File size: 7,094 Bytes
feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 69a2d79 feb2918 11b1aa8 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 |
name: COVER
num_epochs: 0
l_num_epochs: 10
warmup_epochs: 2.5
ema: true
save_model: true
batch_size: 8
num_workers: 6
split_seed: 42
wandb:
project_name: COVER
data:
val-livevqc:
type: ViewDecompositionDataset
args:
weight: 0.598
phase: test
anno_file: ./examplar_data_labels/LIVE_VQC/labels.txt
data_prefix: ./datasets/LIVE_VQC/ # revert before submit
sample_types:
semantic:
size_h: 512
size_w: 512
clip_len: 1
frame_interval: 2
t_frag: 1
num_clips: 1
technical:
fragments_h: 7
fragments_w: 7
fsize_h: 32
fsize_w: 32
aligned: 2
clip_len: 2
t_frag: 1
frame_interval: 2
num_clips: 1
aesthetic:
size_h: 224
size_w: 224
clip_len: 2
frame_interval: 2
t_frag: 1
num_clips: 1
val-kv1k:
type: ViewDecompositionDataset
args:
weight: 0.540
phase: test
anno_file: ./examplar_data_labels/KoNViD/labels.txt
data_prefix: ./datasets/KoNViD/ # revert before submit
sample_types:
semantic:
size_h: 512
size_w: 512
clip_len: 1
frame_interval: 2
t_frag: 1
num_clips: 1
technical:
fragments_h: 7
fragments_w: 7
fsize_h: 32
fsize_w: 32
aligned: 2
clip_len: 2
t_frag: 1
frame_interval: 2
num_clips: 1
aesthetic:
size_h: 224
size_w: 224
clip_len: 2
frame_interval: 2
t_frag: 1
num_clips: 1
val-ltest:
type: ViewDecompositionDataset
args:
weight: 0.603
phase: test
anno_file: ./examplar_data_labels/LSVQ/labels_test.txt
data_prefix: ./datasets/LSVQ/ # revert before submit
sample_types:
semantic:
size_h: 512
size_w: 512
clip_len: 1
frame_interval: 2
t_frag: 1
num_clips: 1
technical:
fragments_h: 7
fragments_w: 7
fsize_h: 32
fsize_w: 32
aligned: 2
clip_len: 2
t_frag: 1
frame_interval: 2
num_clips: 1
aesthetic:
size_h: 224
size_w: 224
clip_len: 2
frame_interval: 2
t_frag: 1
num_clips: 1
val-l1080p:
type: ViewDecompositionDataset
args:
weight: 0.620
phase: test
anno_file: ./examplar_data_labels/LSVQ/labels_1080p.txt
data_prefix: ./datasets/LSVQ/ # revert before submit
sample_types:
semantic:
size_h: 512
size_w: 512
clip_len: 1
frame_interval: 2
t_frag: 1
num_clips: 1
technical:
fragments_h: 7
fragments_w: 7
fsize_h: 32
fsize_w: 32
aligned: 2
clip_len: 2
t_frag: 1
frame_interval: 2
num_clips: 1
aesthetic:
size_h: 224
size_w: 224
clip_len: 2
frame_interval: 2
t_frag: 1
num_clips: 1
val-cvd2014:
type: ViewDecompositionDataset
args:
weight: 0.576
phase: test
anno_file: ./examplar_data_labels/CVD2014/labels.txt
data_prefix: ./datasets/CVD2014/ # revert before submit
sample_types:
semantic:
size_h: 512
size_w: 512
clip_len: 1
frame_interval: 2
t_frag: 1
num_clips: 1
technical:
fragments_h: 7
fragments_w: 7
fsize_h: 32
fsize_w: 32
aligned: 2
clip_len: 2
t_frag: 1
frame_interval: 2
num_clips: 1
aesthetic:
size_h: 224
size_w: 224
clip_len: 2
frame_interval: 2
t_frag: 1
num_clips: 1
val-ytugc:
type: ViewDecompositionDataset
args:
weight: 0.443
phase: test
anno_file: ./examplar_data_labels/YouTubeUGC/labels.txt
data_prefix: ./dataset/YouTubeUGC/ # revert before submit
sample_types:
semantic:
size_h: 512
size_w: 512
clip_len: 1
frame_interval: 2
t_frag: 1
num_clips: 1
technical:
fragments_h: 7
fragments_w: 7
fsize_h: 32
fsize_w: 32
aligned: 2
clip_len: 2
t_frag: 1
frame_interval: 2
num_clips: 1
aesthetic:
size_h: 224
size_w: 224
clip_len: 2
frame_interval: 2
t_frag: 1
num_clips: 1
model:
type: COVER
args:
backbone:
technical:
type: swin_tiny_grpb
checkpoint: true
pretrained:
aesthetic:
type: conv_tiny
semantic:
type: clip_iqa+
backbone_preserve_keys: technical,aesthetic,semantic
divide_head: true
vqa_head:
in_channels: 768
hidden_channels: 64
optimizer:
lr: !!float 1e-3
backbone_lr_mult: !!float 1e-1
wd: 0.05
test_load_path: ./COVER.pth # revert before submit |