The beta value to use with the F-Beta Measure (0.5)ĭropout values to use in the DeepLabV3+ (0.3 0.5) Use wce_dice for exponentially weighted boundary loss Please replace this with the root folder of the dataset samples The dataset to train / evaluate on (other choices: spaceNet, crowdAI, combined) The DeeplabV3+ backbone (final method used drn_c42) We employ the following primary command-line arguments: Parameter To train / evaluate the DeepLabV3+ models described in the paper, please use train_deeplab.sh or test_deeplab.sh for your convenience. Note: these maps are not required for evaluation / testing. Please decrease this value if you notice very high memory usage. The inc parameter is specified for computational reasons. Please use datasets/converters/weighted_boundary_processor.py and follow the example usage. In order to train with the exponentially weighted boundary loss, you will need to create the weight maps as a pre-processing step. For SpaceNet, use datasets/converters/spaceNetDataConverter.py.
For Urban3D, use datasets/converters/urban3dDataConverter.py.For AICrowd, use datasets/converters/cocoAnnotationToMask.py.
#SPACENET DATASET HOW TO#
For all converters, please look at the individual files for an example of how to use them. Please use our provided dataset converters to process the datasets. Tar xvf /SpaceNet/Vegas/AOI_2_Vegas_Test_ Tar xvf /SpaceNet/Vegas/SN2_buildings_train_AOI_2_ Aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/SN2_buildings_train_AOI_2_ /SpaceNet/Vegas/Īws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/AOI_2_Vegas_Test_ /SpaceNet/Vegas/
0 kommentar(er)
