get only mIOU 73.8% of PSPNet？

[ianz27]

I only change some data dir BUT could NOT reproduce the result of 78.20

here is the log:

---

Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.

---

2020-02-20 11:32:31,088 INFO [main.py, 163] BN Type is batchnorm.
2020-02-20 11:32:31,092 INFO [main.py, 164] Config Dict: {
"dataset": "cityscapes",
"task": "seg",
"method": "fcn_segmentor",
"data": {
"image_tool": "cv2",
"input_mode": "BGR",
"num_classes": 19,
"label_list": [
7,
8,
11,
12,
13,
17,
19,
20,
21,
22,
23,
24,
25,
26,
27,
28,
31,
32,
33
],
"data_dir": "/home/MONSTER_SHARE/ZQ/dataset/cityscapes/torchcv",
"workers": 8,
"mean_value": [
103,
116,
123
],
"normalize": {
"div_value": 1.0,
"mean": [
102.9801,
115.9465,
122.7717
],
"std": [
1.0,
1.0,
1.0
]
},
"tag": null,
"include_val": false,
"drop_last": true
},
"train": {
"batch_size": 1,
"aug_trans": {
"trans_seq": [
"random_resize",
"random_crop",
"random_brightness",
"random_hflip"
],
"random_brightness": {
"ratio": 1.0,
"shift_value": 10
},
"random_hflip": {
"ratio": 0.5,
"swap_pair": []
},
"random_resize": {
"ratio": 1.0,
"method": "random",
"scale_range": [
0.5,
2.0
],
"aspect_range": [
0.9,
1.1
]
},
"random_crop": {
"ratio": 1.0,
"crop_size": [
769,
769
],
"method": "random",
"allow_outside_center": false
}
},
"data_transformer": {
"size_mode": "fix_size",
"input_size": [
769,
769
],
"align_method": "only_pad",
"pad_mode": "random"
}
},
"val": {
"batch_size": 1,
"aug_trans": {
"trans_seq": []
},
"data_transformer": {
"size_mode": "fix_size",
"input_size": [
2048,
1024
],
"align_method": "only_pad"
}
},
"test": {
"aug_trans": {
"trans_seq": []
},
"batch_size": 4,
"data_transformer": {
"size_mode": "none"
},
"mscrop_test": {
"scale_search": [
0.75,
1.0,
1.25
],
"crop_stride_ratio": 0.667,
"crop_size": [
864,
864
]
},
"ms_test": {
"scale_search": [
0.75,
1.0,
1.25
]
},
"mode": "ss_test",
"test_dir": null,
"out_dir": "none"
},
"details": {
"color_list": [
[
128,
64,
128
],
[
244,
35,
232
],
[
70,
70,
70
],
[
102,
102,
156
],
[
190,
153,
153
],
[
153,
153,
153
],
[
250,
170,
30
],
[
220,
220,
0
],
[
107,
142,
35
],
[
152,
251,
152
],
[
70,
130,
180
],
[
220,
20,
60
],
[
255,
0,
0
],
[
0,
0,
142
],
[
0,
0,
70
],
[
0,
60,
100
],
[
0,
80,
100
],
[
0,
0,
230
],
[
119,
11,
32
]
]
},
"network": {
"backbone": "deepbase_resnet101_d8",
"multi_grid": [
1,
1,
1
],
"model_name": "pspnet",
"norm_type": "batchnorm",
"stride": 8,
"checkpoints_name": "fs_pspnet_cityscapes_segtask_1",
"checkpoints_dir": "./checkpoints/seg/cityscapes",
"checkpoints_root": null,
"syncbn": true,
"pretrained": "./pretrained_models/3x3resnet101-imagenet.pth",
"resume": null,
"resume_strict": true,
"resume_continue": false,
"resume_val": false,
"gather": true,
"distributed": true
},
"solver": {
"lr": {
"base_lr": 0.01,
"metric": "iters",
"lr_policy": "lambda_poly",
"lambda_poly": {
"power": 0.9
},
"lambda_range": {
"max_power": 2.0
},
"bb_lr_scale": 1.0,
"nbb_mult": 1.0
},
"optim": {
"optim_method": "sgd",
"sgd": {
"weight_decay": 0.0005,
"momentum": 0.9,
"nesterov": false
}
},
"display_iter": 50,
"save_iters": 1000,
"test_interval": 1000,
"max_iters": 40000,
"max_epoch": null,
"save_epoch": null
},
"loss": {
"loss_type": "dsnce_loss",
"loss_weights": {
"ce_loss": {
"ce_loss": 1.0
},
"dsnce_loss": {
"ce_loss": 1.0,
"dsn_ce_loss": 0.4
},
"dsnohemce_loss": {
"ohem_ce_loss": 1.0,
"dsn_ce_loss": 0.4
}
},
"params": {
"ce_loss": {
"weight": [
0.8373,
0.918,
0.866,
1.0345,
1.0166,
0.9969,
0.9754,
1.0489,
0.8786,
1.0023,
0.9539,
0.9843,
1.1116,
0.9037,
1.0865,
1.0955,
1.0865,
1.1529,
1.0507
],
"reduction": "mean",
"ignore_index": -1
},
"ohem_ce_loss": {
"weight": [
0.8373,
0.918,
0.866,
1.0345,
1.0166,
0.9969,
0.9754,
1.0489,
0.8786,
1.0023,
0.9539,
0.9843,
1.1116,
0.9037,
1.0865,
1.0955,
1.0865,
1.1529,
1.0507
],
"reduction": "mean",
"ignore_index": -1,
"thresh": 0.7,
"minkeep": 100000
}
}
},
"config_file": "configs/seg/cityscapes/base_fcn_cityscapes_seg.conf",
"phase": "train",
"gpu": [
0,
1,
2,
3
],
"logging": {
"log_level": "info",
"log_format": "%(asctime)s %(levelname)-7s %(message)s"
},
"seed": null,
"cudnn": true,
"local_rank": 0,
"project_dir": "/home/z00496510/work/torchcv"
}
2020-02-20 11:32:31,888 INFO [module_helper.py, 124] Loading pretrained model:./pretrained_models/3x3resnet101-imagenet.pth
2020-02-20 11:32:32,031 INFO [module_helper.py, 147] Matched Keys: dict_keys(['conv1.weight', 'bn1.running_mean', 'bn1.running_var', 'bn1.weight', 'bn1.bias', 'layer1.0.conv1.weight', 'layer1.0.bn1.running_mean', 'layer1.0.bn1.running_var', 'layer1.0.bn1.weight', 'layer1.0.bn1.bias', 'layer1.0.conv2.weight', 'layer1.0.bn2.running_mean', 'layer1.0.bn2.running_var', 'layer1.0.bn2.weight', 'layer1.0.bn2.bias', 'layer1.0.conv3.weight', 'layer1.0.bn3.running_mean', 'layer1.0.bn3.running_var', 'layer1.0.bn3.weight', 'layer1.0.bn3.bias', 'layer1.0.downsample.0.weight', 'layer1.0.downsample.1.running_mean', 'layer1.0.downsample.1.running_var', 'layer1.0.downsample.1.weight', 'layer1.0.downsample.1.bias', 'layer1.1.conv1.weight', 'layer1.1.bn1.running_mean', 'layer1.1.bn1.running_var', 'layer1.1.bn1.weight', 'layer1.1.bn1.bias', 'layer1.1.conv2.weight', 'layer1.1.bn2.running_mean', 'layer1.1.bn2.running_var', 'layer1.1.bn2.weight', 'layer1.1.bn2.bias', 'layer1.1.conv3.weight', 'layer1.1.bn3.running_mean', 'layer1.1.bn3.running_var', 'layer1.1.bn3.weight', 'layer1.1.bn3.bias', 'layer1.2.conv1.weight', 'layer1.2.bn1.running_mean', 'layer1.2.bn1.running_var', 'layer1.2.bn1.weight', 'layer1.2.bn1.bias', 'layer1.2.conv2.weight', 'layer1.2.bn2.running_mean', 'layer1.2.bn2.running_var', 'layer1.2.bn2.weight', 'layer1.2.bn2.bias', 'layer1.2.conv3.weight', 'layer1.2.bn3.running_mean', 'layer1.2.bn3.running_var', 'layer1.2.bn3.weight', 'layer1.2.bn3.bias', 'layer2.0.conv1.weight', 'layer2.0.bn1.running_mean', 'layer2.0.bn1.running_var', 'layer2.0.bn1.weight', 'layer2.0.bn1.bias', 'layer2.0.conv2.weight', 'layer2.0.bn2.running_mean', 'layer2.0.bn2.running_var', 'layer2.0.bn2.weight', 'layer2.0.bn2.bias', 'layer2.0.conv3.weight', 'layer2.0.bn3.running_mean', 'layer2.0.bn3.running_var', 'layer2.0.bn3.weight', 'layer2.0.bn3.bias', 'layer2.0.downsample.0.weight', 'layer2.0.downsample.1.running_mean', 'layer2.0.downsample.1.running_var', 'layer2.0.downsample.1.weight', 'layer2.0.downsample.1.bias', 'layer2.1.conv1.weight', 'layer2.1.bn1.running_mean', 'layer2.1.bn1.running_var', 'layer2.1.bn1.weight', 'layer2.1.bn1.bias', 'layer2.1.conv2.weight', 'layer2.1.bn2.running_mean', 'layer2.1.bn2.running_var', 'layer2.1.bn2.weight', 'layer2.1.bn2.bias', 'layer2.1.conv3.weight', 'layer2.1.bn3.running_mean', 'layer2.1.bn3.running_var', 'layer2.1.bn3.weight', 'layer2.1.bn3.bias', 'layer2.2.conv1.weight', 'layer2.2.bn1.running_mean', 'layer2.2.bn1.running_var', 'layer2.2.bn1.weight', 'layer2.2.bn1.bias', 'layer2.2.conv2.weight', 'layer2.2.bn2.running_mean', 'layer2.2.bn2.running_var', 'layer2.2.bn2.weight', 'layer2.2.bn2.bias', 'layer2.2.conv3.weight', 'layer2.2.bn3.running_mean', 'layer2.2.bn3.running_var', 'layer2.2.bn3.weight', 'layer2.2.bn3.bias', 'layer2.3.conv1.weight', 'layer2.3.bn1.running_mean', 'layer2.3.bn1.running_var', 'layer2.3.bn1.weight', 'layer2.3.bn1.bias', 'layer2.3.conv2.weight', 'layer2.3.bn2.running_mean', 'layer2.3.bn2.running_var', 'layer2.3.bn2.weight', 'layer2.3.bn2.bias', 'layer2.3.conv3.weight', 'layer2.3.bn3.running_mean', 'layer2.3.bn3.running_var', 'layer2.3.bn3.weight', 'layer2.3.bn3.bias', 'layer3.0.conv1.weight', 'layer3.0.bn1.running_mean', 'layer3.0.bn1.running_var', 'layer3.0.bn1.weight', 'layer3.0.bn1.bias', 'layer3.0.conv2.weight', 'layer3.0.bn2.running_mean', 'layer3.0.bn2.running_var', 'layer3.0.bn2.weight', 'layer3.0.bn2.bias', 'layer3.0.conv3.weight', 'layer3.0.bn3.running_mean', 'layer3.0.bn3.running_var', 'layer3.0.bn3.weight', 'layer3.0.bn3.bias', 'layer3.0.downsample.0.weight', 'layer3.0.downsample.1.running_mean', 'layer3.0.downsample.1.running_var', 'layer3.0.downsample.1.weight', 'layer3.0.downsample.1.bias', 'layer3.1.conv1.weight', 'layer3.1.bn1.running_mean', 'layer3.1.bn1.running_var', 'layer3.1.bn1.weight', 'layer3.1.bn1.bias', 'layer3.1.conv2.weight', 'layer3.1.bn2.running_mean', 'layer3.1.bn2.running_var', 'layer3.1.bn2.weight', 'layer3.1.bn2.bias', 'layer3.1.conv3.weight', 'layer3.1.bn3.running_mean', 'layer3.1.bn3.running_var', 'layer3.1.bn3.weight', 'layer3.1.bn3.bias', 'layer3.2.conv1.weight', 'layer3.2.bn1.running_mean', 'layer3.2.bn1.running_var', 'layer3.2.bn1.weight', 'layer3.2.bn1.bias', 'layer3.2.conv2.weight', 'layer3.2.bn2.running_mean', 'layer3.2.bn2.running_var', 'layer3.2.bn2.weight', 'layer3.2.bn2.bias', 'layer3.2.conv3.weight', 'layer3.2.bn3.running_mean', 'layer3.2.bn3.running_var', 'layer3.2.bn3.weight', 'layer3.2.bn3.bias', 'layer3.3.conv1.weight', 'layer3.3.bn1.running_mean', 'layer3.3.bn1.running_var', 'layer3.3.bn1.weight', 'layer3.3.bn1.bias', 'layer3.3.conv2.weight', 'layer3.3.bn2.running_mean', 'layer3.3.bn2.running_var', 'layer3.3.bn2.weight', 'layer3.3.bn2.bias', 'layer3.3.conv3.weight', 'layer3.3.bn3.running_mean', 'layer3.3.bn3.running_var', 'layer3.3.bn3.weight', 'layer3.3.bn3.bias', 'layer3.4.conv1.weight', 'layer3.4.bn1.running_mean', 'layer3.4.bn1.running_var', 'layer3.4.bn1.weight', 'layer3.4.bn1.bias', 'layer3.4.conv2.weight', 'layer3.4.bn2.running_mean', 'layer3.4.bn2.running_var', 'layer3.4.bn2.weight', 'layer3.4.bn2.bias', 'layer3.4.conv3.weight', 'layer3.4.bn3.running_mean', 'layer3.4.bn3.running_var', 'layer3.4.bn3.weight', 'layer3.4.bn3.bias', 'layer3.5.conv1.weight', 'layer3.5.bn1.running_mean', 'layer3.5.bn1.running_var', 'layer3.5.bn1.weight', 'layer3.5.bn1.bias', 'layer3.5.conv2.weight', 'layer3.5.bn2.running_mean', 'layer3.5.bn2.running_var', 'layer3.5.bn2.weight', 'layer3.5.bn2.bias', 'layer3.5.conv3.weight', 'layer3.5.bn3.running_mean', 'layer3.5.bn3.running_var', 'layer3.5.bn3.weight', 'layer3.5.bn3.bias', 'layer3.6.conv1.weight', 'layer3.6.bn1.running_mean', 'layer3.6.bn1.running_var', 'layer3.6.bn1.weight', 'layer3.6.bn1.bias', 'layer3.6.conv2.weight', 'layer3.6.bn2.running_mean', 'layer3.6.bn2.running_var', 'layer3.6.bn2.weight', 'layer3.6.bn2.bias', 'layer3.6.conv3.weight', 'layer3.6.bn3.running_mean', 'layer3.6.bn3.running_var', 'layer3.6.bn3.weight', 'layer3.6.bn3.bias', 'layer3.7.conv1.weight', 'layer3.7.bn1.running_mean', 'layer3.7.bn1.running_var', 'layer3.7.bn1.weight', 'layer3.7.bn1.bias', 'layer3.7.conv2.weight', 'layer3.7.bn2.running_mean', 'layer3.7.bn2.running_var', 'layer3.7.bn2.weight', 'layer3.7.bn2.bias', 'layer3.7.conv3.weight', 'layer3.7.bn3.running_mean', 'layer3.7.bn3.running_var', 'layer3.7.bn3.weight', 'layer3.7.bn3.bias', 'layer3.8.conv1.weight', 'layer3.8.bn1.running_mean', 'layer3.8.bn1.running_var', 'layer3.8.bn1.weight', 'layer3.8.bn1.bias', 'layer3.8.conv2.weight', 'layer3.8.bn2.running_mean', 'layer3.8.bn2.running_var', 'layer3.8.bn2.weight', 'layer3.8.bn2.bias', 'layer3.8.conv3.weight', 'layer3.8.bn3.running_mean', 'layer3.8.bn3.running_var', 'layer3.8.bn3.weight', 'layer3.8.bn3.bias', 'layer3.9.conv1.weight', 'layer3.9.bn1.running_mean', 'layer3.9.bn1.running_var', 'layer3.9.bn1.weight', 'layer3.9.bn1.bias', 'layer3.9.conv2.weight', 'layer3.9.bn2.running_mean', 'layer3.9.bn2.running_var', 'layer3.9.bn2.weight', 'layer3.9.bn2.bias', 'layer3.9.conv3.weight', 'layer3.9.bn3.running_mean', 'layer3.9.bn3.running_var', 'layer3.9.bn3.weight', 'layer3.9.bn3.bias', 'layer3.10.conv1.weight', 'layer3.10.bn1.running_mean', 'layer3.10.bn1.running_var', 'layer3.10.bn1.weight', 'layer3.10.bn1.bias', 'layer3.10.conv2.weight', 'layer3.10.bn2.running_mean', 'layer3.10.bn2.running_var', 'layer3.10.bn2.weight', 'layer3.10.bn2.bias', 'layer3.10.conv3.weight', 'layer3.10.bn3.running_mean', 'layer3.10.bn3.running_var', 'layer3.10.bn3.weight', 'layer3.10.bn3.bias', 'layer3.11.conv1.weight', 'layer3.11.bn1.running_mean', 'layer3.11.bn1.running_var', 'layer3.11.bn1.weight', 'layer3.11.bn1.bias', 'layer3.11.conv2.weight', 'layer3.11.bn2.running_mean', 'layer3.11.bn2.running_var', 'layer3.11.bn2.weight', 'layer3.11.bn2.bias', 'layer3.11.conv3.weight', 'layer3.11.bn3.running_mean', 'layer3.11.bn3.running_var', 'layer3.11.bn3.weight', 'layer3.11.bn3.bias', 'layer3.12.conv1.weight', 'layer3.12.bn1.running_mean', 'layer3.12.bn1.running_var', 'layer3.12.bn1.weight', 'layer3.12.bn1.bias', 'layer3.12.conv2.weight', 'layer3.12.bn2.running_mean', 'layer3.12.bn2.running_var', 'layer3.12.bn2.weight', 'layer3.12.bn2.bias', 'layer3.12.conv3.weight', 'layer3.12.bn3.running_mean', 'layer3.12.bn3.running_var', 'layer3.12.bn3.weight', 'layer3.12.bn3.bias', 'layer3.13.conv1.weight', 'layer3.13.bn1.running_mean', 'layer3.13.bn1.running_var', 'layer3.13.bn1.weight', 'layer3.13.bn1.bias', 'layer3.13.conv2.weight', 'layer3.13.bn2.running_mean', 'layer3.13.bn2.running_var', 'layer3.13.bn2.weight', 'layer3.13.bn2.bias', 'layer3.13.conv3.weight', 'layer3.13.bn3.running_mean', 'layer3.13.bn3.running_var', 'layer3.13.bn3.weight', 'layer3.13.bn3.bias', 'layer3.14.conv1.weight', 'layer3.14.bn1.running_mean', 'layer3.14.bn1.running_var', 'layer3.14.bn1.weight', 'layer3.14.bn1.bias', 'layer3.14.conv2.weight', 'layer3.14.bn2.running_mean', 'layer3.14.bn2.running_var', 'layer3.14.bn2.weight', 'layer3.14.bn2.bias', 'layer3.14.conv3.weight', 'layer3.14.bn3.running_mean', 'layer3.14.bn3.running_var', 'layer3.14.bn3.weight', 'layer3.14.bn3.bias', 'layer3.15.conv1.weight', 'layer3.15.bn1.running_mean', 'layer3.15.bn1.running_var', 'layer3.15.bn1.weight', 'layer3.15.bn1.bias', 'layer3.15.conv2.weight', 'layer3.15.bn2.running_mean', 'layer3.15.bn2.running_var', 'layer3.15.bn2.weight', 'layer3.15.bn2.bias', 'layer3.15.conv3.weight', 'layer3.15.bn3.running_mean', 'layer3.15.bn3.running_var', 'layer3.15.bn3.weight', 'layer3.15.bn3.bias', 'layer3.16.conv1.weight', 'layer3.16.bn1.running_mean', 'layer3.16.bn1.running_var', 'layer3.16.bn1.weight', 'layer3.16.bn1.bias', 'layer3.16.conv2.weight', 'layer3.16.bn2.running_mean', 'layer3.16.bn2.running_var', 'layer3.16.bn2.weight', 'layer3.16.bn2.bias', 'layer3.16.conv3.weight', 'layer3.16.bn3.running_mean', 'layer3.16.bn3.running_var', 'layer3.16.bn3.weight', 'layer3.16.bn3.bias', 'layer3.17.conv1.weight', 'layer3.17.bn1.running_mean', 'layer3.17.bn1.running_var', 'layer3.17.bn1.weight', 'layer3.17.bn1.bias', 'layer3.17.conv2.weight', 'layer3.17.bn2.running_mean', 'layer3.17.bn2.running_var', 'layer3.17.bn2.weight', 'layer3.17.bn2.bias', 'layer3.17.conv3.weight', 'layer3.17.bn3.running_mean', 'layer3.17.bn3.running_var', 'layer3.17.bn3.weight', 'layer3.17.bn3.bias', 'layer3.18.conv1.weight', 'layer3.18.bn1.running_mean', 'layer3.18.bn1.running_var', 'layer3.18.bn1.weight', 'layer3.18.bn1.bias', 'layer3.18.conv2.weight', 'layer3.18.bn2.running_mean', 'layer3.18.bn2.running_var', 'layer3.18.bn2.weight', 'layer3.18.bn2.bias', 'layer3.18.conv3.weight', 'layer3.18.bn3.running_mean', 'layer3.18.bn3.running_var', 'layer3.18.bn3.weight', 'layer3.18.bn3.bias', 'layer3.19.conv1.weight', 'layer3.19.bn1.running_mean', 'layer3.19.bn1.running_var', 'layer3.19.bn1.weight', 'layer3.19.bn1.bias', 'layer3.19.conv2.weight', 'layer3.19.bn2.running_mean', 'layer3.19.bn2.running_var', 'layer3.19.bn2.weight', 'layer3.19.bn2.bias', 'layer3.19.conv3.weight', 'layer3.19.bn3.running_mean', 'layer3.19.bn3.running_var', 'layer3.19.bn3.weight', 'layer3.19.bn3.bias', 'layer3.20.conv1.weight', 'layer3.20.bn1.running_mean', 'layer3.20.bn1.running_var', 'layer3.20.bn1.weight', 'layer3.20.bn1.bias', 'layer3.20.conv2.weight', 'layer3.20.bn2.running_mean', 'layer3.20.bn2.running_var', 'layer3.20.bn2.weight', 'layer3.20.bn2.bias', 'layer3.20.conv3.weight', 'layer3.20.bn3.running_mean', 'layer3.20.bn3.running_var', 'layer3.20.bn3.weight', 'layer3.20.bn3.bias', 'layer3.21.conv1.weight', 'layer3.21.bn1.running_mean', 'layer3.21.bn1.running_var', 'layer3.21.bn1.weight', 'layer3.21.bn1.bias', 'layer3.21.conv2.weight', 'layer3.21.bn2.running_mean', 'layer3.21.bn2.running_var', 'layer3.21.bn2.weight', 'layer3.21.bn2.bias', 'layer3.21.conv3.weight', 'layer3.21.bn3.running_mean', 'layer3.21.bn3.running_var', 'layer3.21.bn3.weight', 'layer3.21.bn3.bias', 'layer3.22.conv1.weight', 'layer3.22.bn1.running_mean', 'layer3.22.bn1.running_var', 'layer3.22.bn1.weight', 'layer3.22.bn1.bias', 'layer3.22.conv2.weight', 'layer3.22.bn2.running_mean', 'layer3.22.bn2.running_var', 'layer3.22.bn2.weight', 'layer3.22.bn2.bias', 'layer3.22.conv3.weight', 'layer3.22.bn3.running_mean', 'layer3.22.bn3.running_var', 'layer3.22.bn3.weight', 'layer3.22.bn3.bias', 'layer4.0.conv1.weight', 'layer4.0.bn1.running_mean', 'layer4.0.bn1.running_var', 'layer4.0.bn1.weight', 'layer4.0.bn1.bias', 'layer4.0.conv2.weight', 'layer4.0.bn2.running_mean', 'layer4.0.bn2.running_var', 'layer4.0.bn2.weight', 'layer4.0.bn2.bias', 'layer4.0.conv3.weight', 'layer4.0.bn3.running_mean', 'layer4.0.bn3.running_var', 'layer4.0.bn3.weight', 'layer4.0.bn3.bias', 'layer4.0.downsample.0.weight', 'layer4.0.downsample.1.running_mean', 'layer4.0.downsample.1.running_var', 'layer4.0.downsample.1.weight', 'layer4.0.downsample.1.bias', 'layer4.1.conv1.weight', 'layer4.1.bn1.running_mean', 'layer4.1.bn1.running_var', 'layer4.1.bn1.weight', 'layer4.1.bn1.bias', 'layer4.1.conv2.weight', 'layer4.1.bn2.running_mean', 'layer4.1.bn2.running_var', 'layer4.1.bn2.weight', 'layer4.1.bn2.bias', 'layer4.1.conv3.weight', 'layer4.1.bn3.running_mean', 'layer4.1.bn3.running_var', 'layer4.1.bn3.weight', 'layer4.1.bn3.bias', 'layer4.2.conv1.weight', 'layer4.2.bn1.running_mean', 'layer4.2.bn1.running_var', 'layer4.2.bn1.weight', 'layer4.2.bn1.bias', 'layer4.2.conv2.weight', 'layer4.2.bn2.running_mean', 'layer4.2.bn2.running_var', 'layer4.2.bn2.weight', 'layer4.2.bn2.bias', 'layer4.2.conv3.weight', 'layer4.2.bn3.running_mean', 'layer4.2.bn3.running_var', 'layer4.2.bn3.weight', 'layer4.2.bn3.bias', 'fc.weight', 'fc.bias', 'conv2.weight', 'bn2.weight', 'bn2.bias', 'bn2.running_mean', 'bn2.running_var', 'conv3.weight', 'bn3.weight', 'bn3.bias', 'bn3.running_mean', 'bn3.running_var'])
2020-02-20 11:32:33,310 INFO [runner_helper.py, 38] Converting syncbn model...
2020-02-20 11:32:43,330 INFO [controller.py, 28] Training start...
2020-02-20 11:33:53,313 INFO [fcn_segmentor.py, 108] Train Epoch: 0 Train Iteration: 50 Time 69.980s / 50iters, (1.400) Data load 1.257s / 50iters, (0.025133)
Learning rate = [0.00998897432441524, 0.00998897432441524] Loss = {dsn_ce_loss: 1.3799, ce_loss: 1.3481, loss: 1.9001}

2020-02-20 11:34:35,003 INFO [fcn_segmentor.py, 108] Train Epoch: 0 Train Iteration: 100 Time 41.689s / 50iters, (0.834) Data load 0.027s / 50iters, (0.000536)
Learning rate = [0.009977722240963943, 0.009977722240963943] Loss = {dsn_ce_loss: 0.9367, ce_loss: 0.9765, loss: 1.3512}

2020-02-20 11:35:17,380 INFO [fcn_segmentor.py, 108] Train Epoch: 0 Train Iteration: 150 Time 42.377s / 50iters, (0.848) Data load 0.029s / 50iters, (0.000586)
Learning rate = [0.009966468747423728, 0.009966468747423728] Loss = {dsn_ce_loss: 0.7861, ce_loss: 0.7230, loss: 1.0375}

2020-02-20 11:35:59,352 INFO [fcn_segmentor.py, 108] Train Epoch: 0 Train Iteration: 200 Time 41.971s / 50iters, (0.839) Data load 0.028s / 50iters, (0.000555)
Learning rate = [0.00995521384184835, 0.00995521384184835] Loss = {dsn_ce_loss: 0.6903, ce_loss: 0.7181, loss: 0.9943}

2020-02-20 11:36:40,723 INFO [fcn_segmentor.py, 108] Train Epoch: 0 Train Iteration: 250 Time 41.371s / 50iters, (0.827) Data load 0.026s / 50iters, (0.000523)
Learning rate = [0.009943957522286433, 0.009943957522286433] Loss = {dsn_ce_loss: 0.8396, ce_loss: 0.8374, loss: 1.1732}

2020-02-20 11:37:22,195 INFO [fcn_segmentor.py, 108] Train Epoch: 0 Train Iteration: 300 Time 41.471s / 50iters, (0.829) Data load 0.026s / 50iters, (0.000524)
Learning rate = [0.00993269978678144, 0.00993269978678144] Loss = {dsn_ce_loss: 0.6848, ce_loss: 0.6377, loss: 0.9117}

2020-02-20 11:38:04,147 INFO [fcn_segmentor.py, 108] Train Epoch: 0 Train Iteration: 350 Time 41.952s / 50iters, (0.839) Data load 0.033s / 50iters, (0.000659)
Learning rate = [0.009921440633371664, 0.009921440633371664] Loss = {dsn_ce_loss: 0.5995, ce_loss: 0.5507, loss: 0.7905}

2020-02-20 11:38:46,001 INFO [fcn_segmentor.py, 108] Train Epoch: 0 Train Iteration: 400 Time 41.853s / 50iters, (0.837) Data load 0.026s / 50iters, (0.000519)
Learning rate = [0.0099101800600902, 0.0099101800600902] Loss = {dsn_ce_loss: 0.5772, ce_loss: 0.5757, loss: 0.8066}

..............

2020-02-20 21:12:24,048 INFO [fcn_segmentor.py, 108] Train Epoch: 53 Train Iteration: 40000 Time 42.007s / 50iters, (0.840) Data load 0.041s / 50iters, (0.000817)
Learning rate = [7.213499529549767e-07, 7.213499529549767e-07] Loss = {dsn_ce_loss: 0.1446, ce_loss: 0.1275, loss: 0.1853}

2020-02-20 21:19:10,006 INFO [fcn_segmentor.py, 161] Test Time 403.179s, (0.806) Loss = {dsn_ce_loss: 0.1737, ce_loss: 0.1571, loss: 0.2265}

2020-02-20 21:19:10,008 INFO [fcn_segmentor.py, 162] Mean IOU: 0.7380601712549701

2020-02-20 21:19:10,008 INFO [fcn_segmentor.py, 163] Pixel ACC: 0.948288297816425

2020-02-20 21:19:10,012 INFO [controller.py, 51] Training end...

[donnyyou]

The backbone is not the resnet with deepbase. The code may exist some error. I will check it soon!

[donnyyou]

I guess the pretrained model you downloaded is not the right one.

[ianz27]

I just download the 3x3-Res101 backbone(https://drive.google.com/file/d/1bUzCKazlh8ElGVYWlABBAb0b0uIqFgtR/view
), is it NOT the right one ?