|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
|
- train_dataset_params:
- data_dir: /data/coco # root path to coco data
- subdir: images/train2017 # sub directory path of data_dir containing the train data.
- json_file: instances_train2017.json # path to coco train json file, data_dir/annotations/train_json_file.
- input_dim: [640, 640]
- cache_dir:
- cache: False
- transforms:
- - DetectionMosaic:
- input_dim: ${dataset_params.train_dataset_params.input_dim}
- prob: 1.
- - DetectionRandomAffine:
- degrees: 10. # rotation degrees, randomly sampled from [-degrees, degrees]
- translate: 0.1 # image translation fraction
- scales: [ 0.1, 2 ] # random rescale range (keeps size by padding/cropping) after mosaic transform.
- shear: 2.0 # shear degrees, randomly sampled from [-degrees, degrees]
- target_size: ${dataset_params.train_dataset_params.input_dim}
- filter_box_candidates: True # whether to filter out transformed bboxes by edge size, area ratio, and aspect ratio.
- wh_thr: 2 # edge size threshold when filter_box_candidates = True (pixels)
- area_thr: 0.1 # threshold for area ratio between original image and the transformed one, when when filter_box_candidates = True
- ar_thr: 20 # aspect ratio threshold when filter_box_candidates = True
- - DetectionMixup:
- input_dim: ${dataset_params.train_dataset_params.input_dim}
- mixup_scale: [ 0.5, 1.5 ] # random rescale range for the additional sample in mixup
- prob: 1.0 # probability to apply per-sample mixup
- flip_prob: 0.5 # probability to apply horizontal flip
- - DetectionHSV:
- prob: 1.0 # probability to apply HSV transform
- hgain: 5 # HSV transform hue gain (randomly sampled from [-hgain, hgain])
- sgain: 30 # HSV transform saturation gain (randomly sampled from [-sgain, sgain])
- vgain: 30 # HSV transform value gain (randomly sampled from [-vgain, vgain])
- - DetectionHorizontalFlip:
- prob: 0.5 # probability to apply horizontal flip
- - DetectionPaddedRescale:
- input_dim: ${dataset_params.train_dataset_params.input_dim}
- max_targets: 120
- - DetectionTargetsFormatTransform:
- output_format:
- _target_: super_gradients.training.utils.detection_utils.DetectionTargetsFormat # targets format
- value: LABEL_CXCYWH
- tight_box_rotation: False
- class_inclusion_list:
- max_num_samples:
- with_crowd: False
- train_dataloader_params:
- shuffle: True
- batch_size: 16
- num_workers: 8
- batch_sampler: True
- sampler:
- InfiniteSampler:
- seed: 0
- drop_last: False
- pin_memory: True
- worker_init_fn:
- _target_: super_gradients.training.utils.utils.load_func
- dotpath: super_gradients.training.datasets.datasets_utils.worker_init_reset_seed
- collate_fn: # collate function for trainset
- _target_: super_gradients.training.utils.detection_utils.DetectionCollateFN
- val_dataset_params:
- data_dir: /data/coco # root path to coco data
- subdir: images/val2017 # sub directory path of data_dir containing the train data.
- json_file: instances_val2017.json # path to coco train json file, data_dir/annotations/train_json_file.
- input_dim: [640, 640]
- cache_dir:
- cache: False
- transforms:
- - DetectionPaddedRescale:
- input_dim: ${dataset_params.val_dataset_params.input_dim}
- - DetectionTargetsFormatTransform:
- max_targets: 50
- output_format:
- _target_: super_gradients.training.utils.detection_utils.DetectionTargetsFormat # targets format
- value: LABEL_CXCYWH
- tight_box_rotation: False
- class_inclusion_list:
- max_num_samples:
- with_crowd: False
- val_dataloader_params:
- batch_size: 64
- num_workers: 8
- drop_last: False
- pin_memory: True
- collate_fn: # collate function for trainset
- _target_: super_gradients.training.utils.detection_utils.DetectionCollateFN
- _convert_: all
|
Connect to our Discord channel
Models
Annotations