from the Amazon model. The code is available in the repository, in the module named imdb_model.py. Also, here are the model parameters:

{      "embedding_dim":50,    "train_embedding":true,    "embedding_regularizer_l2":0.0,    "sentence_len":30,    "num_sentences":20,    "word_kernel_size":5,