holmesshuan / location-aware-upsampling-for-semantic-segmentation Goto Github PK

#!/bin/bash

CUDA_VISIBLE_DEVICES=1,2 python train.py --dataset ade20k --model encnet --dilated --aux --se-loss --offset-loss --batch-size 8 --backbone resnet50 --checkname encnet_resnet50_ade20k_train --no-val --offset-weight 0.3 --location-weight 0.1 --up-factor 4 --batch-size-per-gpu 4 --bottleneck-channel 128 --offset-branch-input-channel 512 --category 150 --base-size 520 --crop-size 480 --downsampled-input-size 60 --epochs 180 --lr 0.004

/gs/home/jj/anaconda/envs/LaUPy35/lib/python3.5/site-packages/torch/nn/_reduction.py:49: UserWarning: size_average and reduce args will be deprecated, please use reduction='mean' instead.
  warnings.warn(warning.format(ret))
Using poly LR Scheduler!
Starting Epoch: 0
Total Epoches: 180
  0%|                                                                                                     | 0/2526 [00:00<?, ?it/s]
=>Epoches 0, learning rate = 0.0040,                 previous best = 0.0000


./encnet_res50_ade20k_train.sh: line 3: 49054 Segmentation fault     
CUDA_VISIBLE_DEVICES=1,2 python train.py --dataset ade20k --model encnet --dilated --aux --se-loss --offset-loss --batch-size 8 --backbone resnet50 --checkname encnet_resnet50_ade20k_train --no-val --offset-weight 0.3 --location-weight 0.1 --up-factor 4 --batch-size-per-gpu 4 --bottleneck-channel 128 --offset-branch-input-channel 512 --category 150 --base-size 520 --crop-size 480 --downsampled-input-size 60 --epochs 180 --lr 0.004