Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
IDM-VTON_pytorch
Commits
d5096d86
Commit
d5096d86
authored
Jun 14, 2024
by
mashun1
Browse files
idmvton
parents
Pipeline
#1220
canceled with stages
Changes
292
Pipelines
1
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
1226 additions
and
0 deletions
+1226
-0
BasicSR/options/test/EDVR/test_EDVR_L_x4_SR_REDS.yml
BasicSR/options/test/EDVR/test_EDVR_L_x4_SR_REDS.yml
+50
-0
BasicSR/options/test/EDVR/test_EDVR_L_x4_SR_Vid4.yml
BasicSR/options/test/EDVR/test_EDVR_L_x4_SR_Vid4.yml
+49
-0
BasicSR/options/test/EDVR/test_EDVR_L_x4_SR_Vimeo90K.yml
BasicSR/options/test/EDVR/test_EDVR_L_x4_SR_Vimeo90K.yml
+50
-0
BasicSR/options/test/EDVR/test_EDVR_L_x4_SRblur_REDS.yml
BasicSR/options/test/EDVR/test_EDVR_L_x4_SRblur_REDS.yml
+50
-0
BasicSR/options/test/EDVR/test_EDVR_M_x4_SR_REDS.yml
BasicSR/options/test/EDVR/test_EDVR_M_x4_SR_REDS.yml
+50
-0
BasicSR/options/test/ESRGAN/test_ESRGAN_x4.yml
BasicSR/options/test/ESRGAN/test_ESRGAN_x4.yml
+59
-0
BasicSR/options/test/ESRGAN/test_ESRGAN_x4_woGT.yml
BasicSR/options/test/ESRGAN/test_ESRGAN_x4_woGT.yml
+38
-0
BasicSR/options/test/ESRGAN/test_RRDBNet_PSNR_x4.yml
BasicSR/options/test/ESRGAN/test_RRDBNet_PSNR_x4.yml
+59
-0
BasicSR/options/test/HiFaceGAN/test_hifacegan.yml
BasicSR/options/test/HiFaceGAN/test_hifacegan.yml
+76
-0
BasicSR/options/test/HiFaceGAN/test_hifacegan_woGT.yml
BasicSR/options/test/HiFaceGAN/test_hifacegan_woGT.yml
+37
-0
BasicSR/options/test/RCAN/test_RCAN.yml
BasicSR/options/test/RCAN/test_RCAN.yml
+53
-0
BasicSR/options/test/SRResNet_SRGAN/test_MSRGAN_x4.yml
BasicSR/options/test/SRResNet_SRGAN/test_MSRGAN_x4.yml
+59
-0
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x2.yml
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x2.yml
+59
-0
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x3.yml
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x3.yml
+59
-0
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x4.yml
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x4.yml
+67
-0
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x4_woGT.yml
...SR/options/test/SRResNet_SRGAN/test_MSRResNet_x4_woGT.yml
+38
-0
BasicSR/options/test/TOF/test_TOF_official.yml
BasicSR/options/test/TOF/test_TOF_official.yml
+45
-0
BasicSR/options/train/BasicVSR/train_BasicVSR_REDS.yml
BasicSR/options/train/BasicVSR/train_BasicVSR_REDS.yml
+110
-0
BasicSR/options/train/BasicVSR/train_BasicVSR_Vimeo90K_BDx4.yml
...R/options/train/BasicVSR/train_BasicVSR_Vimeo90K_BDx4.yml
+109
-0
BasicSR/options/train/BasicVSR/train_BasicVSR_Vimeo90K_BIx4.yml
...R/options/train/BasicVSR/train_BasicVSR_Vimeo90K_BIx4.yml
+109
-0
No files found.
Too many changes to show.
To preserve performance only
292 of 292+
files are displayed.
Plain diff
Email patch
BasicSR/options/test/EDVR/test_EDVR_L_x4_SR_REDS.yml
0 → 100644
View file @
d5096d86
name
:
EDVR_L_x4_REDS_SR_official
model_type
:
EDVRModel
scale
:
4
num_gpu
:
4
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test
:
name
:
REDS4
type
:
VideoTestDataset
dataroot_gt
:
datasets/REDS/train_sharp
dataroot_lq
:
datasets/REDS/train_sharp_bicubic
meta_info_file
:
basicsr/data/meta_info/meta_info_REDS4_test_GT.txt
io_backend
:
type
:
disk
cache_data
:
false
num_frame
:
5
padding
:
reflection_circle
# network structures
network_g
:
type
:
EDVR
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
128
num_frame
:
5
deformable_groups
:
8
num_extract_block
:
5
num_reconstruct_block
:
40
center_frame_idx
:
~
hr_in
:
false
with_predeblur
:
false
with_tsa
:
true
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/EDVR/EDVR_L_x4_SR_REDS_official-9f5f5039.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
0
test_y_channel
:
false
BasicSR/options/test/EDVR/test_EDVR_L_x4_SR_Vid4.yml
0 → 100644
View file @
d5096d86
name
:
EDVR_L_x4_Vimeo90K_SR_official
model_type
:
EDVRModel
scale
:
4
num_gpu
:
4
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test
:
name
:
Vid4
type
:
VideoTestDataset
dataroot_gt
:
datasets/Vid4/GT
dataroot_lq
:
datasets/Vid4/BIx4
io_backend
:
type
:
disk
cache_data
:
false
num_frame
:
7
padding
:
reflection_circle
# network structures
network_g
:
type
:
EDVR
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
128
num_frame
:
7
deformable_groups
:
8
num_extract_block
:
5
num_reconstruct_block
:
40
center_frame_idx
:
~
hr_in
:
false
with_predeblur
:
false
with_tsa
:
true
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/EDVR/EDVR_L_x4_SR_Vimeo90K_official-162b54e4.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
0
test_y_channel
:
false
BasicSR/options/test/EDVR/test_EDVR_L_x4_SR_Vimeo90K.yml
0 → 100644
View file @
d5096d86
name
:
EDVR_L_x4_Vimeo90K_SR_official
model_type
:
EDVRModel
scale
:
4
num_gpu
:
8
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test
:
name
:
Vimeo90K-Test
type
:
VideoTestVimeo90KDataset
dataroot_gt
:
datasets/vimeo90k/vimeo_septuplet/sequences
dataroot_lq
:
datasets/vimeo90k/vimeo_septuplet_matlabLRx4/sequences
meta_info_file
:
basicsr/data/meta_info/meta_info_Vimeo90K_test_GT.txt
io_backend
:
type
:
disk
cache_data
:
false
num_frame
:
7
padding
:
reflection_circle
# network structures
network_g
:
type
:
EDVR
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
128
num_frame
:
7
deformable_groups
:
8
num_extract_block
:
5
num_reconstruct_block
:
40
center_frame_idx
:
~
hr_in
:
false
with_predeblur
:
false
with_tsa
:
true
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/EDVR/EDVR_L_x4_SR_Vimeo90K_official-162b54e4.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
0
test_y_channel
:
false
BasicSR/options/test/EDVR/test_EDVR_L_x4_SRblur_REDS.yml
0 → 100644
View file @
d5096d86
name
:
EDVR_L_x4_REDS_SRblur_official
model_type
:
EDVRModel
scale
:
4
num_gpu
:
4
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test
:
name
:
REDS4
type
:
VideoTestDataset
dataroot_gt
:
datasets/REDS/train_sharp
dataroot_lq
:
datasets/REDS/train_blur_bicubic
meta_info_file
:
basicsr/data/meta_info/meta_info_REDS4_test_GT.txt
io_backend
:
type
:
disk
cache_data
:
false
num_frame
:
5
padding
:
replicate
# network structures
network_g
:
type
:
EDVR
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
128
num_frame
:
5
deformable_groups
:
8
num_extract_block
:
5
num_reconstruct_block
:
40
center_frame_idx
:
~
hr_in
:
false
with_predeblur
:
true
with_tsa
:
true
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/EDVR/EDVR_L_x4_SRblur_REDS_official-983d7b8e.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
0
test_y_channel
:
false
BasicSR/options/test/EDVR/test_EDVR_M_x4_SR_REDS.yml
0 → 100644
View file @
d5096d86
name
:
EDVR_M_x4_SR_REDS_official
model_type
:
EDVRModel
scale
:
4
num_gpu
:
4
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test
:
name
:
REDS4
type
:
VideoTestDataset
dataroot_gt
:
datasets/REDS/train_sharp
dataroot_lq
:
datasets/REDS/train_sharp_bicubic
meta_info_file
:
basicsr/data/meta_info/meta_info_REDS4_test_GT.txt
io_backend
:
type
:
disk
cache_data
:
false
num_frame
:
5
padding
:
reflection_circle
# network structures
network_g
:
type
:
EDVR
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_frame
:
5
deformable_groups
:
8
num_extract_block
:
5
num_reconstruct_block
:
10
center_frame_idx
:
~
hr_in
:
false
with_predeblur
:
false
with_tsa
:
true
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/EDVR/EDVR_M_x4_SR_REDS_official-32075921.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
0
test_y_channel
:
false
BasicSR/options/test/ESRGAN/test_ESRGAN_x4.yml
0 → 100644
View file @
d5096d86
name
:
ESRGAN_SRx4_DF2KOST_official
model_type
:
ESRGANModel
scale
:
4
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_1
:
# the 1st test dataset
name
:
Set5
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set5/GTmod12
dataroot_lq
:
datasets/Set5/LRbicx4
io_backend
:
type
:
disk
test_2
:
# the 2nd test dataset
name
:
Set14
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set14/GTmod12
dataroot_lq
:
datasets/Set14/LRbicx4
io_backend
:
type
:
disk
test_3
:
name
:
DIV2K100
type
:
PairedImageDataset
dataroot_gt
:
datasets/DIV2K/DIV2K_valid_HR
dataroot_lq
:
datasets/DIV2K/DIV2K_valid_LR_bicubic/X4
filename_tmpl
:
'
{}x4'
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
RRDBNet
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_block
:
23
num_grow_ch
:
32
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/ESRGAN/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
4
test_y_channel
:
false
ssim
:
type
:
calculate_ssim
crop_border
:
4
test_y_channel
:
false
BasicSR/options/test/ESRGAN/test_ESRGAN_x4_woGT.yml
0 → 100644
View file @
d5096d86
name
:
ESRGAN_SRx4_DF2KOST_official
model_type
:
ESRGANModel
scale
:
4
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_1
:
# the 1st test dataset
name
:
Set5
type
:
SingleImageDataset
dataroot_lq
:
datasets/Set5/LRbicx4
io_backend
:
type
:
disk
test_2
:
# the 2nd test dataset
name
:
Set14
type
:
SingleImageDataset
dataroot_lq
:
datasets/Set14/LRbicx4
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
RRDBNet
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_block
:
23
num_grow_ch
:
32
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/ESRGAN/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
BasicSR/options/test/ESRGAN/test_RRDBNet_PSNR_x4.yml
0 → 100644
View file @
d5096d86
name
:
ESRGAN_PSNR_SRx4_DF2K_official
model_type
:
SRModel
scale
:
4
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_1
:
# the 1st test dataset
name
:
Set5
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set5/GTmod12
dataroot_lq
:
datasets/Set5/LRbicx4
io_backend
:
type
:
disk
test_2
:
# the 2nd test dataset
name
:
Set14
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set14/GTmod12
dataroot_lq
:
datasets/Set14/LRbicx4
io_backend
:
type
:
disk
test_3
:
name
:
DIV2K100
type
:
PairedImageDataset
dataroot_gt
:
datasets/DIV2K/DIV2K_valid_HR
dataroot_lq
:
datasets/DIV2K/DIV2K_valid_LR_bicubic/X4
filename_tmpl
:
'
{}x4'
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
RRDBNet
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_block
:
23
num_grow_ch
:
32
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/ESRGAN/ESRGAN_PSNR_SRx4_DF2K_official-150ff491.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
4
test_y_channel
:
false
ssim
:
type
:
calculate_ssim
crop_border
:
4
test_y_channel
:
false
BasicSR/options/test/HiFaceGAN/test_hifacegan.yml
0 → 100644
View file @
d5096d86
name
:
HiFaceGAN_SR4x_test
model_type
:
HiFaceGANModel
scale
:
1
# HiFaceGAN does not resize lq input
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_gt
:
# the 2nd test dataset
name
:
FFHQ_sr4x_val
type
:
PairedImageDataset
dataroot_gt
:
datasets/FFHQ_512_gt_val
dataroot_lq
:
datasets/FFHQ_512_lq_val_sr4x
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
HiFaceGAN
num_in_ch
:
3
num_feat
:
48
use_vae
:
false
z_dim
:
256
# dummy var
crop_size
:
512
#norm_g: 'spectralspadesyncbatch3x3'
#norm_g: 'spectralspadeinstance3x3'
norm_g
:
'
spectralspadebatch3x3'
# 20210519: Use batchnorm for now.
is_train
:
false
# HifaceGAN supports progressive training
# so network architecture depends on it
# path
path
:
pretrain_network_g
:
experiments/HiFaceGAN_SR4x_train_full/models/net_g_latest.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
4
test_y_channel
:
false
ssim
:
type
:
calculate_ssim
crop_border
:
4
test_y_channel
:
false
# More metrics will be supported in the next update
#
# msssim:
# type: calculate_msssim
# crop_border: 4
# test_y_channel: false
# lpips:
# type: calculate_lpips
# crop_border: 4
# test_y_channel: false
# niqe:
# type: calculate_niqe
# crop_border: 4
# num_thread: 8
# fid:
# type: calculate_fid
# crop_border: 0
# test_y_channel: false
# use_bgr_order: true
# face_embedding_distance:
# type: calculate_fed
# crop_border: 0
# test_y_channel: false
# face_landmark_distance:
# type: calculate_lle
# crop_border: 0
# test_y_channel: false
BasicSR/options/test/HiFaceGAN/test_hifacegan_woGT.yml
0 → 100644
View file @
d5096d86
name
:
HiFaceGAN_generic_test
model_type
:
HiFaceGANModel
scale
:
1
# HiFaceGAN does not resize lq input
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_wild
:
# the 1st test dataset
name
:
FFHQ_in_the_wild
type
:
SingleImageDataset
dataroot_lq
:
datasets/real-world-lq
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
HiFaceGAN
# or SPADEGenerator
num_in_ch
:
3
num_feat
:
48
use_vae
:
false
z_dim
:
256
# dummy var
crop_size
:
512
#norm_g: 'spectralspadesyncbatch3x3'
norm_g
:
'
spectralspadebatch3x3'
# 20210519: Use instance norm for now.
is_train
:
false
# HifaceGAN supports progressive training
# so network architecture depends on it
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/generic/latest_net_G.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
generic
# add suffix to saved images, if None, use exp name
# No metrics
BasicSR/options/test/RCAN/test_RCAN.yml
0 → 100644
View file @
d5096d86
name
:
RCAN_BIX4-official
suffix
:
~
# add suffix to saved images
model_type
:
SRModel
scale
:
4
crop_border
:
~
# crop border when evaluation. If None, crop the scale pixels
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_1
:
# the 1st test dataset
name
:
val_set5
type
:
PairedImageDataset
dataroot_gt
:
./datasets/val_set5/Set5
dataroot_lq
:
./datasets/val_set5/Set5_bicLRx4
io_backend
:
type
:
disk
test_2
:
# the 2nd test dataset
name
:
val_set14
type
:
PairedImageDataset
dataroot_gt
:
./datasets/val_set14/Set14
dataroot_lq
:
./datasets/val_set14/Set14_bicLRx4
io_backend
:
type
:
disk
test_3
:
name
:
div2k100
type
:
PairedImageDataset
dataroot_gt
:
./datasets/DIV2K100/DIV2K_valid_HR
dataroot_lq
:
./datasets/DIV2K100/DIV2K_valid_bicLRx4
filename_tmpl
:
'
{}x4'
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
RCAN
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_group
:
10
num_block
:
20
squeeze_factor
:
16
upscale
:
4
res_scale
:
1
img_range
:
255.
rgb_mean
:
[
0.4488
,
0.4371
,
0.4040
]
save_img
:
true
# path
path
:
pretrain_network_g
:
./experiments/pretrained_models/RCAN/RCAN_BIX4-official.pth
strict_load_g
:
true
BasicSR/options/test/SRResNet_SRGAN/test_MSRGAN_x4.yml
0 → 100644
View file @
d5096d86
name
:
004_MSRGAN_x4_f64b16_DIV2K_400k_B16G1_wandb
model_type
:
SRGANModel
scale
:
4
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_1
:
# the 1st test dataset
name
:
Set5
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set5/GTmod12
dataroot_lq
:
datasets/Set5/LRbicx4
io_backend
:
type
:
disk
test_2
:
# the 2nd test dataset
name
:
Set14
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set14/GTmod12
dataroot_lq
:
datasets/Set14/LRbicx4
io_backend
:
type
:
disk
test_3
:
name
:
DIV2K100
type
:
PairedImageDataset
dataroot_gt
:
datasets/DIV2K/DIV2K_valid_HR
dataroot_lq
:
datasets/DIV2K/DIV2K_valid_LR_bicubic/X4
filename_tmpl
:
'
{}x4'
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
MSRResNet
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_block
:
16
upscale
:
4
# path
path
:
pretrain_network_g
:
experiments/004_MSRGAN_x4_f64b16_DIV2K_400k_B16G1_wandb/models/net_g_400000.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
4
test_y_channel
:
false
ssim
:
type
:
calculate_ssim
crop_border
:
4
test_y_channel
:
false
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x2.yml
0 → 100644
View file @
d5096d86
name
:
002_MSRResNet_x2_f64b16_DIV2K_1000k_B16G1_001pretrain_wandb
model_type
:
SRModel
scale
:
2
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_1
:
# the 1st test dataset
name
:
Set5
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set5/GTmod12
dataroot_lq
:
datasets/Set5/LRbicx2
io_backend
:
type
:
disk
test_2
:
# the 2nd test dataset
name
:
Set14
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set14/GTmod12
dataroot_lq
:
datasets/Set14/LRbicx2
io_backend
:
type
:
disk
test_3
:
name
:
DIV2K100
type
:
PairedImageDataset
dataroot_gt
:
datasets/DIV2K/DIV2K_valid_HR
dataroot_lq
:
datasets/DIV2K/DIV2K_valid_LR_bicubic/X2
filename_tmpl
:
'
{}x2'
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
MSRResNet
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_block
:
16
upscale
:
2
# path
path
:
pretrain_network_g
:
experiments/002_MSRResNet_x2_f64b16_DIV2K_1000k_B16G1_001pretrain_wandb/models/net_g_1000000.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
2
test_y_channel
:
false
ssim
:
type
:
calculate_ssim
crop_border
:
2
test_y_channel
:
false
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x3.yml
0 → 100644
View file @
d5096d86
name
:
003_MSRResNet_x3_f64b16_DIV2K_1000k_B16G1_001pretrain_wandb
model_type
:
SRModel
scale
:
3
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_1
:
# the 1st test dataset
name
:
Set5
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set5/GTmod12
dataroot_lq
:
datasets/Set5/LRbicx3
io_backend
:
type
:
disk
test_2
:
# the 2nd test dataset
name
:
Set14
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set14/GTmod12
dataroot_lq
:
datasets/Set14/LRbicx3
io_backend
:
type
:
disk
test_3
:
name
:
DIV2K100
type
:
PairedImageDataset
dataroot_gt
:
datasets/DIV2K/DIV2K_valid_HR
dataroot_lq
:
datasets/DIV2K/DIV2K_valid_LR_bicubic/X3
filename_tmpl
:
'
{}x3'
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
MSRResNet
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_block
:
16
upscale
:
3
# path
path
:
pretrain_network_g
:
experiments/003_MSRResNet_x3_f64b16_DIV2K_1000k_B16G1_001pretrain_wandb/models/net_g_1000000.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
3
test_y_channel
:
false
ssim
:
type
:
calculate_ssim
crop_border
:
3
test_y_channel
:
false
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x4.yml
0 → 100644
View file @
d5096d86
# ----------- Commands for running
# ----------- Single GPU
# PYTHONPATH="./:${PYTHONPATH}" CUDA_VISIBLE_DEVICES=0 python basicsr/test.py -opt options/test/SRResNet_SRGAN/test_MSRResNet_x4.yml
# general settings
name
:
001_MSRResNet_x4_f64b16_DIV2K_1000k_B16G1_wandb
model_type
:
SRModel
scale
:
4
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
# test dataset settings
datasets
:
test_1
:
# the 1st test dataset
name
:
Set5
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set5/GTmod12
dataroot_lq
:
datasets/Set5/LRbicx4
io_backend
:
type
:
disk
test_2
:
# the 2nd test dataset
name
:
Set14
type
:
PairedImageDataset
dataroot_gt
:
datasets/Set14/GTmod12
dataroot_lq
:
datasets/Set14/LRbicx4
io_backend
:
type
:
disk
test_3
:
# the 3rd test dataset
name
:
DIV2K100
type
:
PairedImageDataset
dataroot_gt
:
datasets/DIV2K/DIV2K_valid_HR
dataroot_lq
:
datasets/DIV2K/DIV2K_valid_LR_bicubic/X4
filename_tmpl
:
'
{}x4'
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
MSRResNet
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_block
:
16
upscale
:
4
# path
path
:
pretrain_network_g
:
experiments/001_MSRResNet_x4_f64b16_DIV2K_1000k_B16G1_wandb/models/net_g_1000000.pth
param_key_g
:
params
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
4
test_y_channel
:
false
better
:
higher
# the higher, the better. Default: higher
ssim
:
type
:
calculate_ssim
crop_border
:
4
test_y_channel
:
false
better
:
higher
BasicSR/options/test/SRResNet_SRGAN/test_MSRResNet_x4_woGT.yml
0 → 100644
View file @
d5096d86
name
:
001_MSRResNet_x4_f64b16_DIV2K_1000k_B16G1_wandb
model_type
:
SRModel
scale
:
4
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test_1
:
# the 1st test dataset
name
:
Set5
type
:
SingleImageDataset
dataroot_lq
:
datasets/Set5/LRbicx4
io_backend
:
type
:
disk
test_2
:
# the 2nd test dataset
name
:
Set14
type
:
SingleImageDataset
dataroot_lq
:
datasets/Set14/LRbicx4
io_backend
:
type
:
disk
# network structures
network_g
:
type
:
MSRResNet
num_in_ch
:
3
num_out_ch
:
3
num_feat
:
64
num_block
:
16
upscale
:
4
# path
path
:
pretrain_network_g
:
experiments/001_MSRResNet_x4_f64b16_DIV2K_1000k_B16G1_wandb/models/net_g_1000000.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
BasicSR/options/test/TOF/test_TOF_official.yml
0 → 100644
View file @
d5096d86
name
:
TOF_official
model_type
:
VideoBaseModel
scale
:
4
num_gpu
:
1
# set num_gpu: 0 for cpu mode
manual_seed
:
0
datasets
:
test
:
name
:
Vid4
type
:
VideoTestDataset
dataroot_gt
:
datasets/Vid4/GT
dataroot_lq
:
datasets/Vid4/BIx4up_direct
io_backend
:
type
:
disk
cache_data
:
false
num_frame
:
7
padding
:
reflection_circle
# network structures
network_g
:
type
:
TOFlow
adapt_official_weights
:
true
save_img
:
true
# path
path
:
pretrain_network_g
:
experiments/pretrained_models/TOF/tof_x4_vimeo90k_official-32c9e01f.pth
strict_load_g
:
true
# validation settings
val
:
save_img
:
true
suffix
:
~
# add suffix to saved images, if None, use exp name
metrics
:
psnr_y
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
0
test_y_channel
:
true
ssim_y
:
type
:
calculate_ssim
crop_border
:
0
test_y_channel
:
true
BasicSR/options/train/BasicVSR/train_BasicVSR_REDS.yml
0 → 100644
View file @
d5096d86
# general settings
name
:
BasicVSR_REDS
model_type
:
VideoRecurrentModel
scale
:
4
num_gpu
:
auto
# official: 8 GPUs
manual_seed
:
0
# dataset and data loader settings
datasets
:
train
:
name
:
REDS
type
:
REDSRecurrentDataset
dataroot_gt
:
datasets/REDS/train_sharp
dataroot_lq
:
datasets/REDS/train_sharp_bicubic/X4
meta_info_file
:
basicsr/data/meta_info/meta_info_REDS_GT.txt
val_partition
:
REDS4
# set to 'official' when use the official validation partition
test_mode
:
False
io_backend
:
type
:
disk
num_frame
:
15
gt_size
:
256
interval_list
:
[
1
]
random_reverse
:
false
use_hflip
:
true
use_rot
:
true
# data loader
num_worker_per_gpu
:
6
batch_size_per_gpu
:
4
dataset_enlarge_ratio
:
200
prefetch_mode
:
~
val
:
name
:
REDS4
type
:
VideoRecurrentTestDataset
dataroot_gt
:
datasets/REDS4/GT
dataroot_lq
:
datasets/REDS4/sharp_bicubic
cache_data
:
true
io_backend
:
type
:
disk
num_frame
:
-1
# not needed
# network structures
network_g
:
type
:
BasicVSR
num_feat
:
64
num_block
:
30
spynet_path
:
experiments/pretrained_models/flownet/spynet_sintel_final-3d2a1287.pth
# path
path
:
pretrain_network_g
:
~
strict_load_g
:
true
resume_state
:
~
# training settings
train
:
ema_decay
:
0.999
optim_g
:
type
:
Adam
lr
:
!!float
2e-4
weight_decay
:
0
betas
:
[
0.9
,
0.99
]
scheduler
:
type
:
CosineAnnealingRestartLR
periods
:
[
300000
]
restart_weights
:
[
1
]
eta_min
:
!!float
1e-7
total_iter
:
300000
warmup_iter
:
-1
# no warm up
fix_flow
:
5000
flow_lr_mul
:
0.125
# losses
pixel_opt
:
type
:
CharbonnierLoss
loss_weight
:
1.0
reduction
:
mean
# validation settings
val
:
val_freq
:
!!float
5e3
save_img
:
false
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
0
test_y_channel
:
false
# logging settings
logger
:
print_freq
:
100
save_checkpoint_freq
:
!!float
5e3
use_tb_logger
:
true
wandb
:
project
:
~
resume_id
:
~
# dist training settings
dist_params
:
backend
:
nccl
port
:
29500
find_unused_parameters
:
true
BasicSR/options/train/BasicVSR/train_BasicVSR_Vimeo90K_BDx4.yml
0 → 100644
View file @
d5096d86
# general settings
name
:
BasicVSR_Vimeo90K_BDx4
model_type
:
VideoRecurrentModel
scale
:
4
num_gpu
:
2
# set num_gpu: 0 for cpu mode
manual_seed
:
0
# dataset and data loader settings
datasets
:
train
:
name
:
Vimeo90K
type
:
Vimeo90KRecurrentDataset
dataroot_gt
:
datasets/vimeo90k/vimeo_septuplet/sequences
dataroot_lq
:
datasets/vimeo90k/BDx4
meta_info_file
:
basicsr/data/meta_info/meta_info_Vimeo90K_train_GT.txt
io_backend
:
type
:
disk
num_frame
:
-1
gt_size
:
256
interval_list
:
[
1
]
random_reverse
:
false
use_hflip
:
true
use_rot
:
true
flip_sequence
:
true
# data loader
num_worker_per_gpu
:
6
batch_size_per_gpu
:
4
dataset_enlarge_ratio
:
200
prefetch_mode
:
~
val
:
name
:
Vid4
type
:
VideoRecurrentTestDataset
dataroot_gt
:
datasets/Vid4/GT
dataroot_lq
:
datasets/Vid4/BDx4
cache_data
:
True
io_backend
:
type
:
disk
num_frame
:
-1
# not needed
# network structures
network_g
:
type
:
BasicVSR
num_feat
:
64
num_block
:
30
spynet_path
:
experiments/pretrained_models/flownet/spynet_sintel_final-3d2a1287.pth
# path
path
:
pretrain_network_g
:
~
strict_load_g
:
true
resume_state
:
~
# training settings
train
:
ema_decay
:
0.999
optim_g
:
type
:
Adam
lr
:
!!float
2e-4
weight_decay
:
0
betas
:
[
0.9
,
0.99
]
scheduler
:
type
:
CosineAnnealingRestartLR
periods
:
[
300000
]
restart_weights
:
[
1
]
eta_min
:
!!float
1e-7
total_iter
:
300000
warmup_iter
:
-1
# no warm up
fix_flow
:
5000
flow_lr_mul
:
0.125
# losses
pixel_opt
:
type
:
CharbonnierLoss
loss_weight
:
1.0
reduction
:
mean
# validation settings
val
:
val_freq
:
!!float
5e3
save_img
:
false
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
0
test_y_channel
:
true
# logging settings
logger
:
print_freq
:
100
save_checkpoint_freq
:
!!float
5e3
use_tb_logger
:
true
wandb
:
project
:
~
resume_id
:
~
# dist training settings
dist_params
:
backend
:
nccl
port
:
29500
find_unused_parameters
:
true
BasicSR/options/train/BasicVSR/train_BasicVSR_Vimeo90K_BIx4.yml
0 → 100644
View file @
d5096d86
# general settings
name
:
BasicVSR_Vimeo90K_BIx4
model_type
:
VideoRecurrentModel
scale
:
4
num_gpu
:
2
# set num_gpu: 0 for cpu mode
manual_seed
:
0
# dataset and data loader settings
datasets
:
train
:
name
:
Vimeo90K
type
:
Vimeo90KRecurrentDataset
dataroot_gt
:
datasets/vimeo90k/vimeo_septuplet/sequences
dataroot_lq
:
datasets/vimeo90k/BIx4
meta_info_file
:
basicsr/data/meta_info/meta_info_Vimeo90K_train_GT.txt
io_backend
:
type
:
disk
num_frame
:
-1
gt_size
:
256
interval_list
:
[
1
]
random_reverse
:
false
use_hflip
:
true
use_rot
:
true
flip_sequence
:
true
# data loader
num_worker_per_gpu
:
6
batch_size_per_gpu
:
4
dataset_enlarge_ratio
:
200
prefetch_mode
:
~
val
:
name
:
Vid4
type
:
VideoRecurrentTestDataset
dataroot_gt
:
datasets/Vid4/GT
dataroot_lq
:
datasets/Vid4/BIx4
cache_data
:
True
io_backend
:
type
:
disk
num_frame
:
-1
# not needed
# network structures
network_g
:
type
:
BasicVSR
num_feat
:
64
num_block
:
30
spynet_path
:
experiments/pretrained_models/flownet/spynet_sintel_final-3d2a1287.pth
# path
path
:
pretrain_network_g
:
~
strict_load_g
:
true
resume_state
:
~
# training settings
train
:
ema_decay
:
0.999
optim_g
:
type
:
Adam
lr
:
!!float
2e-4
weight_decay
:
0
betas
:
[
0.9
,
0.99
]
scheduler
:
type
:
CosineAnnealingRestartLR
periods
:
[
300000
]
restart_weights
:
[
1
]
eta_min
:
!!float
1e-7
total_iter
:
300000
warmup_iter
:
-1
# no warm up
fix_flow
:
5000
flow_lr_mul
:
0.125
# losses
pixel_opt
:
type
:
CharbonnierLoss
loss_weight
:
1.0
reduction
:
mean
# validation settings
val
:
val_freq
:
!!float
5e3
save_img
:
false
metrics
:
psnr
:
# metric name, can be arbitrary
type
:
calculate_psnr
crop_border
:
0
test_y_channel
:
true
# logging settings
logger
:
print_freq
:
100
save_checkpoint_freq
:
!!float
5e3
use_tb_logger
:
true
wandb
:
project
:
~
resume_id
:
~
# dist training settings
dist_params
:
backend
:
nccl
port
:
29500
find_unused_parameters
:
true
Prev
1
…
6
7
8
9
10
11
12
13
14
15
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment