mirror of https://github.com/YifanXu74/MQ-Det.git
114 lines
2.4 KiB
YAML
114 lines
2.4 KiB
YAML
MODEL:
|
|
WEIGHT: "MODEL/groundingdino_swint_ogc.pth"
|
|
|
|
BACKBONE:
|
|
OUT_CHANNELS: 256
|
|
|
|
LANGUAGE_BACKBONE:
|
|
FREEZE: False
|
|
TOKENIZER_TYPE: "bert-base-uncased"
|
|
MODEL_TYPE: "bert-base-uncased" # "roberta-base", "clip"
|
|
# TOKENIZER_TYPE: "MODEL/THIRD_PARTIES/bert-base-uncased"
|
|
# MODEL_TYPE: "MODEL/THIRD_PARTIES/bert-base-uncased" # "roberta-base", "clip"
|
|
MASK_SPECIAL: False
|
|
|
|
ROI_BOX_HEAD:
|
|
POOLER_RESOLUTION: 7
|
|
POOLER_SCALES: (0.125, 0.0625, 0.03125, 0.015625)
|
|
POOLER_SAMPLING_RATIO: 0
|
|
|
|
|
|
TEST:
|
|
EVAL_TASK: 'detection'
|
|
DURING_TRAINING: False
|
|
IMS_PER_BATCH: 8
|
|
|
|
# use for grounding model
|
|
DATASETS:
|
|
TRAIN: ("object365_grounding_train", )
|
|
TEST: ("coco_2017_val", )
|
|
DISABLE_SHUFFLE: False
|
|
ADD_DET_PROMPT: False
|
|
RANDOM_SAMPLE_NEG: 85
|
|
# RANDOM_SAMPLE_NEG: 365
|
|
CONTROL_PROB: (0.0, 0.0, 0.5, 0.0)
|
|
|
|
SEPARATION_TOKENS: ". "
|
|
|
|
EXCLUDE_CROWD: True
|
|
SPECIAL_SAFEGUARD_FOR_COCO_GROUNDING: True
|
|
SEP_AT_LAST: True
|
|
ADD_NORMED_CXCY: True
|
|
|
|
INPUT:
|
|
FORMAT: 'rgb'
|
|
PIXEL_MEAN: [0.485, 0.456, 0.406]
|
|
PIXEL_STD: [0.229, 0.224, 0.225]
|
|
MIN_SIZE_TRAIN: 800
|
|
MAX_SIZE_TRAIN: 1333
|
|
MIN_SIZE_TEST: 800
|
|
MAX_SIZE_TEST: 1333
|
|
|
|
AUGMENT:
|
|
MULT_MIN_SIZE_TRAIN: (480,560,640,720,800)
|
|
|
|
DATALOADER:
|
|
SIZE_DIVISIBILITY: 32
|
|
NUM_WORKERS: 0
|
|
|
|
SOLVER:
|
|
OPTIMIZER: ADAMW
|
|
BASE_LR: 0.0001
|
|
#### should be modified during fine-tuning #######
|
|
GATE_LR: 0.005
|
|
QUERY_LR: 0.00001
|
|
#################################################
|
|
LANG_LR: 0.00001
|
|
WEIGHT_DECAY: 0.0001
|
|
# STEPS: (0.67, 0.89)
|
|
STEPS: (0.95,)
|
|
# MAX_EPOCH: 10
|
|
MAX_EPOCH: 1
|
|
IMS_PER_BATCH: 16
|
|
WARMUP_ITERS: 2000
|
|
WARMUP_FACTOR: 0.001
|
|
USE_AMP: True
|
|
MODEL_EMA: 0.999
|
|
FIND_UNUSED_PARAMETERS: False
|
|
CHECKPOINT_PERIOD: 99999999
|
|
CHECKPOINT_PER_EPOCH: 2.0
|
|
# TUNING_HIGHLEVEL_OVERRIDE: "vision_query"
|
|
TUNING_HIGHLEVEL_OVERRIDE: "vision_query"
|
|
MAX_TO_KEEP: 4
|
|
|
|
|
|
CLIP_GRADIENTS:
|
|
ENABLED: True
|
|
CLIP_TYPE: "full_model"
|
|
CLIP_VALUE: 1.0
|
|
# CLIP_VALUE: 0.1
|
|
NORM_TYPE: 2.0
|
|
|
|
VISION_QUERY:
|
|
ENABLED: True
|
|
QUERY_BANK_PATH: 'MODEL/object365_query_5000_pool7_sel_gd.pth'
|
|
PURE_TEXT_RATE: 0.
|
|
TEXT_DROPOUT: 0.4
|
|
VISION_SCALE: 1.0
|
|
NUM_QUERY_PER_CLASS: 5
|
|
RANDOM_KSHOT: False
|
|
ADD_ADAPT_LAYER: False
|
|
CONDITION_GATE: True
|
|
NONLINEAR_GATE: True
|
|
NO_CAT: True
|
|
QUERY_ADDITION_NAME: '_groundingdino-T'
|
|
|
|
GROUNDINGDINO:
|
|
enabled: True
|
|
use_checkpoint: False
|
|
use_transformer_ckpt: False
|
|
text_encoder_type: 'bert-base-uncased'
|
|
box_threshold: 0.05
|
|
|
|
|