Spaces:
Runtime error
Runtime error
_BASE_: Base-YouTubeVIS-VideoInstanceSegmentation.yaml | |
MODEL: | |
WEIGHTS: "model_final_3c8ec9.pkl" | |
META_ARCHITECTURE: "VideoMaskFormer" | |
SEM_SEG_HEAD: | |
NAME: "MaskFormerHead" | |
IGNORE_VALUE: 255 | |
NUM_CLASSES: 40 | |
LOSS_WEIGHT: 1.0 | |
CONVS_DIM: 256 | |
MASK_DIM: 256 | |
NORM: "GN" | |
# pixel decoder | |
PIXEL_DECODER_NAME: "MSDeformAttnPixelDecoder" | |
IN_FEATURES: ["res2", "res3", "res4", "res5"] | |
DEFORMABLE_TRANSFORMER_ENCODER_IN_FEATURES: ["res3", "res4", "res5"] | |
COMMON_STRIDE: 4 | |
TRANSFORMER_ENC_LAYERS: 6 | |
MASK_FORMER: | |
TRANSFORMER_DECODER_NAME: "VideoMultiScaleMaskedTransformerDecoder" | |
TRANSFORMER_IN_FEATURE: "multi_scale_pixel_decoder" | |
DEEP_SUPERVISION: True | |
NO_OBJECT_WEIGHT: 0.1 | |
CLASS_WEIGHT: 2.0 | |
MASK_WEIGHT: 5.0 | |
DICE_WEIGHT: 5.0 | |
HIDDEN_DIM: 256 | |
NUM_OBJECT_QUERIES: 100 | |
NHEADS: 8 | |
DROPOUT: 0.0 | |
DIM_FEEDFORWARD: 2048 | |
ENC_LAYERS: 0 | |
PRE_NORM: False | |
ENFORCE_INPUT_PROJ: False | |
SIZE_DIVISIBILITY: 32 | |
DEC_LAYERS: 10 # 9 decoder layers, add one for the loss on learnable query | |
TRAIN_NUM_POINTS: 12544 | |
OVERSAMPLE_RATIO: 3.0 | |
IMPORTANCE_SAMPLE_RATIO: 0.75 | |
TEST: | |
SEMANTIC_ON: False | |
INSTANCE_ON: True | |
PANOPTIC_ON: False | |
OVERLAP_THRESHOLD: 0.8 | |
OBJECT_MASK_THRESHOLD: 0.8 | |