MQ-Det/configs/vision_query_5shot/lvis_val_groundingdino-T.yaml

74 lines
1.5 KiB
YAML

MODEL:
BACKBONE:
FREEZE_CONV_BODY_AT: -1
ATSS:
NUM_CLASSES: 8 # these fields are not used; just a placeholder
DETECTIONS_PER_IMG: 300
FCOS:
NUM_CLASSES: 8
DETECTIONS_PER_IMG: 300
ROI_BOX_HEAD:
NUM_CLASSES: 8
DYHEAD:
NUM_CLASSES: 8
RETINANET:
DETECTIONS_PER_IMG: 300
ROI_HEADS:
DETECTIONS_PER_IMG: 300
DYHEAD:
NUM_CLASSES: 1204
DATASETS:
REGISTER:
lvis_evaluation_mini_val:
img_dir: "coco"
ann_file: "coco/annotations/lvis_v1_minival_inserted_image_name.json"
lvis_evaluation_val:
img_dir: "coco"
ann_file: "coco/annotations/lvis_od_val.json"
TRAIN: ("lvis_grounding_train_for_obj365", )
TEST: ("lvis_evaluation_val",)
USE_OVERRIDE_CATEGORY: True
DISABLE_SHUFFLE: False
FEW_SHOT: 5
SOLVER:
STEPS: (0.67, 0.89)
BASE_LR: 0.00001
LANG_LR: 0.00001
GATE_LR: 0.0001
QUERY_LR: 0.00001
WEIGHT_DECAY: 0.05
WARMUP_ITERS: 20
USE_AUTOSTEP: True
TEST_WITH_INFERENCE: True
CHECKPOINT_PERIOD: 99999999
CHECKPOINT_PER_EPOCH: -1.0
INPUT:
MIN_SIZE_TRAIN: 800
MAX_SIZE_TRAIN: 1333
MIN_SIZE_TEST: 800
MAX_SIZE_TEST: 1333
DATALOADER:
SIZE_DIVISIBILITY: 32
ASPECT_RATIO_GROUPING: False
TEST:
IMS_PER_BATCH: 1
CHUNKED_EVALUATION: 40
MDETR_STYLE_AGGREGATE_CLASS_NUM: 3000
DURING_TRAINING: False
EVAL_TASK: detection
VISION_QUERY:
QUERY_BANK_PATH: 'MODEL/lvis_query_5_pool7_sel_groundingdino_tiny.pth'
VISION_SCALE: 1.0
PURE_TEXT_RATE: 0.
TEXT_DROPOUT: 0.
NUM_QUERY_PER_CLASS: 5
RANDOM_KSHOT: False