mirror of
https://github.com/alibaba/EasyCV.git
synced 2025-06-03 14:49:00 +08:00
9f01a37ad4
1. The vitdet backbone implemented by d2 is about 20% faster than the vitdet backbone originally reproduced by easycv. 2. 50.57 -> 50.65
118 lines
4.0 KiB
Python
118 lines
4.0 KiB
Python
CLASSES = [
|
|
'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train',
|
|
'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign',
|
|
'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
|
|
'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag',
|
|
'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite',
|
|
'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
|
|
'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon',
|
|
'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
|
|
'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant',
|
|
'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
|
|
'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
|
|
'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
|
|
'hair drier', 'toothbrush'
|
|
]
|
|
|
|
# dataset settings
|
|
data_root = 'data/coco/'
|
|
img_norm_cfg = dict(
|
|
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
|
|
|
|
image_size = (1024, 1024)
|
|
train_pipeline = [
|
|
# large scale jittering
|
|
dict(
|
|
type='MMResize',
|
|
img_scale=image_size,
|
|
ratio_range=(0.1, 2.0),
|
|
multiscale_mode='range',
|
|
keep_ratio=True),
|
|
dict(
|
|
type='MMRandomCrop',
|
|
crop_type='absolute_range',
|
|
crop_size=image_size,
|
|
recompute_bbox=False,
|
|
allow_negative_crop=True),
|
|
dict(type='MMFilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
|
|
dict(type='MMRandomFlip', flip_ratio=0.5),
|
|
dict(type='MMNormalize', **img_norm_cfg),
|
|
dict(type='MMPad', size=image_size),
|
|
dict(type='DefaultFormatBundle'),
|
|
dict(
|
|
type='Collect',
|
|
keys=['img', 'gt_bboxes', 'gt_labels'],
|
|
meta_keys=('filename', 'ori_filename', 'ori_shape', 'ori_img_shape',
|
|
'img_shape', 'pad_shape', 'scale_factor', 'flip',
|
|
'flip_direction', 'img_norm_cfg'))
|
|
]
|
|
test_pipeline = [
|
|
dict(
|
|
type='MMMultiScaleFlipAug',
|
|
img_scale=image_size,
|
|
flip=False,
|
|
transforms=[
|
|
dict(type='MMResize', keep_ratio=True),
|
|
dict(type='MMRandomFlip'),
|
|
dict(type='MMNormalize', **img_norm_cfg),
|
|
dict(type='MMPad', size_divisor=1024),
|
|
dict(type='ImageToTensor', keys=['img']),
|
|
dict(
|
|
type='Collect',
|
|
keys=['img'],
|
|
meta_keys=('filename', 'ori_filename', 'ori_shape',
|
|
'ori_img_shape', 'img_shape', 'pad_shape',
|
|
'scale_factor', 'flip', 'flip_direction',
|
|
'img_norm_cfg'))
|
|
])
|
|
]
|
|
|
|
train_dataset = dict(
|
|
type='DetDataset',
|
|
data_source=dict(
|
|
type='DetSourceCoco',
|
|
ann_file=data_root + 'annotations/instances_train2017.json',
|
|
img_prefix=data_root + 'train2017/',
|
|
pipeline=[
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='LoadAnnotations', with_bbox=True)
|
|
],
|
|
classes=CLASSES,
|
|
test_mode=False,
|
|
filter_empty_gt=True,
|
|
iscrowd=False),
|
|
pipeline=train_pipeline)
|
|
|
|
val_dataset = dict(
|
|
type='DetDataset',
|
|
imgs_per_gpu=1,
|
|
data_source=dict(
|
|
type='DetSourceCoco',
|
|
ann_file=data_root + 'annotations/instances_val2017.json',
|
|
img_prefix=data_root + 'val2017/',
|
|
pipeline=[
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='LoadAnnotations', with_bbox=True)
|
|
],
|
|
classes=CLASSES,
|
|
test_mode=True,
|
|
filter_empty_gt=False,
|
|
iscrowd=True),
|
|
pipeline=test_pipeline)
|
|
|
|
data = dict(
|
|
imgs_per_gpu=4, workers_per_gpu=2, train=train_dataset, val=val_dataset
|
|
) # 64(total batch size) = 4 (batch size/per gpu) x 8 (gpu num) x 2(node)
|
|
|
|
# evaluation
|
|
eval_config = dict(initial=False, interval=1, gpu_collect=False)
|
|
eval_pipelines = [
|
|
dict(
|
|
mode='test',
|
|
# dist_eval=True,
|
|
evaluators=[
|
|
dict(type='CocoDetectionEvaluator', classes=CLASSES),
|
|
],
|
|
)
|
|
]
|