detectron2: DeepLab Inference seems to not be working / Unable to display predictions

Hi, thank you Yuxin and team for making this amazing resource and for all of your support answering questions!!!

I’m running into an issue where I think I am either not running inference properly or I’m just having difficulty displaying my predictions because I keep getting an error when trying to run visualize_data.py.

Instructions To Reproduce the 🐛 Bug:

1. Full runnable code or full changes you made: This is my file train_net_xbd.py (removing imports)

def build_sem_seg_train_aug(cfg):
    augs = [
        T.ResizeShortestEdge(
            cfg.INPUT.MIN_SIZE_TRAIN, cfg.INPUT.MAX_SIZE_TRAIN, cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING
        )
    ]
    if cfg.INPUT.CROP.ENABLED:
        augs.append(
            T.RandomCrop_CategoryAreaConstraint(
                cfg.INPUT.CROP.TYPE,
                cfg.INPUT.CROP.SIZE,
                cfg.INPUT.CROP.SINGLE_CATEGORY_MAX_AREA,
                cfg.MODEL.SEM_SEG_HEAD.IGNORE_VALUE,
            )
        )
    augs.append(T.RandomFlip())
    return augs


class Trainer(DefaultTrainer):
    """
    We use the "DefaultTrainer" which contains a number pre-defined logic for
    standard training workflow. They may not work for you, especially if you
    are working on a new research project. In that case you can use the cleaner
    "SimpleTrainer", or write your own training loop.
    """
    @classmethod
    def build_evaluator(cls, cfg, dataset_name, output_folder=None):
        """
        Create evaluator(s) for a given dataset.
        This uses the special metadata "evaluator_type" associated with each builtin dataset.
        For your own dataset, you can simply create an evaluator manually in your
        script and do not have to worry about the hacky if-else logic here.
        """
        if output_folder is None:
            output_folder = os.path.join(cfg.OUTPUT_DIR, "inference")
        evaluator_list = []
        evaluator_type = MetadataCatalog.get(dataset_name).evaluator_type
        if evaluator_type == "sem_seg":
            print("datasetname", dataset_name)
            return SemSegEvaluator(
                dataset_name,
                distributed=True,
                num_classes=cfg.MODEL.SEM_SEG_HEAD.NUM_CLASSES,
                ignore_label=cfg.MODEL.SEM_SEG_HEAD.IGNORE_VALUE,
                output_dir=output_folder,
            )
        return DatasetEvaluators(evaluator_list)

    @classmethod
    def build_train_loader(cls, cfg):
        if "SemanticSegmentor" in cfg.MODEL.META_ARCHITECTURE:
            mapper = DatasetMapper(cfg, is_train=True, augmentations=build_sem_seg_train_aug(cfg))
        else:
            mapper = None
        return build_detection_train_loader(cfg, mapper=mapper)

    @classmethod
    def build_lr_scheduler(cls, cfg, optimizer):
        """
        It now calls :func:`detectron2.solver.build_lr_scheduler`.
        Overwrite it if you'd like a different scheduler.
        """
        return build_lr_scheduler(cfg, optimizer)


def setup(args):
    """
    Create configs and perform basic setups.
    """
    cfg = get_cfg()
    add_deeplab_config(cfg)
    cfg.merge_from_file(args.config_file)
    cfg.merge_from_list(args.opts)
    cfg.freeze()
    default_setup(cfg, args)
    return cfg

def get_building_dicts(img_dir):
    """This function loads the JSON file created with the annotator and converts it to
    the detectron2 metadata specifications.
    """
    img_links = glob.glob(img_dir+"labels/*.json")
    # only keep the images that include post
    img_anns = list(filter(lambda x: "post" in x, img_links)) 

    dataset_dicts = []
    # loop through the entries in the JSON file
    for idx, single in enumerate(img_anns):
        v = json.load(open(single))
        record = {}
        # add file_name, image_id, height and width information to the records
        filename = os.path.join(img_dir, "images/", v["metadata"]["img_name"])
        height, width = (v["metadata"]["height"], v["metadata"]["width"])

        record["file_name"] = filename
        record["image_id"] = idx
        record["height"] = height
        record["width"] = width
        record["sem_seg_file_name"] = img_dir+"bin_masks/" + v["metadata"]["img_name"]
        dataset_dicts.append(record)

    return dataset_dicts


def main(args):

    for d in ["train", "test"]:
        DatasetCatalog.register(
            "xbddata_" + d, lambda d=d: get_building_dicts("/n/tambe_lab/Users/michelewang/" + d+"/"),
        )
        MetadataCatalog.get("xbddata_"+d).stuff_classes = ["0","1","2"]
        MetadataCatalog.get("xbddata_"+d).evaluator_type = "sem_seg"
    
    print("Dataset Catalog", DatasetCatalog.list())
    print("XBDDATA_TRAIN", DatasetCatalog.get("xbddata_train"))
    xbdtrain_metadata = MetadataCatalog.get("xbddata_train")
    xbdtest_metadata = MetadataCatalog.get("xbddata_test")

    cfg = setup(args)

    if args.eval_only:
        print("hi, we're in eval only")
        model = Trainer.build_model(cfg)
        print("cfg.MODEL.WEIGHTS", cfg.MODEL.WEIGHTS)
        print("cfg.OUTPUT_DIR", cfg.OUTPUT_DIR)
        DetectionCheckpointer(model, save_dir=cfg.OUTPUT_DIR).resume_or_load(
            cfg.MODEL.WEIGHTS, resume=args.resume
        )
        res = Trainer.test(cfg, model)
        return res

    trainer = Trainer(cfg)
    trainer.resume_or_load(resume=args.resume)
    return trainer.train()


if __name__ == "__main__":
    args = default_argument_parser().parse_args()
    print("Command Line Args:", args)
    launch(
        main,
        args.num_gpus,
        num_machines=args.num_machines,
        machine_rank=args.machine_rank,
        dist_url=args.dist_url,
        args=(args,),
    )

This is my file visualize_data.py:

#!/usr/bin/env python
# Copyright (c) Facebook, Inc. and its affiliates.
import argparse
import os
from itertools import chain
import cv2
import tqdm

from detectron2.config import get_cfg
from detectron2.data import DatasetCatalog, MetadataCatalog, build_detection_train_loader
from detectron2.data import detection_utils as utils
from detectron2.data.build import filter_images_with_few_keypoints
from detectron2.utils.logger import setup_logger
from detectron2.utils.visualizer import Visualizer


def setup(args):
    cfg = get_cfg()
    if args.config_file:
        cfg.merge_from_file(args.config_file)
    cfg.merge_from_list(args.opts)
    cfg.DATALOADER.NUM_WORKERS = 0
    cfg.freeze()
    return cfg


def parse_args(in_args=None):
    parser = argparse.ArgumentParser(description="Visualize ground-truth data")
    parser.add_argument(
        "--source",
        choices=["annotation", "dataloader"],
        required=True,
        help="visualize the annotations or the data loader (with pre-processing)",
    )
    parser.add_argument("--config-file", metavar="FILE", help="path to config file")
    parser.add_argument("--output-dir", default="./", help="path to output directory")
    parser.add_argument("--show", action="store_true", help="show output in a window")
    parser.add_argument(
        "opts",
        help="Modify config options using the command-line",
        default=None,
        nargs=argparse.REMAINDER,
    )
    return parser.parse_args(in_args)


if __name__ == "__main__":
    args = parse_args()
    logger = setup_logger()
    logger.info("Arguments: " + str(args))
    cfg = setup(args)

    dirname = args.output_dir
    os.makedirs(dirname, exist_ok=True)
    metadata = MetadataCatalog.get(cfg.DATASETS.TRAIN[0])

    def output(vis, fname):
        if args.show:
            print(fname)
            cv2.imshow("window", vis.get_image()[:, :, ::-1])
            cv2.waitKey()
        else:
            filepath = os.path.join(dirname, fname)
            print("Saving to {} ...".format(filepath))
            vis.save(filepath)

    scale = 1.0
    if args.source == "dataloader":
        train_data_loader = build_detection_train_loader(cfg)
        for batch in train_data_loader:
            for per_image in batch:
                # Pytorch tensor is in (C, H, W) format
                img = per_image["image"].permute(1, 2, 0).cpu().detach().numpy()
                img = utils.convert_image_to_rgb(img, cfg.INPUT.FORMAT)

                visualizer = Visualizer(img, metadata=metadata, scale=scale)
                target_fields = per_image["instances"].get_fields()
                labels = [metadata.thing_classes[i] for i in target_fields["gt_classes"]]
                vis = visualizer.overlay_instances(
                    labels=labels,
                    boxes=target_fields.get("gt_boxes", None),
                    masks=target_fields.get("gt_masks", None),
                    keypoints=target_fields.get("gt_keypoints", None),
                )
                output(vis, str(per_image["image_id"]) + ".jpg")
    else:
        dicts = list(chain.from_iterable([DatasetCatalog.get(k) for k in cfg.DATASETS.TRAIN]))
        if cfg.MODEL.KEYPOINT_ON:
            dicts = filter_images_with_few_keypoints(dicts, 1)
        for dic in tqdm.tqdm(dicts):
            img = utils.read_image(dic["file_name"], "RGB")
            visualizer = Visualizer(img, metadata=metadata, scale=scale)
            vis = visualizer.draw_dataset_dict(dic)
            output(vis, os.path.basename(dic["file_name"]))

1. What exact command you run: This was the script I ran for inference (It finished in <1 min so I think something is wrong here):

cd /n/home07/michelewang/thesis/detectron2/projects/DeepLab
python train_net_xbd.py --config-file configs/xBD-configs/base-deeplabv3.yaml --eval-only MODEL.WEIGHTS ./output/model_0024999.pth

This was the script I ran to try to view my predictions:

cd /n/home07/michelewang/thesis/detectron2/tools
python visualize_data.py --source annotation --config-file ../projects/DeepLab/configs/xBD-configs/base-deeplabv3.yaml --output-dir ../projects/DeepLab/output/inference --show

1. Full logs or other relevant observations: Logs from Inference:

WARNING [03/07 21:38:53 d2.evaluation.sem_seg_evaluation]: SemSegEvaluator(num_classes) is deprecated! It should be obtained from metadata.
WARNING [03/07 21:38:53 d2.evaluation.sem_seg_evaluation]: SemSegEvaluator(ignore_label) is deprecated! It should be obtained from metadata.
[03/07 21:38:54 d2.evaluation.evaluator]: Start inference on 933 images
[03/07 21:38:56 d2.evaluation.evaluator]: Inference done 11/933. 0.0817 s / img. ETA=0:01:55
[03/07 21:39:01 d2.evaluation.evaluator]: Inference done 51/933. 0.0817 s / img. ETA=0:01:50
[03/07 21:39:06 d2.evaluation.evaluator]: Inference done 70/933. 0.0817 s / img. ETA=0:02:26
[03/07 21:39:11 d2.evaluation.evaluator]: Inference done 110/933. 0.0818 s / img. ETA=0:02:06
[03/07 21:39:17 d2.evaluation.evaluator]: Inference done 150/933. 0.0818 s / img. ETA=0:01:54
[03/07 21:39:22 d2.evaluation.evaluator]: Inference done 190/933. 0.0819 s / img. ETA=0:01:45
[03/07 21:39:27 d2.evaluation.evaluator]: Inference done 229/933. 0.0820 s / img. ETA=0:01:38
[03/07 21:39:32 d2.evaluation.evaluator]: Inference done 270/933. 0.0820 s / img. ETA=0:01:30
[03/07 21:39:37 d2.evaluation.evaluator]: Inference done 310/933. 0.0819 s / img. ETA=0:01:24
[03/07 21:39:42 d2.evaluation.evaluator]: Inference done 351/933. 0.0819 s / img. ETA=0:01:18
[03/07 21:39:47 d2.evaluation.evaluator]: Inference done 391/933. 0.0819 s / img. ETA=0:01:12
[03/07 21:39:52 d2.evaluation.evaluator]: Inference done 432/933. 0.0819 s / img. ETA=0:01:06
[03/07 21:39:57 d2.evaluation.evaluator]: Inference done 473/933. 0.0819 s / img. ETA=0:01:00
[03/07 21:40:02 d2.evaluation.evaluator]: Inference done 514/933. 0.0819 s / img. ETA=0:00:54
[03/07 21:40:07 d2.evaluation.evaluator]: Inference done 554/933. 0.0818 s / img. ETA=0:00:49
[03/07 21:40:12 d2.evaluation.evaluator]: Inference done 595/933. 0.0818 s / img. ETA=0:00:44
[03/07 21:40:17 d2.evaluation.evaluator]: Inference done 636/933. 0.0818 s / img. ETA=0:00:38
[03/07 21:40:23 d2.evaluation.evaluator]: Inference done 677/933. 0.0818 s / img. ETA=0:00:33
[03/07 21:40:28 d2.evaluation.evaluator]: Inference done 717/933. 0.0818 s / img. ETA=0:00:27
[03/07 21:40:33 d2.evaluation.evaluator]: Inference done 758/933. 0.0818 s / img. ETA=0:00:22
[03/07 21:40:38 d2.evaluation.evaluator]: Inference done 799/933. 0.0818 s / img. ETA=0:00:17
[03/07 21:40:43 d2.evaluation.evaluator]: Inference done 840/933. 0.0818 s / img. ETA=0:00:11
[03/07 21:40:48 d2.evaluation.evaluator]: Inference done 881/933. 0.0818 s / img. ETA=0:00:06
[03/07 21:40:53 d2.evaluation.evaluator]: Inference done 922/933. 0.0818 s / img. ETA=0:00:01
[03/07 21:40:54 d2.evaluation.evaluator]: Total inference time: 0:01:59.094921 (0.128335 s / img per device, on 1 devices)
[03/07 21:40:54 d2.evaluation.evaluator]: Total inference pure compute time: 0:01:15 (0.081782 s / img per device, on 1 devices)
[03/07 21:40:56 d2.evaluation.sem_seg_evaluation]: OrderedDict([('sem_seg', {'mIoU': 14.286231780375028, 'fwIoU': 30.412502468859948, 'IoU-0': 31.958253593820217, 'IoU-1': 5.555678249276511, 'IoU-2': 5.344763498028353, 'mACC': 53.518182755044954, 'pACC': 34.17634953767668, 'ACC-0': 32.13264257356594, 'ACC-1': 69.63928432518483, 'ACC-2': 58.78262136638409})])
[03/07 21:40:56 d2.engine.defaults]: Evaluation results for xbddata_test in csv format:
[03/07 21:40:56 d2.evaluation.testing]: copypaste: Task: sem_seg
[03/07 21:40:56 d2.evaluation.testing]: copypaste: mIoU,fwIoU,mACC,pACC
[03/07 21:40:56 d2.evaluation.testing]: copypaste: 14.2862,30.4125,53.5182,34.1763

The Semantic Segmentation JSON created in my Outputs folder, sem_seg_predictions.json – is this normal??

The Error I got from my second script to visualize_data.py:

Traceback (most recent call last):
Traceback (most recent call last):
  File "visualize_data.py", line 51, in <module>
    cfg = setup(args)
  File "visualize_data.py", line 20, in setup
    cfg.merge_from_file(args.config_file)
  File "/n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/detectron2/config/config.py", line 54, in merge_from_file
    self.merge_from_other_cfg(loaded_cfg)
  File "/n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/fvcore/common/config.py", line 123, in merge_from_other_cfg
    return super().merge_from_other_cfg(cfg_other)
  File "/n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/yacs/config.py", line 217, in merge_from_other_cfg
    _merge_a_into_b(cfg_other, self, self, [])
  File "/n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/yacs/config.py", line 478, in _merge_a_into_b
    _merge_a_into_b(v, b[k], root, key_list + [k])
  File "/n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/yacs/config.py", line 478, in _merge_a_into_b
    _merge_a_into_b(v, b[k], root, key_list + [k])
  File "/n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/yacs/config.py", line 491, in _merge_a_into_b
    raise KeyError("Non-existent config key: {}".format(full_key))
KeyError: 'Non-existent config key: MODEL.RESNETS.RES5_MULTI_GRID'

1. please simplify the steps as much as possible so they do not require additional resources to run, such as a private dataset.

Expected behavior:

I first ran the inference script. It ran really fast, taking less than a minute. Then I ran the script to visualize my predictions, because I wanted to see how accurate Deeplab’s semantic segmentation predictions for my model were. However, I was blocked by syntax errors for the model and I don’t think I did inference correctly given that it ran so fast, and the Json file of predictions, is gibberish, but I’m not sure how to do it correctly.

Environment:

Provide your environment information using the following command:

wget -nc -q https://github.com/facebookresearch/detectron2/raw/master/detectron2/utils/collect_env.py && python collect_env.py

If your issue looks like an installation issue / environment issue, please first try to solve it yourself with the instructions in https://detectron2.readthedocs.io/tutorials/install.html#common-installation-issues

Full Error Logs for Inference the stuff at the top is just the model reprinting all the data in my original train dataset)

{'file_name': '/n/tambe_lab/Users/michelewang/train/images/midwest-flooding_00000173_post_disaster.png', 'image_id': 2715, 'height': 1024, 'width': 1024, 'sem_seg_file_name': '/n/tambe_lab/Users/michelewang/train/bin_masks/midwest-flooding_00000173_post_disaster.png'}, {'file_name': '/n/tambe_lab/Users/michelewang/train/images/midwest-flooding_00000293_post_disaster.png', 'image_id': 2716, 'height': 1024, 'width': 1024, 'sem_seg_file_n
[03/07 21:38:45 detectron2]: Rank of current process: 0. World size: 1
[03/07 21:38:48 detectron2]: Environment info:
----------------------  -----------------------------------------------------------------------------------------------------------------
sys.platform            linux
Python                  3.8.5 (default, Sep  4 2020, 07:30:14) [GCC 7.3.0]
numpy                   1.19.2
detectron2              0.3 @/n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/detectron2
Compiler                GCC 9.2
CUDA compiler           not available
detectron2 arch flags   /n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/detectron2/_C.cpython-38-x86_64-linux-gnu.so
DETECTRON2_ENV_MODULE   <not set>
PyTorch                 1.7.1 @/n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/torch
PyTorch debug build     False
GPU available           True
GPU 0,1,2,3,4,5,6,7     Tesla V100-PCIE-32GB (arch=7.0)
CUDA_HOME               /n/helmod/apps/centos7/Core/cuda/10.2.89-fasrc01/cuda
Pillow                  8.1.0
torchvision             0.8.2 @/n/home07/michelewang/.conda/envs/active/lib/python3.8/site-packages/torchvision
torchvision arch flags  3.5, 5.0, 6.0, 7.0, 7.5
fvcore                  0.1.3.post20210220
cv2                     4.4.0
----------------------  -----------------------------------------------------------------------------------------------------------------
PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 10.1
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37
  - CuDNN 7.6.3
  - Magma 2.5.2
  - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, 

[03/07 21:38:48 detectron2]: Command line arguments: Namespace(config_file='configs/xBD-configs/base-deeplabv3.yaml', dist_url='tcp://127.0.0.1:62862', eval_only=True, machine_rank=0, num_gpus=1, num_machines=1, opts=['MODEL.WEIGHTS', './output/model_0024999.pth'], resume=False)
[03/07 21:38:48 detectron2]: Contents of args.config_file=configs/xBD-configs/base-deeplabv3.yaml:
_BASE_: base.yaml
MODEL:
  WEIGHTS: "detectron2://DeepLab/R-103.pkl"
  PIXEL_MEAN: [123.675, 116.280, 103.530]
  PIXEL_STD: [58.395, 57.120, 57.375]
  BACKBONE:
    NAME: "build_resnet_deeplab_backbone"
  RESNETS:
    DEPTH: 101
    NORM: "SyncBN"
    OUT_FEATURES: ["res2", "res5"]
    RES5_MULTI_GRID: [1, 2, 4]
    STEM_TYPE: "deeplab"
    STEM_OUT_CHANNELS: 128
    STRIDE_IN_1X1: False
  SEM_SEG_HEAD:
    NAME: "DeepLabV3PlusHead"
    IN_FEATURES: ["res2", "res5"]
    PROJECT_FEATURES: ["res2"]
    PROJECT_CHANNELS: [48]
    NORM: "SyncBN"
    COMMON_STRIDE: 4
INPUT:
  FORMAT: "RGB"

[03/07 21:38:48 detectron2]: Running with full config:
CUDNN_BENCHMARK: False
DATALOADER:
  ASPECT_RATIO_GROUPING: True
  FILTER_EMPTY_ANNOTATIONS: True
  NUM_WORKERS: 10
  REPEAT_THRESHOLD: 0.0
  SAMPLER_TRAIN: TrainingSampler
DATASETS:
  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
  PROPOSAL_FILES_TEST: ()
  PROPOSAL_FILES_TRAIN: ()
  TEST: ('xbddata_test',)
  TRAIN: ('xbddata_train',)
GLOBAL:
  HACK: 1.0
INPUT:
  CROP:
    ENABLED: True
    SINGLE_CATEGORY_MAX_AREA: 1.0
    SIZE: [512, 1024]
    TYPE: absolute
  FORMAT: RGB
  MASK_FORMAT: polygon
  MAX_SIZE_TEST: 1024
  MAX_SIZE_TRAIN: 1024
  MIN_SIZE_TEST: 1024
  MIN_SIZE_TRAIN: (1024,)
  MIN_SIZE_TRAIN_SAMPLING: choice
  RANDOM_FLIP: horizontal
MODEL:
  ANCHOR_GENERATOR:
    ANGLES: [[-90, 0, 90]]
    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]
    NAME: DefaultAnchorGenerator
    OFFSET: 0.0
    SIZES: [[32, 64, 128, 256, 512]]
  BACKBONE:
    FREEZE_AT: 0
    NAME: build_resnet_deeplab_backbone
  DEVICE: cuda
  FPN:
    FUSE_TYPE: sum
    IN_FEATURES: []
    NORM: 
    OUT_CHANNELS: 256
  KEYPOINT_ON: False
  LOAD_PROPOSALS: False
  MASK_ON: False
  META_ARCHITECTURE: SemanticSegmentor
  PANOPTIC_FPN:
    COMBINE:
      ENABLED: True
      INSTANCES_CONFIDENCE_THRESH: 0.5
      OVERLAP_THRESH: 0.5
      STUFF_AREA_LIMIT: 4096
    INSTANCE_LOSS_WEIGHT: 1.0
  PIXEL_MEAN: [123.675, 116.28, 103.53]
  PIXEL_STD: [58.395, 57.12, 57.375]
  PROPOSAL_GENERATOR:
    MIN_SIZE: 0
    NAME: RPN
  RESNETS:
    DEFORM_MODULATED: False
    DEFORM_NUM_GROUPS: 1
    DEFORM_ON_PER_STAGE: [False, False, False, False]
    DEPTH: 101
    NORM: SyncBN
    NUM_GROUPS: 1
    OUT_FEATURES: ['res2', 'res5']
    RES2_OUT_CHANNELS: 256
    RES4_DILATION: 1
    RES5_DILATION: 2
    RES5_MULTI_GRID: [1, 2, 4]
    STEM_OUT_CHANNELS: 128
    STEM_TYPE: deeplab
    STRIDE_IN_1X1: False
    WIDTH_PER_GROUP: 64
  RETINANET:
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_WEIGHTS: (1.0, 1.0, 1.0, 1.0)
    FOCAL_LOSS_ALPHA: 0.25
    FOCAL_LOSS_GAMMA: 2.0
    IN_FEATURES: ['p3', 'p4', 'p5', 'p6', 'p7']
    IOU_LABELS: [0, -1, 1]
    IOU_THRESHOLDS: [0.4, 0.5]
    NMS_THRESH_TEST: 0.5
    NORM: 
    NUM_CLASSES: 80
    NUM_CONVS: 4
    PRIOR_PROB: 0.01
    SCORE_THRESH_TEST: 0.05
    SMOOTH_L1_LOSS_BETA: 0.1
    TOPK_CANDIDATES_TEST: 1000
  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_BOX_HEAD:
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_LOSS_WEIGHT: 1.0
    BBOX_REG_WEIGHTS: (10.0, 10.0, 5.0, 5.0)
    CLS_AGNOSTIC_BBOX_REG: False
    CONV_DIM: 256
    FC_DIM: 1024
    NAME: FastRCNNConvFCHead
    NORM: 
    NUM_CONV: 0
    NUM_FC: 2
    POOLER_RESOLUTION: 7
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
    SMOOTH_L1_BETA: 0.0
    TRAIN_ON_PRED_BOXES: False
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 512
    IN_FEATURES: ['res5']
    IOU_LABELS: [0, 1]
    IOU_THRESHOLDS: [0.5]
    NAME: StandardROIHeads
    NMS_THRESH_TEST: 0.5
    NUM_CLASSES: 80
    POSITIVE_FRACTION: 0.25
    PROPOSAL_APPEND_GT: True
    SCORE_THRESH_TEST: 0.05
  ROI_KEYPOINT_HEAD:
    CONV_DIMS: (512, 512, 512, 512, 512, 512, 512, 512)
    LOSS_WEIGHT: 1.0
    MIN_KEYPOINTS_PER_IMAGE: 1
    NAME: KRCNNConvDeconvUpsampleHead
    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: True
    NUM_KEYPOINTS: 17
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
  ROI_MASK_HEAD:
    CLS_AGNOSTIC_MASK: False
    CONV_DIM: 256
    NAME: MaskRCNNConvUpsampleHead
    NORM: 
    NUM_CONV: 4
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
  RPN:
    BATCH_SIZE_PER_IMAGE: 256
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_LOSS_WEIGHT: 1.0
    BBOX_REG_WEIGHTS: (1.0, 1.0, 1.0, 1.0)
    BOUNDARY_THRESH: -1
    HEAD_NAME: StandardRPNHead
    IN_FEATURES: ['res5']
    IOU_LABELS: [0, -1, 1]
    IOU_THRESHOLDS: [0.3, 0.7]
    LOSS_WEIGHT: 1.0
    NMS_THRESH: 0.7
    POSITIVE_FRACTION: 0.5
    POST_NMS_TOPK_TEST: 1000
    POST_NMS_TOPK_TRAIN: 2000
    PRE_NMS_TOPK_TEST: 6000
    PRE_NMS_TOPK_TRAIN: 12000
    SMOOTH_L1_BETA: 0.0
  SEM_SEG_HEAD:
    ASPP_CHANNELS: 256
    ASPP_DILATIONS: [6, 12, 18]
    ASPP_DROPOUT: 0.1
    COMMON_STRIDE: 4
    CONVS_DIM: 256
    IGNORE_VALUE: 255
    IN_FEATURES: ['res2', 'res5']
    LOSS_TYPE: hard_pixel_mining
    LOSS_WEIGHT: 1.0
    NAME: DeepLabV3PlusHead
    NORM: SyncBN
    NUM_CLASSES: 3
    PROJECT_CHANNELS: [48]
    PROJECT_FEATURES: ['res2']
    USE_DEPTHWISE_SEPARABLE_CONV: False
  WEIGHTS: ./output/model_0024999.pth
OUTPUT_DIR: ./output
SEED: -1
SOLVER:
  AMP:
    ENABLED: False
  BASE_LR: 0.01
  BIAS_LR_FACTOR: 1.0
  CHECKPOINT_PERIOD: 5000
  CLIP_GRADIENTS:
    CLIP_TYPE: value
    CLIP_VALUE: 1.0
    ENABLED: False
    NORM_TYPE: 2.0
  GAMMA: 0.1
  IMS_PER_BATCH: 16
  LR_SCHEDULER_NAME: WarmupPolyLR
  MAX_ITER: 90000
  MOMENTUM: 0.9
  NESTEROV: False
  POLY_LR_CONSTANT_ENDING: 0.0
  POLY_LR_POWER: 0.9
  REFERENCE_WORLD_SIZE: 0
  STEPS: (60000, 80000)
  WARMUP_FACTOR: 0.001
  WARMUP_ITERS: 1000
  WARMUP_METHOD: linear
  WEIGHT_DECAY: 0.0001
  WEIGHT_DECAY_BIAS: 0.0001
  WEIGHT_DECAY_NORM: 0.0
TEST:
  AUG:
    ENABLED: False
    FLIP: True
    MAX_SIZE: 4000
    MIN_SIZES: (400, 500, 600, 700, 800, 900, 1000, 1100, 1200)
  DETECTIONS_PER_IMAGE: 100
  EVAL_PERIOD: 0
  EXPECTED_RESULTS: []
  KEYPOINT_OKS_SIGMAS: []
  PRECISE_BN:
    ENABLED: False
    NUM_ITER: 200
VERSION: 2
VIS_PERIOD: 0
[03/07 21:38:48 detectron2]: Full config saved to ./output/config.yaml
[03/07 21:38:48 d2.utils.env]: Using a generated random seed 48437111

cfg.MODEL.WEIGHTS ./output/model_0024999.pth
cfg.OUTPUT_DIR ./output
[03/07 21:38:52 fvcore.common.checkpoint]: Loading checkpoint from ./output/model_0024999.pth
WARNING [03/07 21:38:52 fvcore.common.checkpoint]: Skip loading parameter 'sem_seg_head.predictor.weight' to the model due to incompatible shapes: (19, 256, 1, 1) in the checkpoint but (3, 256, 1, 1) in the model! You might want to double check if this is expected.
WARNING [03/07 21:38:52 fvcore.common.checkpoint]: Skip loading parameter 'sem_seg_head.predictor.bias' to the model due to incompatible shapes: (19,) in the checkpoint but (3,) in the model! You might want to double check if this is expected.
[03/07 21:38:52 fvcore.common.checkpoint]: Some model parameters or buffers are not found in the checkpoint:
sem_seg_head.predictor.{bias, weight}
[03/07 21:38:53 d2.data.dataset_mapper]: [DatasetMapper] Augmentations used in inference: [ResizeShortestEdge(short_edge_length=(1024, 1024), max_size=1024, sample_style='choice')]
[03/07 21:38:53 d2.data.common]: Serializing 933 elements to byte tensors and concatenating them all ...
[03/07 21:38:53 d2.data.common]: Serialized dataset takes 0.23 MiB
datasetname xbddata_test
WARNING [03/07 21:38:53 d2.evaluation.sem_seg_evaluation]: SemSegEvaluator(num_classes) is deprecated! It should be obtained from metadata.
WARNING [03/07 21:38:53 d2.evaluation.sem_seg_evaluation]: SemSegEvaluator(ignore_label) is deprecated! It should be obtained from metadata.
[03/07 21:38:54 d2.evaluation.evaluator]: Start inference on 933 images
[03/07 21:38:56 d2.evaluation.evaluator]: Inference done 11/933. 0.0817 s / img. ETA=0:01:55
[03/07 21:39:01 d2.evaluation.evaluator]: Inference done 51/933. 0.0817 s / img. ETA=0:01:50
[03/07 21:39:06 d2.evaluation.evaluator]: Inference done 70/933. 0.0817 s / img. ETA=0:02:26
[03/07 21:39:11 d2.evaluation.evaluator]: Inference done 110/933. 0.0818 s / img. ETA=0:02:06
[03/07 21:39:17 d2.evaluation.evaluator]: Inference done 150/933. 0.0818 s / img. ETA=0:01:54
[03/07 21:39:22 d2.evaluation.evaluator]: Inference done 190/933. 0.0819 s / img. ETA=0:01:45
[03/07 21:39:27 d2.evaluation.evaluator]: Inference done 229/933. 0.0820 s / img. ETA=0:01:38
[03/07 21:39:32 d2.evaluation.evaluator]: Inference done 270/933. 0.0820 s / img. ETA=0:01:30
[03/07 21:39:37 d2.evaluation.evaluator]: Inference done 310/933. 0.0819 s / img. ETA=0:01:24
[03/07 21:39:42 d2.evaluation.evaluator]: Inference done 351/933. 0.0819 s / img. ETA=0:01:18
[03/07 21:39:47 d2.evaluation.evaluator]: Inference done 391/933. 0.0819 s / img. ETA=0:01:12
[03/07 21:39:52 d2.evaluation.evaluator]: Inference done 432/933. 0.0819 s / img. ETA=0:01:06
[03/07 21:39:57 d2.evaluation.evaluator]: Inference done 473/933. 0.0819 s / img. ETA=0:01:00
[03/07 21:40:02 d2.evaluation.evaluator]: Inference done 514/933. 0.0819 s / img. ETA=0:00:54
[03/07 21:40:07 d2.evaluation.evaluator]: Inference done 554/933. 0.0818 s / img. ETA=0:00:49
[03/07 21:40:12 d2.evaluation.evaluator]: Inference done 595/933. 0.0818 s / img. ETA=0:00:44
[03/07 21:40:17 d2.evaluation.evaluator]: Inference done 636/933. 0.0818 s / img. ETA=0:00:38
[03/07 21:40:23 d2.evaluation.evaluator]: Inference done 677/933. 0.0818 s / img. ETA=0:00:33
[03/07 21:40:28 d2.evaluation.evaluator]: Inference done 717/933. 0.0818 s / img. ETA=0:00:27
[03/07 21:40:33 d2.evaluation.evaluator]: Inference done 758/933. 0.0818 s / img. ETA=0:00:22
[03/07 21:40:38 d2.evaluation.evaluator]: Inference done 799/933. 0.0818 s / img. ETA=0:00:17
[03/07 21:40:43 d2.evaluation.evaluator]: Inference done 840/933. 0.0818 s / img. ETA=0:00:11
[03/07 21:40:48 d2.evaluation.evaluator]: Inference done 881/933. 0.0818 s / img. ETA=0:00:06
[03/07 21:40:53 d2.evaluation.evaluator]: Inference done 922/933. 0.0818 s / img. ETA=0:00:01
[03/07 21:40:54 d2.evaluation.evaluator]: Total inference time: 0:01:59.094921 (0.128335 s / img per device, on 1 devices)
[03/07 21:40:54 d2.evaluation.evaluator]: Total inference pure compute time: 0:01:15 (0.081782 s / img per device, on 1 devices)
[03/07 21:40:56 d2.evaluation.sem_seg_evaluation]: OrderedDict([('sem_seg', {'mIoU': 14.286231780375028, 'fwIoU': 30.412502468859948, 'IoU-0': 31.958253593820217, 'IoU-1': 5.555678249276511, 'IoU-2': 5.344763498028353, 'mACC': 53.518182755044954, 'pACC': 34.17634953767668, 'ACC-0': 32.13264257356594, 'ACC-1': 69.63928432518483, 'ACC-2': 58.78262136638409})])
[03/07 21:40:56 d2.engine.defaults]: Evaluation results for xbddata_test in csv format:
[03/07 21:40:56 d2.evaluation.testing]: copypaste: Task: sem_seg
[03/07 21:40:56 d2.evaluation.testing]: copypaste: mIoU,fwIoU,mACC,pACC
[03/07 21:40:56 d2.evaluation.testing]: copypaste: 14.2862,30.4125,53.5182,34.1763