Build vocabulary of VOCAB_SIZE most frequent words

Download the dataset text8 if it's not already downloaded

Read data into a list of tokens There should be 17,005,207 tokens

Step 2: define weights. In word2vec, it's actually the weights that we care about

Step 3 + 4: define the model + the loss function

Step 5: define optimizer

Step 1: define the placeholders for input and output

filenames is the list of files you want to read from. In this case, it contains only heart.csv

Build the graph for our model

Replace each word in the dataset with its index in the dictionary

Form training pairs according to the skip-gram model.

Group a numerical stream into batches and yield them as Numpy arrays.

You can read in the image using tensorflow too, but it's a drag since you have to create graphs. It's much easier using Pillow and NumPy

Build the graph for word2vec model and train it

Build the graph for word2vec model and train it

This example is to write a sample to TFRecord file. If you want to write more samples, just use a loop.

Create a directory if there isn't one already.