-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy patheval.py
188 lines (156 loc) · 8.11 KB
/
eval.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
import argparse
import numpy as np
import os
from pathlib import Path
import torch
torch.backends.cuda.matmul.allow_tf32 = True
torch.backends.cudnn.allow_tf32 = True
import torch.backends.cudnn as cudnn
from torch.utils.tensorboard import SummaryWriter
import util.misc as misc
from models.vae import AutoencoderKL
from models import flowar
from engine import evaluate
def get_args_parser():
parser = argparse.ArgumentParser('FlowAR training with flow matching Loss', add_help=False)
parser.add_argument('--batch_size', default=16, type=int,
help='Batch size per GPU (effective batch size is batch_size * # gpus')
parser.add_argument('--epochs', default=400, type=int)
# Model parameters
parser.add_argument('--model', default='flowar_large', type=str, metavar='MODEL',
help='Name of model to train')
# VAE parameters
parser.add_argument('--img_size', default=256, type=int,
help='images input size')
parser.add_argument('--vae_path', default="pretrained_models/vae/kl16.ckpt", type=str,
help='images input size')
parser.add_argument('--vae_embed_dim', default=16, type=int,
help='vae output embedding dimension')
parser.add_argument('--vae_stride', default=16, type=int,
help='tokenizer stride, default use KL16')
parser.add_argument('--patch_size', default=1, type=int,
help='number of tokens to group as a patch.')
# Generation parameters
parser.add_argument('--num_steps', default=25, type=int,
help='number of autoregressive iterations to generate an image')
parser.add_argument('--guidance', default=0.9, type=float,
help='number of autoregressive iterations to generate an image')
parser.add_argument('--num_images', default=50000, type=int,
help='number of images to generate')
parser.add_argument('--cfg', default=1.0, type=float, help="classifier-free guidance")
parser.add_argument('--cfg_schedule', default="linear", type=str)
parser.add_argument('--label_drop_prob', default=0.1, type=float)
parser.add_argument('--eval_freq', type=int, default=40, help='evaluation frequency')
parser.add_argument('--save_last_freq', type=int, default=5, help='save last frequency')
parser.add_argument('--online_eval', action='store_true')
parser.add_argument('--evaluate', action='store_true')
parser.add_argument('--eval_bsz', type=int, default=64, help='generation batch size')
# Optimizer parameters
parser.add_argument('--weight_decay', type=float, default=0.02,
help='weight decay (default: 0.02)')
parser.add_argument('--lr', type=float, default=None, metavar='LR',
help='learning rate (absolute lr)')
parser.add_argument('--blr', type=float, default=1e-4, metavar='LR',
help='base learning rate: absolute_lr = base_lr * total_batch_size / 256')
parser.add_argument('--min_lr', type=float, default=0., metavar='LR',
help='lower lr bound for cyclic schedulers that hit 0')
parser.add_argument('--lr_schedule', type=str, default='constant',
help='learning rate schedule')
parser.add_argument('--warmup_epochs', type=int, default=100, metavar='N',
help='epochs to warmup LR')
parser.add_argument('--ema_rate', default=0.9999, type=float)
parser.add_argument('--grad_clip', type=float, default=3.0,
help='Gradient clip')
parser.add_argument('--attn_dropout', type=float, default=0.1,
help='attention dropout')
parser.add_argument('--proj_dropout', type=float, default=0.1,
help='projection dropout')
parser.add_argument('--buffer_size', type=int, default=0)
# Diffusion Loss params
parser.add_argument('--diffloss_d', type=int, default=12)
parser.add_argument('--diffloss_w', type=int, default=1536)
parser.add_argument('--temperature', default=1.0, type=float, help='diffusion loss sampling temperature')
# Dataset parameters
parser.add_argument('--data_path', default='./data/imagenet', type=str,
help='dataset path')
parser.add_argument('--class_num', default=1000, type=int)
parser.add_argument('--output_dir', default='./output_dir',
help='path where to save, empty for no saving')
parser.add_argument('--log_dir', default='./output_dir',
help='path where to tensorboard log')
parser.add_argument('--device', default='cuda',
help='device to use for training / testing')
parser.add_argument('--seed', default=1, type=int)
parser.add_argument('--resume', default='',
help='resume from checkpoint')
parser.add_argument('--start_epoch', default=0, type=int, metavar='N',
help='start epoch')
parser.add_argument('--num_workers', default=10, type=int)
parser.add_argument('--pin_mem', action='store_true',
help='Pin CPU memory in DataLoader for more efficient (sometimes) transfer to GPU.')
parser.add_argument('--no_pin_mem', action='store_false', dest='pin_mem')
parser.set_defaults(pin_mem=True)
# distributed training parameters
parser.add_argument('--world_size', default=1, type=int,
help='number of distributed processes')
parser.add_argument('--local_rank', default=-1, type=int)
parser.add_argument('--dist_on_itp', action='store_true')
parser.add_argument('--dist_url', default='env://',
help='url used to set up distributed training')
# caching latents
parser.add_argument('--use_cached', action='store_true', dest='use_cached',
help='Use cached latents')
parser.set_defaults(use_cached=True)
parser.add_argument('--cached_path', default='', help='path to cached latents')
return parser
def main(args):
misc.init_distributed_mode(args)
print('job dir: {}'.format(os.path.dirname(os.path.realpath(__file__))))
print("{}".format(args).replace(', ', ',\n'))
device = torch.device(args.device)
# fix the seed for reproducibility
seed = args.seed + misc.get_rank()
torch.manual_seed(seed)
np.random.seed(seed)
cudnn.benchmark = True
num_tasks = misc.get_world_size()
global_rank = misc.get_rank()
if global_rank == 0 and args.log_dir is not None:
os.makedirs(args.log_dir, exist_ok=True)
log_writer = SummaryWriter(log_dir=args.log_dir)
else:
log_writer = None
vae = AutoencoderKL(embed_dim=args.vae_embed_dim, ch_mult=(1, 1, 2, 2, 4), ckpt_path=args.vae_path).cuda().eval()
for param in vae.parameters():
param.requires_grad = False
model = flowar.__dict__[args.model](
img_size=args.img_size,
vae_stride=args.vae_stride,
patch_size=args.patch_size,
vae_embed_dim=args.vae_embed_dim,
label_drop_prob=args.label_drop_prob,
class_num=args.class_num,
attn_dropout=args.attn_dropout,
proj_dropout=args.proj_dropout,
buffer_size=args.buffer_size,
diffloss_d=args.diffloss_d,
diffloss_w=args.diffloss_w,
)
print("Model = %s" % str(model))
# following timm: set wd as 0 for bias and norm layers
n_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
print("Number of trainable parameters: {}M".format(n_params / 1e6))
model.to(device)
model_without_ddp = model
checkpoint = torch.load(os.path.join(args.resume), map_location='cpu')
model_without_ddp.load_state_dict(checkpoint)
print("Resume checkpoint %s" % args.resume)
torch.cuda.empty_cache()
evaluate(model_without_ddp, vae, args, 0, batch_size=args.eval_bsz, log_writer=log_writer,
cfg=args.cfg, use_ema=True)
if __name__ == '__main__':
args = get_args_parser()
args = args.parse_args()
Path(args.output_dir).mkdir(parents=True, exist_ok=True)
args.log_dir = args.output_dir
main(args)