IDM-VTON-demo2 / configs /cse /Base-DensePose-RCNN-FPN.yaml
IDM-VTON
update IDM-VTON Demo
938e515
VERSION: 2
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
BACKBONE:
NAME: "build_resnet_fpn_backbone"
RESNETS:
OUT_FEATURES: ["res2", "res3", "res4", "res5"]
FPN:
IN_FEATURES: ["res2", "res3", "res4", "res5"]
ANCHOR_GENERATOR:
SIZES: [[32], [64], [128], [256], [512]] # One size for each in feature map
ASPECT_RATIOS: [[0.5, 1.0, 2.0]] # Three aspect ratios (same for all in feature maps)
RPN:
IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
PRE_NMS_TOPK_TRAIN: 2000 # Per FPN level
PRE_NMS_TOPK_TEST: 1000 # Per FPN level
# Detectron1 uses 2000 proposals per-batch,
# (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
# which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
POST_NMS_TOPK_TRAIN: 1000
POST_NMS_TOPK_TEST: 1000
DENSEPOSE_ON: True
ROI_HEADS:
NAME: "DensePoseROIHeads"
IN_FEATURES: ["p2", "p3", "p4", "p5"]
NUM_CLASSES: 1
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_FC: 2
POOLER_RESOLUTION: 7
POOLER_SAMPLING_RATIO: 2
POOLER_TYPE: "ROIAlign"
ROI_DENSEPOSE_HEAD:
NAME: "DensePoseV1ConvXHead"
POOLER_TYPE: "ROIAlign"
NUM_COARSE_SEGM_CHANNELS: 2
PREDICTOR_NAME: "DensePoseEmbeddingPredictor"
LOSS_NAME: "DensePoseCseLoss"
CSE:
# embedding loss, possible values:
# - "EmbeddingLoss"
# - "SoftEmbeddingLoss"
EMBED_LOSS_NAME: "EmbeddingLoss"
SOLVER:
IMS_PER_BATCH: 16
BASE_LR: 0.01
STEPS: (60000, 80000)
MAX_ITER: 90000
WARMUP_FACTOR: 0.1
CLIP_GRADIENTS:
CLIP_TYPE: norm
CLIP_VALUE: 1.0
ENABLED: true
NORM_TYPE: 2.0
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
DENSEPOSE_EVALUATION:
TYPE: cse
STORAGE: file