My reproduce results is slightly lower

[YanFangCS]

Hello, I use the config file you provide to reproduce on Pascal Voc dataset. But I got somehow slightly lower results in multiple dataset split setting. My reproduce result are as following.

And config file used in my experiment is as following.

{
    "name": "CAC",
    "experim_name": "cac_datalist0_1of8_3",
    "dataset": "voc",
    "data_dir": ###,
    "datalist": 3,
    "n_gpu": 4,
    "n_labeled_examples": 10582,
    "diff_lrs": true,
    "ramp_up": 0.1,
    "unsupervised_w": 30,
    "ignore_index": 255,
    "lr_scheduler": "Poly",
    "use_weak_lables":false,
    "weakly_loss_w": 0.4,
    "pretrained": true,
    "random_seed": 42,

    "model":{
        "supervised": false,
        "semi": true,
        "supervised_w": 1,

        "sup_loss": "CE",

        "layers": 101,
        "downsample": true,
        "proj_final_dim": 128,
        "out_dim": 256,
        "backbone": "deeplab_v3+",
        "pos_thresh_value": 0.75,
        "weight_unsup": 0.1,
        "epoch_start_unsup": 5,
        "selected_num": 3200,
        "temp": 0.1,
        "step_save": 2,
        "stride": 8
    },


    "optimizer": {
        "type": "SGD",
        "args":{
            "lr": 0.01,
            "weight_decay": 1e-4,
            "momentum": 0.9
        }
    },

    "train_supervised": {
        "batch_size": 8,
        "crop_size": 320,
        "shuffle": true,
        "base_size": 400,
        "scale": true,
        "augment": true,
        "flip": true,
        "rotate": false,
        "blur": false,
        "split": "train_supervised",
        "num_workers": 8
    },

    "train_unsupervised": {
        "batch_size": 8,
        "crop_size": 320,
        "shuffle": true,
        "base_size": 400,
        "scale": true,
        "augment": true,
        "flip": true,
        "rotate": false,
        "blur": false,
        "split": "train_unsupervised",
        "num_workers": 8,
        "iou_bound": [0.1, 1.0],
        "stride": 8
    },

    "val_loader": {
        "batch_size": 4,
        "val": true,
        "split": "val",
        "shuffle": false,
        "num_workers": 4
    },

    "trainer": {
        "epochs": 80,
        "save_dir": "saved/",
        "save_period": 1,
  
        "monitor": "max Mean_IoU",
        "early_stop": 100,
        
        "tensorboardX": true,
        "log_dir": "saved/",
        "log_per_iter": 20,

        "val": true,
        "val_per_epochs": 1
    }
}

Could you give me some advice about how to correctly reproduce your results?
Thanks a lot.

[X-Lai]

Thanks for your interest in our work. I think the performance gap may come from n_gpu, batch_size or selected_num. If you want to reproduce the results reported in our paper, I recommend you to use the given configs without any change.

[X-Lai]

Besides, note that the results reported in our paper are averaged from three runs on different datalists.

[YanFangCS]

Thanks for your suggestion, I will try again.