'vqgan_jax_strongaug.ckpt'，Can you provide a model of VQgan for pre training.

[Liuhp133]

Not using distributed mode
[12:38:29.539022] job dir: /home/omnisky/hdd_15T_sdd/ljx/mage
[12:38:29.539092] Namespace(accum_iter=1,
batch_size=64,
blr=0.00015,
data_path='/home/omnisky/sda/zmc/dataset/train',
device='cuda:0',
dist_on_itp=False,
dist_url='env://',
distributed=False,
epochs=100,
grad_clip=3.0,
input_size=256,
local_rank=-1,
log_dir='./output_dir',
lr=None,
mask_ratio_max=1.0,
mask_ratio_min=0.5,
mask_ratio_mu=0.55,
mask_ratio_std=0.25,
min_lr=0.0,
model='mage_vit_base_patch16',
num_workers=10,
output_dir='./output_dir',
pin_mem=True,
resume='',
seed=0,
start_epoch=0,
warmup_epochs=10,
weight_decay=0.05,
world_size=1)
[12:38:30.443237] Dataset ImageFolder
Number of datapoints: 220000
Root location: /home/omnisky/sda/zmc/dataset/train/train
StandardTransform
Transform: Compose(
RandomResizedCrop(size=(256, 256), scale=(0.2, 1.0), ratio=(0.75, 1.3333), interpolation=PIL.Image.BILINEAR)
RandomHorizontalFlip(p=0.5)
ToTensor()
)
[12:38:30.443520] Sampler_train = <torch.utils.data.distributed.DistributedSampler object at 0x7f7e6f7b7fd0>
[12:38:30.629825] Working with z of shape (1, 256, 16, 16) = 65536 dimensions.
Traceback (most recent call last):
File "/home/omnisky/hdd_15T_sdd/ljx/mage/main_pretrain.py", line 223, in
main(args)
File "/home/omnisky/hdd_15T_sdd/ljx/mage/main_pretrain.py", line 152, in main
model = models_mage.dict[args.model](mask_ratio_mu=args.mask_ratio_mu, mask_ratio_std=args.mask_ratio_std,
File "/home/omnisky/hdd_15T_sdd/ljx/mage/models_mage.py", line 363, in mage_vit_base_patch16
model = MaskedGenerativeEncoderViT(
File "/home/omnisky/hdd_15T_sdd/ljx/mage/models_mage.py", line 160, in init
self.vqgan = VQModel(ddconfig=config.params.ddconfig,
File "/home/omnisky/hdd_15T_sdd/ljx/mage/taming/models/vqgan.py", line 28, in init
self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys)
File "/home/omnisky/hdd_15T_sdd/ljx/mage/taming/models/vqgan.py", line 37, in init_from_ckpt
sd = torch.load(path, map_location="cpu")
File "/home/omnisky/anaconda3/envs/mage/lib/python3.8/site-packages/torch/serialization.py", line 581, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/omnisky/anaconda3/envs/mage/lib/python3.8/site-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/omnisky/anaconda3/envs/mage/lib/python3.8/site-packages/torch/serialization.py", line 211, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'vqgan_jax_strongaug.ckpt'