Comments (11)
From your information you only compile bbox cython module with python 3.7, make sure you also use python 3.7 when you run experiments.
from upsnet.
Also please note that config files w/o 4gpu suffix are with horovod in distributed setting
from upsnet.
�We only have 1 GPU in our environment now. Is it still compatible with the distributed setting?
from upsnet.
Then please edit the 4gpu config, reduce lr by 4x / enlarge #iter by 4x, etc. BTW I don't think you can run coco dataset w/ 1 GPU in a acceptable time, please try cityscapes instead.
from upsnet.
I am not so sure to make the setting upsnet_resnet50_cityscapes_4gpu.yaml to fit my current environment with only 1 GPU. I have done the change below.
====
train:
gpus: '0,1,2,3' -> '0'
lr: 0.005 -> 0.00125
max_iteration: 48000 -> 192000
decay_iteration:
- 36000 -> 144000
warmup_iteration: 1500 -> 6000
====
test:
test_iteration: 48000 -> 192000
====
Did I miss anything? Thanks.
from upsnet.
looks good to me
from upsnet.
I know training takes a long time. Could you please give me a rough time how long it may take to finish training a model using only 1 GPU based on the above setting? Thank you!
from upsnet.
It will take ~3 days to train on 1 1080Ti GPU
from upsnet.
I see. What if I don't need a model as accurate as your best one? Could I trade off performance for less training time? For example, I can decrease the iteration numbers in order to get a trained model more quickly, which may have lower accuracy. If this is acceptable, what parameters I can try first, iteration number or else? Thank you!
from upsnet.
You can reduce #iter, e.g. 72k/96k rather than 144k/192k
from upsnet.
兄弟请问怎么自定义自己的coco panoptic格式的数据集
from upsnet.
Related Issues (20)
- Why the PQ is not equal to SQ * RQ?
- Pan output exceeds number of classes
- Defining New Datasets in Cityscapes Format
- batch_size per gpu is limited to 1
- PQ calculation error HOT 2
- Segmentation fault (core dumped) HOT 1
- Can't generate Panoptic results, only Instance. HOT 3
- System and environment
- RuntimeError: DataLoader worker (pid 60087) is killed by signal: Killed. HOT 1
- Inference is slow when the classes is large.
- Getting NaN for loss/accuracy values on 4 GPU config file HOT 2
- Missing nvcc?
- AssertionError: Failed to read image
- How to infer one Image with COCO Config?
- TypeError: new(): invalid data type 'str'
- Panoptic head implementation
- RuntimeError: expected a Variable argument, but got list
- Dataset overview
- Shipments not recieved
- RuntimeError: CUDA error: no kernel image is available for execution on the device HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from upsnet.