Closed Particle1904 closed 4 months ago
After 3 days of first fighting google colab, python and conda I finally figured out how to run the training in Google Colab. If anyone is interested, I'll share the colab notebook.
If the same error appears, it is recommended to check the size set in step prepare_data. If you made it 512 size, for example, you should write down the --size 512 flag when running finetune_stylegan.py.
Running the command:
!torchrun --nproc_per_node=1 --master_port=8765 /content/DualStyleGAN/finetune_stylegan.py --iter 600 --batch 4 --ckpt /content/DualStyleGAN/checkpoint/stylegan2-ffhq-config-f.pt --style mydataset /content/DualStyleGAN/data/mydataset/lmdb/