test

Author: qilei123

configs/apps/trans_drone/full_segformer_mit-b5_640x640_160k_td.py

@@ -126,7 +126,7 @@
     power=1.0,
     min_lr=0.0,
     by_epoch=False)
-runner = dict(type='IterBasedRunner', max_iters=10000)
-checkpoint_config = dict(by_epoch=False, interval=1000)
-evaluation = dict(interval=1000, metric='mIoU', pre_eval=True)
+runner = dict(type='IterBasedRunner', max_iters=40000)
+checkpoint_config = dict(by_epoch=False, interval=4000)
+evaluation = dict(interval=4000, metric='mIoU', pre_eval=True)
 work_dir = data_root+'work_dirs/full_segformer_mit-b5_640x640_160k_td_nbg_640/'

configs/apps/trans_drone/full_segformer_mit-b5_640x640_160k_td_960.py

@@ -0,0 +1,132 @@
+from PIL.Image import TRANSPOSE
+
+
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+num_classes = 3
+dataset_type = 'TDDataset'
+data_root = 'data/td/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+#crop_size = (640, 640)
+#img_scale = (2048, 640)
+img_scale = (960, 540)
+#img_scale = (640, 640)
+keep_ratio = True
+model = dict(
+    type='EncoderDecoder',
+    pretrained='pretrain/mit_b5.pth',
+    backbone=dict(
+        type='MixVisionTransformer',
+        in_channels=3,
+        embed_dims=64,
+        num_stages=4,
+        num_layers=[3, 6, 40, 3],
+        num_heads=[1, 2, 5, 8],
+        patch_sizes=[7, 3, 3, 3],
+        sr_ratios=[8, 4, 2, 1],
+        out_indices=(0, 1, 2, 3),
+        mlp_ratio=4,
+        qkv_bias=True,
+        drop_rate=0.0,
+        attn_drop_rate=0.0,
+        drop_path_rate=0.1),
+    decode_head=dict(
+        type='SegformerHead',
+        in_channels=[64, 128, 320, 512],
+        in_index=[0, 1, 2, 3],
+        channels=256,
+        dropout_ratio=0.1,
+        num_classes=num_classes,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(type='Resize', img_scale=img_scale, keep_ratio=keep_ratio),
+    #dict(type='RandomCrop', crop_size=(640, 640), cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    #dict(type='Pad', size=(640, 640), pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale,
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=keep_ratio),
+            dict(type='RandomFlip'),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=1,
+    workers_per_gpu=1,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images',
+        ann_dir='annotations/train_AW.json',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images',
+        ann_dir='annotations/test_AW.json',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images',
+        ann_dir='annotations/test_AW.json',
+        pipeline=test_pipeline))
+log_config = dict(
+    interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+cudnn_benchmark = True
+optimizer = dict(
+    type='AdamW',
+    lr=6e-06,
+    betas=(0.9, 0.999),
+    weight_decay=0.01,
+    paramwise_cfg=dict(
+        custom_keys=dict(
+            pos_block=dict(decay_mult=0.0),
+            norm=dict(decay_mult=0.0),
+            head=dict(lr_mult=10.0))))
+optimizer_config = dict()
+lr_config = dict(
+    policy='poly',
+    warmup='linear',
+    warmup_iters=3200,
+    warmup_ratio=1e-06,
+    power=1.0,
+    min_lr=0.0,
+    by_epoch=False)
+runner = dict(type='IterBasedRunner', max_iters=40000)
+checkpoint_config = dict(by_epoch=False, interval=4000)
+evaluation = dict(interval=4000, metric='mIoU', pre_eval=True)
+work_dir = data_root+'work_dirs/full_segformer_mit-b5_640x640_160k_td_nbg_960/'