virtex-redcaps / virtex /configs /detectron2 /_base_mask_rcnn_R_50_FPN.yaml
zamborg's picture
added datasets and virtex
a5f8a35
raw history blame
No virus
2.05 kB
# ----------------------------------------------------------------------------
# Train a Mask R-CNN with ResNet-50 and FPN backbone. This config follows
# Detectron2 format; and is unrelated with our VirTex configs. Params here
# replicate evaluation protocol as per MoCo (https://arxiv.org/abs/1911.05722).
# ----------------------------------------------------------------------------
INPUT:
# Input format will always be RGB, consistent with torchvision.
FORMAT: "RGB"
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
MIN_SIZE_TEST: 800
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
# Train all layers end-to-end by default.
BACKBONE:
NAME: "build_resnet_fpn_backbone"
FREEZE_AT: 0
# Fine-tune with SyncBN.
# STRIDE_IN_1X1 is False for torchvision-like models.
RESNETS:
DEPTH: 50
NORM: "SyncBN"
STRIDE_IN_1X1: False
OUT_FEATURES: ["res2", "res3", "res4", "res5"]
FPN:
IN_FEATURES: ["res2", "res3", "res4", "res5"]
ANCHOR_GENERATOR:
# One size for each in feature map
SIZES: [[32], [64], [128], [256], [512]]
# Three aspect ratios (same for all in feature maps)
ASPECT_RATIOS: [[0.5, 1.0, 2.0]]
RPN:
IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
PRE_NMS_TOPK_TRAIN: 2000
PRE_NMS_TOPK_TEST: 1000
POST_NMS_TOPK_TRAIN: 1000
POST_NMS_TOPK_TEST: 1000
ROI_HEADS:
NAME: "StandardROIHeads"
IN_FEATURES: ["p2", "p3", "p4", "p5"]
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_FC: 2
POOLER_RESOLUTION: 7
ROI_MASK_HEAD:
NAME: "MaskRCNNConvUpsampleHead"
NUM_CONV: 4
POOLER_RESOLUTION: 14
# ImageNet color mean for torchvision-like models (RGB order).
# These are in [0-255] range as expected by Detectron2. Rest of our codebase
# uses [0-1] range; but both are equivalent and consistent.
PIXEL_MEAN: [123.675, 116.280, 103.530]
PIXEL_STD: [58.395, 57.120, 57.375]
SOLVER:
# This is for 8 GPUs, apply linear scaling for 4 GPUs.
IMS_PER_BATCH: 16
BASE_LR: 0.02
TEST:
PRECISE_BN:
ENABLED: True
VERSION: 2