Blizzard Model

[PetrochukM]

Can't use the Blizzard model without the original training data:

Traceback (most recent call last):
  File "generate.py", line 156, in <module>
    main()
  File "generate.py", line 83, in main
    train_dataset = NpzFolder(train_args.data + '/numpy_features')
  File "/home/michael/Desktop/loop/data.py", line 84, in __init__
    self.NPZ_EXTENSION))
RuntimeError: Found 0 npz in subfolders of: data/blizzard/numpy_features
Supported image extensions are: npz

Looks generate.py uses parameters in the training data to generate.py

[adampolyak]

Fixed in 84234d3.

[PetrochukM]

Hi!

Thanks for your quick work. The code is still dependent:

Line 83, generate.py:
train_dataset = NpzFolder(train_args.data + '/numpy_features')

Line 156, utils.py:
fid = open(norm_info_file, 'rb')

[adampolyak]

Right, it was still dependent on the norm file.

Check it out now, you'll need to download blizzard model again to obtain the norm file.

[PetrochukM]

Okay! I'll need to download the blizzard model and extract features to obtain the norm file, right?

[adampolyak]

I've added the norm information to the model zip. So just download the model as in the documentation. The generation script will find it.

…

On Thu, Mar 22, 2018, 17:25 Michael Petrochuk ***@***.***> wrote: Okay! I'll need to download the blizzard model and extract features to obtain the norm file, right? — You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub <#44 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AHXBtV0bCMjPTogz-a1vrxibohstE4Q2ks5tg8J8gaJpZM4S2ghf> .

[PetrochukM]

Perfect! Thanks worked well!!