-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathstdout.9444980.venus01
170 lines (169 loc) · 5.78 KB
/
stdout.9444980.venus01
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
Not using distributed mode
[20:39:30.077609] job dir: /home/svu/e1100476/Project/SSL/mae
[20:39:30.077745] Namespace(batch_size=64,
epochs=400,
accum_iter=1,
model='mae_vit_base_patch16',
input_size=224,
mask_ratio=0.75,
norm_pix_loss=False,
momentum=0.999,
weight_decay=0.05,
lr=None,
blr=0.001,
min_lr=0.0,
warmup_epochs=40,
data_path='/hpctmp/pbs_dm_stage/access_temp_stage/e1100476/Dataset/retina images/pretrain',
output_dir='/hpctmp/pbs_dm_stage/access_temp_stage/e1100476/Model/MAE/v2_.75',
log_dir='/hpctmp/pbs_dm_stage/access_temp_stage/e1100476/Model/MAE/v2_.75',
device='cuda',
seed=0,
resume='',
start_epoch=0,
num_workers=10,
pin_mem=True,
world_size=1,
local_rank=-1,
dist_on_itp=False,
dist_url='env://',
distributed=False)
[20:39:30.164023] Dataset ImageFolder
Number of datapoints: 35126
Root location: /hpctmp/pbs_dm_stage/access_temp_stage/e1100476/Dataset/retina images/pretrain
StandardTransform
Transform: Compose(
RandomResizedCrop(size=(224, 224), scale=(0.2, 1.0), ratio=(0.75, 1.3333), interpolation=bicubic, antialias=warn)
RandomHorizontalFlip(p=0.5)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
[20:39:30.164132] Sampler_train = <torch.utils.data.distributed.DistributedSampler object at 0x2afcbaf6eb60>
[20:39:36.388655] Model = MaskedAutoencoderViT(
(Encoder): Encoder(
(patch_embed): PatchEmbed(
(proj): Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16))
(norm): Identity()
)
(blocks): ModuleList(
(0-11): 12 x Block(
(norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(attn): Attention(
(qkv): Linear(in_features=768, out_features=2304, bias=True)
(q_norm): Identity()
(k_norm): Identity()
(attn_drop): Dropout(p=0.0, inplace=False)
(proj): Linear(in_features=768, out_features=768, bias=True)
(proj_drop): Dropout(p=0.0, inplace=False)
)
(ls1): Identity()
(drop_path1): Identity()
(norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=768, out_features=3072, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(norm): Identity()
(fc2): Linear(in_features=3072, out_features=768, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(ls2): Identity()
(drop_path2): Identity()
)
)
(norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
)
(ContextEncoder): ContextEncoder(
(patch_embed): PatchEmbed(
(proj): Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16))
(norm): Identity()
)
(blocks): ModuleList(
(0-11): 12 x Block(
(norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(attn): Attention(
(qkv): Linear(in_features=768, out_features=2304, bias=True)
(q_norm): Identity()
(k_norm): Identity()
(attn_drop): Dropout(p=0.0, inplace=False)
(proj): Linear(in_features=768, out_features=768, bias=True)
(proj_drop): Dropout(p=0.0, inplace=False)
)
(ls1): Identity()
(drop_path1): Identity()
(norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=768, out_features=3072, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(norm): Identity()
(fc2): Linear(in_features=3072, out_features=768, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(ls2): Identity()
(drop_path2): Identity()
)
)
(norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
)
(Decoder): Decoder(
(decoder_embed): Linear(in_features=768, out_features=512, bias=True)
(decoder_blocks): ModuleList(
(0-7): 8 x Block(
(norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(attn): Attention(
(qkv): Linear(in_features=512, out_features=1536, bias=True)
(q_norm): Identity()
(k_norm): Identity()
(attn_drop): Dropout(p=0.0, inplace=False)
(proj): Linear(in_features=512, out_features=512, bias=True)
(proj_drop): Dropout(p=0.0, inplace=False)
)
(ls1): Identity()
(drop_path1): Identity()
(norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(mlp): Mlp(
(fc1): Linear(in_features=512, out_features=2048, bias=True)
(act): GELU(approximate='none')
(drop1): Dropout(p=0.0, inplace=False)
(norm): Identity()
(fc2): Linear(in_features=2048, out_features=512, bias=True)
(drop2): Dropout(p=0.0, inplace=False)
)
(ls2): Identity()
(drop_path2): Identity()
)
)
(decoder_norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True)
(decoder_pred): Linear(in_features=512, out_features=768, bias=True)
)
)
[20:39:36.388720] base lr: 1.00e-03
[20:39:36.388729] actual lr: 2.50e-04
[20:39:36.388735] accumulate grad iterations: 1
[20:39:36.388740] effective batch size: 64
[20:39:36.391366] AdamW (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.95)
capturable: False
differentiable: False
eps: 1e-08
foreach: None
fused: None
lr: 0.00025
maximize: False
weight_decay: 0.0
Parameter Group 1
amsgrad: False
betas: (0.9, 0.95)
capturable: False
differentiable: False
eps: 1e-08
foreach: None
fused: None
lr: 0.00025
maximize: False
weight_decay: 0.05
)
[20:39:36.391496] Start training for 400 epochs
[20:39:36.394246] log_dir: /hpctmp/pbs_dm_stage/access_temp_stage/e1100476/Model/MAE/v2_.75