ControlNet-v1-1-Annotators-cpu / annotator /oneformer /configs /ade20k /Base-ADE20K-UnifiedSegmentation.yaml
atatakun's picture
Duplicate from atatakun/testapp2
18dd6ad
raw
history blame
1.68 kB
MODEL:
BACKBONE:
FREEZE_AT: 0
NAME: "build_resnet_backbone"
WEIGHTS: "detectron2://ImageNetPretrained/torchvision/R-50.pkl"
PIXEL_MEAN: [123.675, 116.280, 103.530]
PIXEL_STD: [58.395, 57.120, 57.375]
RESNETS:
DEPTH: 50
STEM_TYPE: "basic" # not used
STEM_OUT_CHANNELS: 64
STRIDE_IN_1X1: False
OUT_FEATURES: ["res2", "res3", "res4", "res5"]
# NORM: "SyncBN"
RES5_MULTI_GRID: [1, 1, 1] # not used
DATASETS:
TRAIN: ("ade20k_panoptic_train",)
TEST_PANOPTIC: ("ade20k_panoptic_val",)
TEST_INSTANCE: ("ade20k_instance_val",)
TEST_SEMANTIC: ("ade20k_sem_seg_val",)
SOLVER:
IMS_PER_BATCH: 16
BASE_LR: 0.0001
MAX_ITER: 160000
WARMUP_FACTOR: 1.0
WARMUP_ITERS: 0
WEIGHT_DECAY: 0.05
OPTIMIZER: "ADAMW"
LR_SCHEDULER_NAME: "WarmupPolyLR"
BACKBONE_MULTIPLIER: 0.1
CLIP_GRADIENTS:
ENABLED: True
CLIP_TYPE: "full_model"
CLIP_VALUE: 0.01
NORM_TYPE: 2.0
AMP:
ENABLED: True
INPUT:
MIN_SIZE_TRAIN: !!python/object/apply:eval ["[int(x * 0.1 * 512) for x in range(5, 21)]"]
MIN_SIZE_TRAIN_SAMPLING: "choice"
MIN_SIZE_TEST: 512
MAX_SIZE_TRAIN: 2048
MAX_SIZE_TEST: 2048
CROP:
ENABLED: True
TYPE: "absolute"
SIZE: (512, 512)
SINGLE_CATEGORY_MAX_AREA: 1.0
COLOR_AUG_SSD: True
SIZE_DIVISIBILITY: 512 # used in dataset mapper
FORMAT: "RGB"
DATASET_MAPPER_NAME: "oneformer_unified"
MAX_SEQ_LEN: 77
TASK_SEQ_LEN: 77
TASK_PROB:
SEMANTIC: 0.33
INSTANCE: 0.66
TEST:
EVAL_PERIOD: 5000
AUG:
ENABLED: False
MIN_SIZES: [256, 384, 512, 640, 768, 896]
MAX_SIZE: 3584
FLIP: True
DATALOADER:
FILTER_EMPTY_ANNOTATIONS: True
NUM_WORKERS: 4
VERSION: 2