Thanks for the great tutorial. I’m using your approach for my own dataset to predict the watch-rate of a video using its tag names and taxonomy types. However, when I run the training line (an equivalent of line 18 in your keras-wide-deep.ipynb on GitHub) below:
combined_model.fit([tag_name_train, taxonomy_type_train] + [train_embed], labels_train, epochs=10, batch_size=128)
I got this error:
ValueError: Error when checking input: expected input_1 to have shape (12000,) but got array with shape (1,)
Can you let me know what I might have done wrong? Thanks a ton!