ProGamerGov

@vikhyat that was the output from `model.encode_image`, but I see that functionality is built into `batch_answer` now. Everything is working now, thanks for the help!

@T8star1984 Try making a new conda instance and install the requirements.txt from this repo. That's how I solved this issue

@ad48hp The base models were trained with millions of images, so I'm not sure how well training from scratch would work. All you would have to do is set the...

@ad48hp Apologies for the late reply, but zeroing models is actually a bit of a bad idea. You general want a range of numbers to initialize a brand new model...

Also, if you aren't using a GPU then its going to be painfully slow.

@ad48hp Not sure if there's an issue, but that's often what it looks like at first when training from scratch. How many images are you using and how many steps...

@Testin1234 That's because on Windows 10, Python 3 is run with `python` and not `python3`. I never tested the script on Windows, but I believe you can resolve the issue...

Try creating a folder called `output_dir`, as the code expects that folder to exist (and tries to create it).

@Testin1234 What are the neural-zoom specific parameters that you are using?

@Testin1234 Sorry, for the late response, so far I've found the slash direction to be a potential error source, but the error message still remains. Your parameters are not the...