Comments (3)
Yes , the training time significantly decreases with lower resolution images. I'm using 720x960 images and iteration time has decreased from 2.5 sec to 1.2 sec. I'm using 1080Ti.
from fast-semantic-segmentation.
Hey @heethesh, please excuse the delayed reply. @harora, thanks for the input. If you'd like to change the input size for inference, you can just do so with the flags in the export script.
For the training flow, you can change the input image size by specifying a cropping size within the training config. Look for the random_image_crop
field in the configs. When I had trained, I stuck with 713x713 input crops for PSPNet and 1025x1025 for ICNet. From what I remember from the papers, the author suggests that you use as large of an input size as possible for performance. However, as expected, the computation increases significantly when training on larger images. In terms of inference, same rule will apply in terms of saving computation.
If you are not talking about crop size, but the actual size of the input image fetched from the TFRecord - there is currently a bug where I have hardcoded the cityscapes input image size of 1024x2048 in the dataset_builder
. Hoping to do some cleanup this weekend or next and fix this so you can use whatever size you like.
from fast-semantic-segmentation.
Hey @heethesh, I am sorry for the delayed update. I have not had the chance to work on this project for awhile but recent provided a larger update. I thought I would update this issue incase anyone else stumbles upon this.
With 42c6bbe, the dataset builder should now be able to parse datasets with TFRecords that have images that are not the standard 1024x2048 found in Cityscapes. I removed these hardcoded values. Let me know if you have any other issues.
from fast-semantic-segmentation.
Related Issues (20)
- For c++ pb HOT 6
- I'd like to inference pictures with a different size, what should I do? HOT 1
- How to execute the sample code? HOT 2
- ImportError HOT 2
- Using multi-modal data for training HOT 1
- Help: Convert ICNET_0.5 to onnx file HOT 5
- I cannot compress the model HOT 7
- Could not find pipeline.config in Pre-trained ICNet and PSPNet Models archives HOT 1
- ImportError: cannot import name 'hyperparams_pb2'
- MORE INFO ON LICENSE
- Consult for help HOT 2
- For running and using the inference.py script, the model.ckpt file is needed but it is not available. can you help me here with this issue?
- Error during evaluation - used PASCAL VOC dataset HOT 1
- ImportError: cannot import name 'pipeline_pb2'
- How to increase the frame rate HOT 1
- where is create_cityscapes_tfrecord.py HOT 1
- could anybody share a working setup please?
- Cannot import name 'input_reader_pb2' from 'protos'
- Error while loading checkpoint when training
- License info
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 fast-semantic-segmentation.