Closed iumyx2612 closed 3 years ago
Use --resume=CHECKPOINT_PATH
to resume; you can directly modify this line to 1
.
what exactly is the CHECKPOINT_PATH? I saw 2 new file in my dataset, one .tfrecords file and one .pkl file. And about the training_loop.py script, do I just call it directly with arguments or is it called by another script?
*.tfrecords
is the dataset file; *.pkl
is the checkpoint file. You do not need to call training_loop.py
, just modify it and then run run_low_shot.py
.
*.tfrecords
is the dataset file;*.pkl
is the checkpoint file. You do not need to calltraining_loop.py
, just modify it and then runrun_low_shot.py
.
Thanks, I get it now
I ran the run_low_shot.py with --resume="the/path/to/my/datasets/*.pkl"
other arguments of run_low_shot.py are:
--DiffAugment="" --num-gpus=1 --batch-size=8 --resolution=64 --fmap-base=16384 --datasets="path/to/my/datasets"
ERROR REPORT
Traceback (most recent call last):
File "run_low_shot.py", line 171, in
Oh, *.pkl
should not be in your dataset folder but in the experiment folder (usually inside a folder called results
).
My training
folder does't have any .pkl files, it contains only __pycache__
folder and scripts of yours. Also, I took a look at .stylegan2-cache
folder and I can't find the .pkl for my dataset
Sorry I meant the folder called results
. If there are no *.pkl
in the results
folder, that means your training did not reach the progress of saving a checkpoint.
Great! Thank you so much, really appreciated
I am training my custom dataset with run_low_shot.py on Google Colab. How can I resume my training progress and see the image created every tick. I saw the training_loop.py scripts but I don't know how to implement it