Closed Hassan022020 closed 2 years ago
While, I met the same problem as U.
I have trained the model as per instructions but now I am stuck... how do I generate images using text only as there are no clear instructions for this in readme
Do you know what text encoder has been used for the datasets taken? Is it bi-directional LSTM ?
Text Encoder is LSTM on trained model. But you can switch it on GRU during training. It is in config.py line 20.
So, how to test the model using my own caption?
I have trained the model as per instructions but now I am stuck... how do I generate images using text only as there are no clear instructions for this in readme