Python Generic_MIL_Dataset示例

示例#1

}

with open(args.save_dir + '/eval_experiment_{}.txt'.format(args.save_exp_code),
          'w') as f:
    print(settings, file=f)
f.close()

print(settings)
if args.task == 'task_1_tumor_vs_normal':
    args.n_classes = 2
    dataset = Generic_MIL_Dataset(
        csv_path='dataset_csv/tumor_vs_normal_dummy_clean.csv',
        data_dir=os.path.join(args.data_root_dir,
                              'tumor_vs_normal_resnet_features'),
        shuffle=False,
        print_info=True,
        label_dict={
            'normal_tissue': 0,
            'tumor_tissue': 1
        },
        patient_strat=False,
        ignore=[])

elif args.task == 'task_2_tumor_subtyping':
    args.n_classes = 3
    dataset = Generic_MIL_Dataset(
        csv_path='dataset_csv/tumor_subtyping_dummy_clean.csv',
        data_dir=os.path.join(args.data_root_dir,
                              'tumor_subtyping_resnet_features'),
        shuffle=False,
        print_info=True,
        label_dict={

示例#2

    settings.update({
        'bag_weight': args.bag_weight,
        'inst_loss': args.inst_loss,
        'B': args.B
    })

print('\nLoad Dataset')
if args.task == 'camelyon_40x_cv':
    args.n_classes = 2
    dataset = Generic_MIL_Dataset(csv_path='dataset_csv/camelyon_clean.csv',
                                  data_dir=os.path.join(
                                      args.data_root_dir,
                                      'camelyon_feat_resnet'),
                                  shuffle=False,
                                  seed=args.seed,
                                  print_info=True,
                                  label_dict={
                                      'normal_tissue': 0,
                                      'tumor_tissue': 1
                                  },
                                  patient_strat=False,
                                  ignore=[])

elif args.task == 'tcga_kidney_cv':
    args.n_classes = 3
    dataset = Generic_MIL_Dataset(csv_path='dataset_csv/tcga_kidney_clean.csv',
                                  data_dir=os.path.join(
                                      args.data_root_dir,
                                      'tcga_kidney_resnet_features'),
                                  shuffle=False,
                                  seed=args.seed,

示例#3

        'bag_weight': args.bag_weight,
        'inst_loss': args.inst_loss,
        'B': args.B
    })

print('\nLoad Dataset')

if args.task == 'task_1_tumor_vs_normal':
    args.n_classes = 2
    dataset = Generic_MIL_Dataset(
        csv_path='dataset_csv/tumor_vs_normal_dummy_clean.csv',
        data_dir=os.path.join(args.data_root_dir,
                              'tumor_vs_normal_resnet_features'),
        shuffle=False,
        seed=args.seed,
        print_info=True,
        label_dict={
            'normal_tissue': 0,
            'tumor_tissue': 1
        },
        patient_strat=False,
        ignore=[])

elif args.task == 'task_2_tumor_subtyping':
    args.n_classes = 3
    dataset = Generic_MIL_Dataset(
        csv_path='dataset_csv/tumor_subtyping_dummy_clean.csv',
        data_dir=os.path.join(args.data_root_dir,
                              'tumor_subtyping_resnet_features'),
        shuffle=False,
        seed=args.seed,

示例#4

文件： eval.py 项目： yangsenwxy/CLAM

}

with open(args.save_dir + '/eval_experiment_{}.txt'.format(args.save_exp_code),
          'w') as f:
    print(settings, file=f)
f.close()

print(settings)
if args.task == 'camelyon_40x_cv':
    args.n_classes = 2
    dataset = Generic_MIL_Dataset(csv_path='dataset_csv/camelyon_clean.csv',
                                  data_dir=os.path.join(
                                      args.data_root_dir,
                                      'camelyon_40x_resnet_features'),
                                  shuffle=False,
                                  print_info=True,
                                  label_dict={
                                      'normal_tissue': 0,
                                      'tumor_tissue': 1
                                  },
                                  patient_strat=False,
                                  ignore=[])

elif args.task == 'tcga_kidney_cv':
    args.n_classes = 3
    dataset = Generic_MIL_Dataset(csv_path='dataset_csv/tcga_kidney_clean.csv',
                                  data_dir=os.path.join(
                                      args.data_root_dir,
                                      'tcga_kidney_resnet_features'),
                                  shuffle=False,
                                  print_info=True,
                                  label_dict={

示例#5

文件： main.py 项目： zaid478/MSDS19006_Project_DLSpring2020

    'model_size': args.model_size,
    "use_drop_out": args.drop_out,
    'weighted_sample': args.weighted_sample,
    'opt': args.opt
}

print('\nLoad Dataset')
if args.task == 'camelyon_40x_cv':
    args.n_classes = 2
    dataset = Generic_MIL_Dataset(csv_path='dataset_csv/camelyon_clean.csv',
                                  data_dir=os.path.join(
                                      args.data_root_dir,
                                      'camelyon_feat_resnet'),
                                  shuffle=False,
                                  seed=args.seed,
                                  print_info=True,
                                  label_dict={
                                      'normal_tissue': 0,
                                      'tumor_tissue': 1
                                  },
                                  patient_strat=False,
                                  ignore=[])

elif args.task == 'colon_cancer':
    args.n_classes = 2
    dataset = Generic_MIL_Dataset(
        csv_path='dataset_csv/label_information_colon.csv',
        data_dir=os.path.join(args.data_root_dir, 'resnet_features_colon'),
        shuffle=False,
        seed=args.seed,
        print_info=True,

示例#6

            'subtype_1': 0,
            'subtype_2': 1,
            'subtype_3': 2
        },
        patient_strat=True,
        patient_voting='maj',
        ignore=[])

elif args.task == 'hpa':

    args.n_classes = 19
    dataset = Generic_MIL_Dataset(csv_path='/content/label_df.csv',
                                  data_dir='/content/feature',
                                  shuffle=False,
                                  seed=args.seed,
                                  print_info=True,
                                  label_dict={i: i
                                              for i in range(19)},
                                  patient_strat=False,
                                  ignore=[],
                                  hpa=True)

else:
    raise NotImplementedError

num_slides_cls = np.array(
    [len(cls_ids) for cls_ids in dataset.patient_cls_ids])
val_num = np.round(num_slides_cls * args.val_frac).astype(int)
test_num = np.round(num_slides_cls * args.test_frac).astype(int)

if __name__ == '__main__':
    if args.label_frac > 0: