holmesshuan / location-aware-upsampling-for-semantic-segmentation Goto Github PK
View Code? Open in Web Editor NEWThe Pytorch implementation of "Location-aware Upsampling for Semantic Segmentation" (LaU)
License: BSD 2-Clause "Simplified" License
The Pytorch implementation of "Location-aware Upsampling for Semantic Segmentation" (LaU)
License: BSD 2-Clause "Simplified" License
How to import the LAU which contains" LAU.location_determined_upsampling_forward"?
Hi @HolmesShuan ,
When training with modified encnet_res50_ade20k_train.sh, it cannot run. I only modified CUDA_VISIBLE_DEVICES=1,2
and --batch-size 8
, is there any suggested fix for me?
And what's wrong with my encnet_res50_ade20k_train.sh? Thanks.
#!/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
It raises ./encnet_res50_ade20k_train.sh: line 3: 49054 Segmentation fault after initializing the model and dataloader.
/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
Where is the ‘LAU.location_aware_upsampling_forward’ in location_aware_upsampling_func.py please?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.