Lex

[Feature request] Add documentation on the functional differences between the available pretrained models

1

As it stands there 6 pre-trained models availible for fine tuning: - MobileNetV2 - InceptionV3 - VGG16 - VGG19 - NASNetMobile - SimpleCnnModel It is not however from that which...

Per image tokens with a larger dataset.

7

I'm curious about trying per-image token training with my dataset however the per_img_token_list in personalized.py is only 22 entries long, which appears to be posing an issue in that there...

CAPTCHA prompt seems to prevent any content from downloading

9

When attempting to run this script no content is downloaded, when looking at the script output in the console the body section appears to contain the markup for a CAPTCHA...

[Suggestion] Add documentation on how to run 3D reconstruction on user data.

3

Currently the readme provides an example of how one might do 3D reconstruction with an existing image and transforms_train.json pair but provides no details on how we'd start doing reconstructions...