| 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182 |
- _base_ = 'ssd300_voc0712.py'
- input_size = 512
- model = dict(
- neck=dict(
- out_channels=(512, 1024, 512, 256, 256, 256, 256),
- level_strides=(2, 2, 2, 2, 1),
- level_paddings=(1, 1, 1, 1, 1),
- last_kernel_size=4),
- bbox_head=dict(
- in_channels=(512, 1024, 512, 256, 256, 256, 256),
- anchor_generator=dict(
- input_size=input_size,
- strides=[8, 16, 32, 64, 128, 256, 512],
- basesize_ratio_range=(0.15, 0.9),
- ratios=([2], [2, 3], [2, 3], [2, 3], [2, 3], [2], [2]))))
- # dataset settings
- dataset_type = 'VOCDataset'
- data_root = 'data/VOCdevkit/'
- train_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='Expand',
- mean={{_base_.model.data_preprocessor.mean}},
- to_rgb={{_base_.model.data_preprocessor.bgr_to_rgb}},
- ratio_range=(1, 4)),
- dict(
- type='MinIoURandomCrop',
- min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
- min_crop_size=0.3),
- dict(type='Resize', scale=(input_size, input_size), keep_ratio=False),
- dict(type='RandomFlip', prob=0.5),
- dict(
- type='PhotoMetricDistortion',
- brightness_delta=32,
- contrast_range=(0.5, 1.5),
- saturation_range=(0.5, 1.5),
- hue_delta=18),
- dict(type='PackDetInputs')
- ]
- test_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(type='Resize', scale=(input_size, input_size), keep_ratio=False),
- # avoid bboxes being resized
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='PackDetInputs',
- meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
- 'scale_factor'))
- ]
- train_dataloader = dict(
- batch_size=8,
- num_workers=3,
- dataset=dict( # RepeatDataset
- # the dataset is repeated 10 times, and the training schedule is 2x,
- # so the actual epoch = 12 * 10 = 120.
- times=10,
- dataset=dict( # ConcatDataset
- # VOCDataset will add different `dataset_type` in dataset.metainfo,
- # which will get error if using ConcatDataset. Adding
- # `ignore_keys` can avoid this error.
- ignore_keys=['dataset_type'],
- datasets=[
- dict(
- type=dataset_type,
- data_root=data_root,
- ann_file='VOC2007/ImageSets/Main/trainval.txt',
- data_prefix=dict(sub_data_root='VOC2007/'),
- filter_cfg=dict(filter_empty_gt=True, min_size=32),
- pipeline=train_pipeline),
- dict(
- type=dataset_type,
- data_root=data_root,
- ann_file='VOC2012/ImageSets/Main/trainval.txt',
- data_prefix=dict(sub_data_root='VOC2012/'),
- filter_cfg=dict(filter_empty_gt=True, min_size=32),
- pipeline=train_pipeline)
- ])))
- val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
- test_dataloader = val_dataloader
|
