Upload 10 files

TTP/distill/best_mIoU_epoch_62.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da4157232f82dd7b508bebb25b9bbfc5a3afa5ee1b22c0fa05e34f5e9dbd779
+size 5657329713

TTP/distill/config.py

@@ -0,0 +1,85 @@
+_base_ = [
+    '/home/liuziyuan/proj/rmcd-kd/configs/_base_/models/KD-ttp_vit-sam-l.py', 
+    '/home/liuziyuan/proj/rmcd-kd/configs/common/standard_512x512_300e_cgwx.py']
+
+dataset_type = 'LEVIR_CD_Dataset'
+data_root = '/nas/datasets/lzy/RS-ChangeDetection/CGWX'
+
+crop_size = (512, 512)
+
+checkpoint_student = '/nas/datasets/lzy/RS-ChangeDetection/checkpoints_distill/TTP/teacher_ckpt/initial/best_mIoU_epoch_110.pth'
+checkpoint_teacher_l = '/nas/datasets/lzy/RS-ChangeDetection/checkpoints_distill/TTP/teacher_ckpt/large/best_mIoU_epoch_90.pth'
+checkpoint_teacher_m = '/nas/datasets/lzy/RS-ChangeDetection/checkpoints_distill/TTP/teacher_ckpt/medium/best_mIoU_epoch_100.pth'
+checkpoint_teacher_s = '/nas/datasets/lzy/RS-ChangeDetection/checkpoints_distill/TTP/teacher_ckpt/small/best_mIoU_epoch_115.pth'
+
+model = dict(
+    # student
+    init_cfg=dict(type='Pretrained', checkpoint=checkpoint_student),
+    # teacher large    
+    init_cfg_t_l = dict(type='Pretrained', checkpoint=checkpoint_teacher_l),
+    # teacher medium    
+    init_cfg_t_m = dict(type='Pretrained', checkpoint=checkpoint_teacher_m),
+    # teacher small    
+    init_cfg_t_s = dict(type='Pretrained', checkpoint=checkpoint_teacher_s),
+    
+    backbone=dict(
+        encoder_cfg=dict(img_size=crop_size)),
+        test_cfg=dict(mode='slide', crop_size=crop_size, stride=(crop_size[0]//2, crop_size[1]//2)))
+
+train_pipeline = [
+    dict(type='MultiImgLoadImageFromFile'),
+    dict(type='MultiImgLoadAnnotations'),
+    dict(type='MultiImgRandomRotate', prob=0.5, degree=180),
+    dict(type='MultiImgRandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='vertical'),
+    # dict(type='MultiImgExchangeTime', prob=0.5),
+    dict(
+        type='MultiImgPhotoMetricDistortion',
+        brightness_delta=10,
+        contrast_range=(0.8, 1.2),
+        saturation_range=(0.8, 1.2),
+        hue_delta=10),
+    dict(type='MultiImgPackSegInputs')
+]
+
+# By default, models are trained on 8 GPUs with 2 images per GPU
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=4,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(pipeline=train_pipeline))
+
+# optimizer
+max_epochs = 100
+
+optim_wrapper = dict(
+    _delete_=True,
+    type='OptimWrapper',
+    optimizer=dict(
+        type='AdamW', lr=0.0004, betas=(0.9, 0.999), weight_decay=0.05))
+
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=1e-4, by_epoch=True, begin=0, end=5, convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=max_epochs,
+        begin=5,
+        by_epoch=True,
+        end=max_epochs,
+        convert_to_iter_based=True
+    ),
+]
+
+test_pipeline = [
+    dict(type='MultiImgLoadImageFromFile'),
+    dict(type='MultiImgResize', scale=(512, 512), keep_ratio=True),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='MultiImgLoadAnnotations'),
+    dict(type='MultiImgPackSegInputs')
+]
+
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=2)
+default_hooks = dict(checkpoint=dict(interval=2))

TTP/initial/best_mIoU_epoch_110.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a48ae1689ea33d9800e12d7004c79e7f532ab772027b2aa7f5c978b77be595
+size 1419294427

TTP/initial/config.py

@@ -0,0 +1,59 @@
+_base_ = [
+    '/home/liuziyuan/proj/RS-CD/rs-cd-cgwx/configs/_base_/models/ttp_vit-sam-l.py', 
+    '/home/liuziyuan/proj/RS-CD/rs-cd-cgwx/configs/common/standard_512x512_300e_cgwx.py']
+
+crop_size = (512, 512)
+
+model = dict(
+    backbone=dict(
+        encoder_cfg=dict(img_size=crop_size)),
+        test_cfg=dict(mode='slide', crop_size=crop_size, stride=(crop_size[0]//2, crop_size[1]//2)))
+
+train_pipeline = [
+    dict(type='MultiImgLoadImageFromFile'),
+    dict(type='MultiImgLoadAnnotations'),
+    dict(type='MultiImgRandomRotate', prob=0.5, degree=180),
+    dict(type='MultiImgRandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='vertical'),
+    # dict(type='MultiImgExchangeTime', prob=0.5),
+    dict(
+        type='MultiImgPhotoMetricDistortion',
+        brightness_delta=10,
+        contrast_range=(0.8, 1.2),
+        saturation_range=(0.8, 1.2),
+        hue_delta=10),
+    dict(type='MultiImgPackSegInputs')
+]
+
+# By default, models are trained on 8 GPUs with 2 images per GPU
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=4,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(pipeline=train_pipeline))
+
+# optimizer
+max_epochs = 300
+
+optim_wrapper = dict(
+    _delete_=True,
+    type='OptimWrapper',
+    optimizer=dict(
+        type='AdamW', lr=0.0004, betas=(0.9, 0.999), weight_decay=0.05))
+
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=1e-4, by_epoch=True, begin=0, end=5, convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=max_epochs,
+        begin=5,
+        by_epoch=True,
+        end=max_epochs,
+        convert_to_iter_based=True
+    ),
+]
+
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=5)
+default_hooks = dict(checkpoint=dict(interval=5))

TTP/large/best_mIoU_epoch_90.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3ea21ad14e349de399594f0e79f7e050b52fd4927632c86679a7f3e8024b96
+size 1414011867

TTP/large/config.py

@@ -0,0 +1,59 @@
+_base_ = [
+    '/home/liuziyuan/proj/RS-CD/rs-cd-cgwx/configs/_base_/models/ttp_vit-sam-l.py', 
+    '/home/liuziyuan/proj/RS-CD/rs-cd-cgwx/configs/common/train_large_512x512_200e_cgwx.py']
+
+crop_size = (512, 512)
+
+model = dict(
+    backbone=dict(
+        encoder_cfg=dict(img_size=crop_size)),
+        test_cfg=dict(mode='slide', crop_size=crop_size, stride=(crop_size[0]//2, crop_size[1]//2)))
+
+train_pipeline = [
+    dict(type='MultiImgLoadImageFromFile'),
+    dict(type='MultiImgLoadAnnotations'),
+    dict(type='MultiImgRandomRotate', prob=0.5, degree=180),
+    dict(type='MultiImgRandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='vertical'),
+    # dict(type='MultiImgExchangeTime', prob=0.5),
+    dict(
+        type='MultiImgPhotoMetricDistortion',
+        brightness_delta=10,
+        contrast_range=(0.8, 1.2),
+        saturation_range=(0.8, 1.2),
+        hue_delta=10),
+    dict(type='MultiImgPackSegInputs')
+]
+
+# By default, models are trained on 8 GPUs with 2 images per GPU
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=4,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(pipeline=train_pipeline))
+
+# optimizer
+max_epochs = 200
+
+optim_wrapper = dict(
+    _delete_=True,
+    type='OptimWrapper',
+    optimizer=dict(
+        type='AdamW', lr=0.0004, betas=(0.9, 0.999), weight_decay=0.05))
+
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=1e-4, by_epoch=True, begin=0, end=5, convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=max_epochs,
+        begin=5,
+        by_epoch=True,
+        end=max_epochs,
+        convert_to_iter_based=True
+    ),
+]
+
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=5)
+default_hooks = dict(checkpoint=dict(interval=5))

TTP/medium/best_mIoU_epoch_100.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e361691e7fee59bdfe990f8392b35959c432c3350d5c419a7bd6900f3be341
+size 1414948827

TTP/medium/config.py

@@ -0,0 +1,59 @@
+_base_ = [
+    '/home/liuziyuan/proj/RS-CD/rs-cd-cgwx/configs/_base_/models/ttp_vit-sam-l.py', 
+    '/home/liuziyuan/proj/RS-CD/rs-cd-cgwx/configs/common/train_medium_512x512_200e_cgwx.py']
+
+crop_size = (512, 512)
+
+model = dict(
+    backbone=dict(
+        encoder_cfg=dict(img_size=crop_size)),
+        test_cfg=dict(mode='slide', crop_size=crop_size, stride=(crop_size[0]//2, crop_size[1]//2)))
+
+train_pipeline = [
+    dict(type='MultiImgLoadImageFromFile'),
+    dict(type='MultiImgLoadAnnotations'),
+    dict(type='MultiImgRandomRotate', prob=0.5, degree=180),
+    dict(type='MultiImgRandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='vertical'),
+    # dict(type='MultiImgExchangeTime', prob=0.5),
+    dict(
+        type='MultiImgPhotoMetricDistortion',
+        brightness_delta=10,
+        contrast_range=(0.8, 1.2),
+        saturation_range=(0.8, 1.2),
+        hue_delta=10),
+    dict(type='MultiImgPackSegInputs')
+]
+
+# By default, models are trained on 8 GPUs with 2 images per GPU
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=4,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(pipeline=train_pipeline))
+
+# optimizer
+max_epochs = 200
+
+optim_wrapper = dict(
+    _delete_=True,
+    type='OptimWrapper',
+    optimizer=dict(
+        type='AdamW', lr=0.0004, betas=(0.9, 0.999), weight_decay=0.05))
+
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=1e-4, by_epoch=True, begin=0, end=5, convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=max_epochs,
+        begin=5,
+        by_epoch=True,
+        end=max_epochs,
+        convert_to_iter_based=True
+    ),
+]
+
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=5)
+default_hooks = dict(checkpoint=dict(interval=5))

TTP/small/best_mIoU_epoch_115.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38e2f33063a4e4cb57cf37e50d648f7606063efdcde67bb36eaa702b6bb0016
+size 1417865883

TTP/small/config.py

@@ -0,0 +1,59 @@
+_base_ = [
+    '/home/liuziyuan/proj/RS-CD/rs-cd-cgwx/configs/_base_/models/ttp_vit-sam-l.py', 
+    '/home/liuziyuan/proj/RS-CD/rs-cd-cgwx/configs/common/train_small_512x512_200e_cgwx.py']
+
+crop_size = (512, 512)
+
+model = dict(
+    backbone=dict(
+        encoder_cfg=dict(img_size=crop_size)),
+        test_cfg=dict(mode='slide', crop_size=crop_size, stride=(crop_size[0]//2, crop_size[1]//2)))
+
+train_pipeline = [
+    dict(type='MultiImgLoadImageFromFile'),
+    dict(type='MultiImgLoadAnnotations'),
+    dict(type='MultiImgRandomRotate', prob=0.5, degree=180),
+    dict(type='MultiImgRandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='MultiImgRandomFlip', prob=0.5, direction='vertical'),
+    # dict(type='MultiImgExchangeTime', prob=0.5),
+    dict(
+        type='MultiImgPhotoMetricDistortion',
+        brightness_delta=10,
+        contrast_range=(0.8, 1.2),
+        saturation_range=(0.8, 1.2),
+        hue_delta=10),
+    dict(type='MultiImgPackSegInputs')
+]
+
+# By default, models are trained on 8 GPUs with 2 images per GPU
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=4,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(pipeline=train_pipeline))
+
+# optimizer
+max_epochs = 200
+
+optim_wrapper = dict(
+    _delete_=True,
+    type='OptimWrapper',
+    optimizer=dict(
+        type='AdamW', lr=0.0004, betas=(0.9, 0.999), weight_decay=0.05))
+
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=1e-4, by_epoch=True, begin=0, end=5, convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=max_epochs,
+        begin=5,
+        by_epoch=True,
+        end=max_epochs,
+        convert_to_iter_based=True
+    ),
+]
+
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=5)
+default_hooks = dict(checkpoint=dict(interval=5))