[Config] Add oCLIP configs (#1509)

* [Config] Add oClip configs * fix linitng * fix
2025-06-03 21:54:47 +08:00 · 2022-11-03 17:57:13 +08:00 · 2022-11-03 17:57:13 +08:00 · d92444097d
commit d92444097d
parent f1dd437d8d
12 changed files with 197 additions and 0 deletions
--- a/configs/textdet/dbnet/dbnet_resnet50-oclip_1200e_icdar2015.py
+++ b/configs/textdet/dbnet/dbnet_resnet50-oclip_1200e_icdar2015.py
@ -0,0 +1,20 @@
+_base_ = [
+    'dbnet_resnet50-dcnv2_fpnc_1200e_icdar2015.py',
+]
+
+load_from = None
+
+_base_.model.backbone = dict(
+    type='CLIPResNet',
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))
+
+_base_.train_dataloader.num_workers = 24
+_base_.optim_wrapper.optimizer.lr = 0.002
+
+param_scheduler = [
+    dict(type='LinearLR', end=100, start_factor=0.001),
+    dict(type='PolyLR', power=0.9, eta_min=1e-7, begin=100, end=1200),
+]
--- a/configs/textdet/dbnet/dbnet_resnet50_1200e_icdar2015.py
+++ b/configs/textdet/dbnet/dbnet_resnet50_1200e_icdar2015.py
@ -0,0 +1,24 @@
+_base_ = [
+    'dbnet_resnet50-dcnv2_fpnc_1200e_icdar2015.py',
+]
+
+load_from = None
+
+_base_.model.backbone = dict(
+    type='mmdet.ResNet',
+    depth=50,
+    num_stages=4,
+    out_indices=(0, 1, 2, 3),
+    frozen_stages=-1,
+    norm_cfg=dict(type='BN', requires_grad=True),
+    norm_eval=True,
+    style='pytorch',
+    init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'))
+
+_base_.train_dataloader.num_workers = 24
+_base_.optim_wrapper.optimizer.lr = 0.002
+
+param_scheduler = [
+    dict(type='LinearLR', end=100, start_factor=0.001),
+    dict(type='PolyLR', power=0.9, eta_min=1e-7, begin=100, end=1200),
+]
--- a/configs/textdet/dbnetpp/dbnetpp_resnet50-oclip_fpnc_1200e_icdar2015.py
+++ b/configs/textdet/dbnetpp/dbnetpp_resnet50-oclip_fpnc_1200e_icdar2015.py
@ -0,0 +1,20 @@
+_base_ = [
+    'dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015.py',
+]
+
+load_from = None
+
+_base_.model.backbone = dict(
+    type='CLIPResNet',
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))
+
+_base_.train_dataloader.num_workers = 24
+_base_.optim_wrapper.optimizer.lr = 0.002
+
+param_scheduler = [
+    dict(type='LinearLR', end=200, start_factor=0.001),
+    dict(type='PolyLR', power=0.9, eta_min=1e-7, begin=200, end=1200),
+]
--- a/configs/textdet/dbnetpp/dbnetpp_resnet50_fpnc_1200e_icdar2015.py
+++ b/configs/textdet/dbnetpp/dbnetpp_resnet50_fpnc_1200e_icdar2015.py
@ -0,0 +1,24 @@
+_base_ = [
+    'dbnetpp_resnet50-dcnv2_fpnc_1200e_icdar2015.py',
+]
+
+load_from = None
+
+_base_.model.backbone = dict(
+    type='mmdet.ResNet',
+    depth=50,
+    num_stages=4,
+    out_indices=(0, 1, 2, 3),
+    frozen_stages=-1,
+    norm_cfg=dict(type='BN', requires_grad=True),
+    norm_eval=True,
+    style='pytorch',
+    init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'))
+
+_base_.train_dataloader.num_workers = 24
+_base_.optim_wrapper.optimizer.lr = 0.003
+
+param_scheduler = [
+    dict(type='LinearLR', end=200, start_factor=0.001),
+    dict(type='PolyLR', power=0.9, eta_min=1e-7, begin=200, end=1200),
+]
--- a/configs/textdet/drrg/drrg_resnet50-oclip_fpn-unet_1200e_ctw1500.py
+++ b/configs/textdet/drrg/drrg_resnet50-oclip_fpn-unet_1200e_ctw1500.py
@ -0,0 +1,17 @@
+_base_ = [
+    'drrg_resnet50_fpn-unet_1200e_ctw1500.py',
+]
+
+load_from = None
+
+_base_.model.backbone = dict(
+    type='CLIPResNet',
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))
+
+param_scheduler = [
+    dict(type='LinearLR', end=100, start_factor=0.001),
+    dict(type='PolyLR', power=0.9, eta_min=1e-7, begin=100, end=1200),
+]
--- a/configs/textdet/fcenet/fcenet_resnet50-oclip_fpn_1500e_ctw1500.py
+++ b/configs/textdet/fcenet/fcenet_resnet50-oclip_fpn_1500e_ctw1500.py
@ -0,0 +1,16 @@
+_base_ = [
+    'fcenet_resnet50-dcnv2_fpn_1500e_ctw1500.py',
+]
+
+load_from = None
+
+_base_.model.backbone = dict(
+    type='CLIPResNet',
+    out_indices=(1, 2, 3),
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))
+
+_base_.train_dataloader.num_workers = 24
+_base_.optim_wrapper.optimizer.lr = 0.0005
--- a/configs/textdet/fcenet/fcenet_resnet50-oclip_fpn_1500e_icdar2015.py
+++ b/configs/textdet/fcenet/fcenet_resnet50-oclip_fpn_1500e_icdar2015.py
@ -0,0 +1,16 @@
+_base_ = [
+    'fcenet_resnet50_fpn_1500e_icdar2015.py',
+]
+load_from = None
+
+_base_.model.backbone = dict(
+    type='CLIPResNet',
+    out_indices=(1, 2, 3),
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))
+
+_base_.train_dataloader.batch_size = 16
+_base_.train_dataloader.num_workers = 24
+_base_.optim_wrapper.optimizer.lr = 0.0005
--- a/configs/textdet/maskrcnn/mask-rcnn_resnet50-oclip_fpn_160e_ctw1500.py
+++ b/configs/textdet/maskrcnn/mask-rcnn_resnet50-oclip_fpn_160e_ctw1500.py
@ -0,0 +1,15 @@
+_base_ = [
+    'mask-rcnn_resnet50_fpn_160e_ctw1500.py',
+]
+
+load_from = None
+
+_base_.model.cfg.backbone = dict(
+    _scope_='mmocr',
+    type='CLIPResNet',
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))
+
+_base_.optim_wrapper.optimizer.lr = 0.02
--- a/configs/textdet/maskrcnn/mask-rcnn_resnet50-oclip_fpn_160e_icdar2015.py
+++ b/configs/textdet/maskrcnn/mask-rcnn_resnet50-oclip_fpn_160e_icdar2015.py
@ -0,0 +1,15 @@
+_base_ = [
+    'mask-rcnn_resnet50_fpn_160e_icdar2015.py',
+]
+
+load_from = None
+
+_base_.model.cfg.backbone = dict(
+    _scope_='mmocr',
+    type='CLIPResNet',
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))
+
+_base_.optim_wrapper.optimizer.lr = 0.02
--- a/configs/textdet/psenet/psenet_resnet50-oclip_fpnf_600e_ctw1500.py
+++ b/configs/textdet/psenet/psenet_resnet50-oclip_fpnf_600e_ctw1500.py
@ -0,0 +1,10 @@
+_base_ = [
+    'psenet_resnet50_fpnf_600e_ctw1500.py',
+]
+
+_base_.model.backbone = dict(
+    type='CLIPResNet',
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))
--- a/configs/textdet/psenet/psenet_resnet50-oclip_fpnf_600e_icdar2015.py
+++ b/configs/textdet/psenet/psenet_resnet50-oclip_fpnf_600e_icdar2015.py
@ -0,0 +1,10 @@
+_base_ = [
+    'psenet_resnet50_fpnf_600e_icdar2015.py',
+]
+
+_base_.model.backbone = dict(
+    type='CLIPResNet',
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))
--- a/configs/textdet/textsnake/textsnake_resnet50-oclip_fpn-unet_1200e_ctw1500.py
+++ b/configs/textdet/textsnake/textsnake_resnet50-oclip_fpn-unet_1200e_ctw1500.py
@ -0,0 +1,10 @@
+_base_ = [
+    'textsnake_resnet50_fpn-unet_1200e_ctw1500.py',
+]
+
+_base_.model.backbone = dict(
+    type='CLIPResNet',
+    init_cfg=dict(
+        type='Pretrained',
+        checkpoint='https://download.openmmlab.com/'
+        'mmocr/backbone/resnet50-oclip-7ba0c533.pth'))