{ "VERSION": 2, "MODEL": { "LOAD_PROPOSALS": false, "MASK_ON": false, "KEYPOINT_ON": false, "DEVICE": "cpu", "META_ARCHITECTURE": "GeneralizedRCNN", "WEIGHTS": "https://www.dropbox.com/s/dgy9c10wykk4lq4/model_final.pth?dl=1", "PIXEL_MEAN": [ 103.53, 116.28, 123.675 ], "PIXEL_STD": [ 1.0, 1.0, 1.0 ], "BACKBONE": { "NAME": "build_resnet_fpn_backbone", "FREEZE_AT": 2 }, "FPN": { "IN_FEATURES": [ "res2", "res3", "res4", "res5" ], "OUT_CHANNELS": 256, "NORM": "", "FUSE_TYPE": "sum" }, "PROPOSAL_GENERATOR": { "NAME": "RPN", "MIN_SIZE": 0 }, "ANCHOR_GENERATOR": { "NAME": "DefaultAnchorGenerator", "SIZES": [ [ 32 ], [ 64 ], [ 128 ], [ 256 ], [ 512 ] ], "ASPECT_RATIOS": [ [ 0.5, 1.0, 2.0 ] ], "ANGLES": [ [ -90, 0, 90 ] ], "OFFSET": 0.0 }, "RPN": { "HEAD_NAME": "StandardRPNHead", "IN_FEATURES": [ "p2", "p3", "p4", "p5", "p6" ], "BOUNDARY_THRESH": -1, "IOU_THRESHOLDS": [ 0.3, 0.7 ], "IOU_LABELS": [ 0, -1, 1 ], "BATCH_SIZE_PER_IMAGE": 256, "POSITIVE_FRACTION": 0.5, "BBOX_REG_LOSS_TYPE": "smooth_l1", "BBOX_REG_LOSS_WEIGHT": 1.0, "BBOX_REG_WEIGHTS": [ 1.0, 1.0, 1.0, 1.0 ], "SMOOTH_L1_BETA": 0.0, "LOSS_WEIGHT": 1.0, "PRE_NMS_TOPK_TRAIN": 2000, "PRE_NMS_TOPK_TEST": 1000, "POST_NMS_TOPK_TRAIN": 1000, "POST_NMS_TOPK_TEST": 1000, "NMS_THRESH": 0.7, "CONV_DIMS": [ -1 ] }, "ROI_HEADS": { "NAME": "StandardROIHeads", "NUM_CLASSES": 2, "IN_FEATURES": [ "p2", "p3", "p4", "p5" ], "IOU_THRESHOLDS": [ 0.5 ], "IOU_LABELS": [ 0, 1 ], "BATCH_SIZE_PER_IMAGE": 128, "POSITIVE_FRACTION": 0.25, "SCORE_THRESH_TEST": 0.8, "NMS_THRESH_TEST": 0.5, "PROPOSAL_APPEND_GT": true }, "ROI_BOX_HEAD": { "NAME": "FastRCNNConvFCHead", "BBOX_REG_LOSS_TYPE": "smooth_l1", "BBOX_REG_LOSS_WEIGHT": 1.0, "BBOX_REG_WEIGHTS": [ 10.0, 10.0, 5.0, 5.0 ], "SMOOTH_L1_BETA": 0.0, "POOLER_RESOLUTION": 7, "POOLER_SAMPLING_RATIO": 0, "POOLER_TYPE": "ROIAlignV2", "NUM_FC": 2, "FC_DIM": 1024, "NUM_CONV": 0, "CONV_DIM": 256, "NORM": "", "CLS_AGNOSTIC_BBOX_REG": false, "TRAIN_ON_PRED_BOXES": false }, "ROI_BOX_CASCADE_HEAD": { "BBOX_REG_WEIGHTS": [ [ 10.0, 10.0, 5.0, 5.0 ], [ 20.0, 20.0, 10.0, 10.0 ], [ 30.0, 30.0, 15.0, 15.0 ] ], "IOUS": [ 0.5, 0.6, 0.7 ] }, "ROI_MASK_HEAD": { "NAME": "MaskRCNNConvUpsampleHead", "POOLER_RESOLUTION": 14, "POOLER_SAMPLING_RATIO": 0, "NUM_CONV": 4, "CONV_DIM": 256, "NORM": "", "CLS_AGNOSTIC_MASK": false, "POOLER_TYPE": "ROIAlignV2" }, "ROI_KEYPOINT_HEAD": { "NAME": "KRCNNConvDeconvUpsampleHead", "POOLER_RESOLUTION": 14, "POOLER_SAMPLING_RATIO": 0, "CONV_DIMS": [ 512, 512, 512, 512, 512, 512, 512, 512 ], "NUM_KEYPOINTS": 17, "MIN_KEYPOINTS_PER_IMAGE": 1, "NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS": true, "LOSS_WEIGHT": 1.0, "POOLER_TYPE": "ROIAlignV2" }, "SEM_SEG_HEAD": { "NAME": "SemSegFPNHead", "IN_FEATURES": [ "p2", "p3", "p4", "p5" ], "IGNORE_VALUE": 255, "NUM_CLASSES": 54, "CONVS_DIM": 128, "COMMON_STRIDE": 4, "NORM": "GN", "LOSS_WEIGHT": 1.0 }, "PANOPTIC_FPN": { "INSTANCE_LOSS_WEIGHT": 1.0, "COMBINE": { "ENABLED": true, "OVERLAP_THRESH": 0.5, "STUFF_AREA_LIMIT": 4096, "INSTANCES_CONFIDENCE_THRESH": 0.5 } }, "RETINANET": { "NUM_CLASSES": 80, "IN_FEATURES": [ "p3", "p4", "p5", "p6", "p7" ], "NUM_CONVS": 4, "IOU_THRESHOLDS": [ 0.4, 0.5 ], "IOU_LABELS": [ 0, -1, 1 ], "PRIOR_PROB": 0.01, "SCORE_THRESH_TEST": 0.05, "TOPK_CANDIDATES_TEST": 1000, "NMS_THRESH_TEST": 0.5, "BBOX_REG_WEIGHTS": [ 1.0, 1.0, 1.0, 1.0 ], "FOCAL_LOSS_GAMMA": 2.0, "FOCAL_LOSS_ALPHA": 0.25, "SMOOTH_L1_LOSS_BETA": 0.1, "BBOX_REG_LOSS_TYPE": "smooth_l1", "NORM": "" }, "RESNETS": { "DEPTH": 50, "OUT_FEATURES": [ "res2", "res3", "res4", "res5" ], "NUM_GROUPS": 1, "NORM": "FrozenBN", "WIDTH_PER_GROUP": 64, "STRIDE_IN_1X1": true, "RES5_DILATION": 1, "RES2_OUT_CHANNELS": 256, "STEM_OUT_CHANNELS": 64, "DEFORM_ON_PER_STAGE": [ false, false, false, false ], "DEFORM_MODULATED": false, "DEFORM_NUM_GROUPS": 1 } }, "INPUT": { "MIN_SIZE_TRAIN": [ 640, 672, 704, 736, 768, 800 ], "MIN_SIZE_TRAIN_SAMPLING": "choice", "MAX_SIZE_TRAIN": 1333, "MIN_SIZE_TEST": 800, "MAX_SIZE_TEST": 1333, "RANDOM_FLIP": "none", "CROP": { "ENABLED": true, "TYPE": "relative_range", "SIZE": [ 0.9, 0.9 ] }, "FORMAT": "BGR", "MASK_FORMAT": "polygon" }, "DATASETS": { "TRAIN": [ "oer_checkbox_train" ], "PROPOSAL_FILES_TRAIN": [], "PRECOMPUTED_PROPOSAL_TOPK_TRAIN": 2000, "TEST": [], "PROPOSAL_FILES_TEST": [], "PRECOMPUTED_PROPOSAL_TOPK_TEST": 1000 }, "DATALOADER": { "NUM_WORKERS": 2, "ASPECT_RATIO_GROUPING": true, "SAMPLER_TRAIN": "TrainingSampler", "REPEAT_THRESHOLD": 0.0, "FILTER_EMPTY_ANNOTATIONS": true }, "SOLVER": { "LR_SCHEDULER_NAME": "WarmupMultiStepLR", "MAX_ITER": 600, "BASE_LR": 0.00025, "MOMENTUM": 0.9, "NESTEROV": false, "WEIGHT_DECAY": 0.0001, "WEIGHT_DECAY_NORM": 0.0, "GAMMA": 0.1, "STEPS": [], "WARMUP_FACTOR": 0.001, "WARMUP_ITERS": 1000, "WARMUP_METHOD": "linear", "CHECKPOINT_PERIOD": 5000, "IMS_PER_BATCH": 2, "REFERENCE_WORLD_SIZE": 0, "BIAS_LR_FACTOR": 1.0, "WEIGHT_DECAY_BIAS": 0.0001, "CLIP_GRADIENTS": { "ENABLED": false, "CLIP_TYPE": "value", "CLIP_VALUE": 1.0, "NORM_TYPE": 2.0 }, "AMP": { "ENABLED": false } }, "TEST": { "EXPECTED_RESULTS": [], "EVAL_PERIOD": 0, "KEYPOINT_OKS_SIGMAS": [], "DETECTIONS_PER_IMAGE": 100, "AUG": { "ENABLED": false, "MIN_SIZES": [ 400, 500, 600, 700, 800, 900, 1000, 1100, 1200 ], "MAX_SIZE": 4000, "FLIP": true }, "PRECISE_BN": { "ENABLED": false, "NUM_ITER": 200 } }, "OUTPUT_DIR": "output/oer_checkbox/faster_rcnn_R_50_FPN_3x/", "SEED": -1, "CUDNN_BENCHMARK": false, "VIS_PERIOD": 0, "GLOBAL": { "HACK": 1.0 } }